# Embed a SLNG voice agent on your website
Source: https://docs.slng.ai/agents/embed-web

Add a browser-based voice session with a SLNG voice agent to any web page using LiveKit, a React frontend, and a backend proxy that hides your SLNG key.

You can let visitors talk to an SLNG voice agent directly in the browser. You need a small backend to create the web session (keeps your SLNG key off the client) and a frontend that connects to LiveKit for real-time audio.

## Placeholders

The snippets below use these placeholders. Replace them with your own values before running the code.

| Placeholder     | Replace with                                                          |
| --------------- | --------------------------------------------------------------------- |
| `SLNG_API_KEY`  | An SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys) |
| `SLNG_AGENT_ID` | The ID of a configured [Voice Agent](/voice-agents)                   |

## Prerequisites

* A configured [Voice Agent](/voice-agents) with its agent ID
* An SLNG key (get one at [app.slng.ai](https://app.slng.ai/api-keys))
* A backend you can deploy server-side code to (Node.js, Deno, Python, etc.)
* A frontend project with React (the examples below use React, but the LiveKit client SDK works with any framework)

## How it works

```mermaid theme={null}
sequenceDiagram
    participant Browser
    participant Backend as Your backend
    participant SLNG as Voice Agents API
    participant LK as LiveKit room

    Browser->>Backend: POST /api/session
    Backend->>SLNG: POST /v1/agents/SLNG_AGENT_ID/web-sessions
    SLNG-->>Backend: livekit_url + livekit_token
    Backend-->>Browser: livekit_url + livekit_token
    Browser->>LK: Connect (token)
    Browser->>LK: Publish mic audio
    LK-->>Browser: Agent audio + transcripts
```

1. The browser asks your backend to start a session.
2. Your backend calls the Voice Agents web-sessions endpoint and forwards the LiveKit credentials back.
3. The browser connects to the LiveKit room, publishes the mic, and plays the agent's audio.

## Step 1: Create a backend endpoint

Your backend proxies the Voice Agents API so the SLNG key never reaches the browser.

<Warning>
  Never call the Voice Agents API directly from client-side code. Your `SLNG_API_KEY`
  must stay server-side.
</Warning>

The only call you need is:

```
POST https://api.agents.slng.ai/v1/agents/SLNG_AGENT_ID/web-sessions
```

<CodeGroup>
  ```javascript Node.js (Express) theme={null}
  import express from "express";

  const app = express();
  app.use(express.json());

  const SLNG_API_KEY = process.env.SLNG_API_KEY;
  const SLNG_AGENT_ID = process.env.SLNG_AGENT_ID;

  app.post("/api/session", async (req, res) => {
    const response = await fetch(
      `https://api.agents.slng.ai/v1/agents/${SLNG_AGENT_ID}/web-sessions`,
      {
        method: "POST",
        headers: {
          "Content-Type": "application/json",
          Authorization: `Bearer ${SLNG_API_KEY}`,
        },
        body: JSON.stringify({
          arguments: {},
          ...(req.body.participant_name
            ? { participant_name: req.body.participant_name }
            : {}),
        }),
      }
    );

    const data = await response.json();
    if (!response.ok) {
      return res.status(response.status).json({ error: "SLNG error", details: data });
    }
    res.json(data);
  });

  app.listen(3001);
  ```

  ```python Python (FastAPI) theme={null}
  import os
  import httpx
  from fastapi import FastAPI
  from pydantic import BaseModel

  app = FastAPI()

  SLNG_API_KEY = os.environ["SLNG_API_KEY"]
  SLNG_AGENT_ID = os.environ["SLNG_AGENT_ID"]

  class SessionRequest(BaseModel):
      participant_name: str | None = None

  @app.post("/api/session")
  async def create_session(body: SessionRequest):
      async with httpx.AsyncClient() as client:
          payload = {"arguments": {}}
          if body.participant_name:
              payload["participant_name"] = body.participant_name

          r = await client.post(
              f"https://api.agents.slng.ai/v1/agents/{SLNG_AGENT_ID}/web-sessions",
              headers={
                  "Content-Type": "application/json",
                  "Authorization": f"Bearer {SLNG_API_KEY}",
              },
              json=payload,
          )
      return r.json()
  ```
</CodeGroup>

The response includes the fields you need for the frontend:

```json theme={null}
{
  "livekit_url": "wss://...",
  "livekit_token": "...",
  "call_id": "...",
  "max_session_seconds": 300
}
```

## Step 2: Install the LiveKit client SDK

```bash theme={null}
npm install livekit-client
```

## Step 3: Connect to the LiveKit room

Call your backend to get a session, then connect to the room:

```tsx theme={null}
import { Room, RoomEvent, createLocalAudioTrack } from "livekit-client";

async function startSession() {
  // 1. Get session credentials from your backend
  const res = await fetch("/api/session", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ participant_name: "visitor" }),
  });
  const session = await res.json();

  // 2. Create and connect to the LiveKit room
  const room = new Room({ adaptiveStream: true, dynacast: true });
  await room.connect(session.livekit_url, session.livekit_token);

  // 3. Publish your microphone
  const micTrack = await createLocalAudioTrack();
  await room.localParticipant.publishTrack(micTrack);

  return { room, micTrack, session };
}
```

<Tip>
  The browser will prompt the user for microphone access on `createLocalAudioTrack()`.
  If your page is not served over HTTPS, most browsers will block the request.
</Tip>

## Step 4: Play the agent's audio

Attach the agent's remote audio track to the DOM so the browser plays it:

```tsx theme={null}
room.on(RoomEvent.TrackSubscribed, (track) => {
  if (track.kind !== "audio") return;
  const el = track.attach();
  el.autoplay = true;
  document.body.appendChild(el);
});

room.on(RoomEvent.TrackUnsubscribed, (track) => {
  track.detach().forEach((el) => el.remove());
});
```

## Step 5: Show live transcripts

Transcript updates arrive over a LiveKit data channel on the `slng.transcript.v1` topic:

```tsx theme={null}
const TRANSCRIPT_TOPIC = "slng.transcript.v1";

room.on(RoomEvent.DataReceived, (payload, _participant, _kind, topic) => {
  if (topic !== TRANSCRIPT_TOPIC) return;

  const msg = JSON.parse(new TextDecoder().decode(payload));

  if (msg.type === "conversation_item_added" && msg.item) {
    const { id, role, content, created_at } = msg.item;
    const text = Array.isArray(content) ? content.join("\n") : String(content);
    // Append { id, role, content: text, created_at } to your transcript state
  }
});
```

Each transcript item has:

| Field        | Description                                       |
| ------------ | ------------------------------------------------- |
| `id`         | Unique message ID (use to deduplicate)            |
| `role`       | `"user"` or `"assistant"`                         |
| `content`    | The transcribed text (string or array of strings) |
| `created_at` | Timestamp                                         |

## Step 6: Add mute and disconnect controls

```tsx theme={null}
// Toggle mute
async function toggleMute(micTrack, muted) {
  if (muted) {
    await micTrack.unmute();
  } else {
    await micTrack.mute();
  }
  return !muted;
}

// End the session
async function disconnect(room, micTrack) {
  micTrack.stop();
  await room.disconnect();
}
```

## Step 7: Detect who is speaking

The active-speakers event tells you when the agent is talking, so you can drive a visual indicator or avatar animation:

```tsx theme={null}
room.on(RoomEvent.ActiveSpeakersChanged, (speakers) => {
  const agentIsSpeaking = speakers.some(
    (p) => p.identity !== room.localParticipant.identity
  );
  // Update your UI based on agentIsSpeaking
});
```

## Optional: Add a visual persona

A voice-only interface gives users no visual cue about what the agent is doing. Adding an animated persona (an orb, waveform, or avatar) makes the experience feel more responsive. Two ready-made libraries work well here:

<CardGroup>
  <Card title="Vercel AI SDK Persona" href="https://elements.ai-sdk.dev/components/persona">
    A React component with built-in states: `idle`, `listening`, `speaking`, `thinking`. Drop it in and map LiveKit events to states.
  </Card>

  <Card title="ElevenLabs Conversational UI" href="https://ui.elevenlabs.io/docs/components">
    Orb and avatar components designed for voice interfaces, with audio-reactive animations.
  </Card>
</CardGroup>

To wire either library up, map your session and LiveKit events to persona states:

```tsx theme={null}
// Derive a persona state from your session + LiveKit events
function getPersonaState({ status, muted, agentIsSpeaking }) {
  if (status === "connecting") return "idle";
  if (status === "ended") return "idle";
  if (agentIsSpeaking) return "speaking";
  if (muted) return "thinking";
  return "listening";
}

// Update on active-speaker changes (Step 7)
room.on(RoomEvent.ActiveSpeakersChanged, (speakers) => {
  const agentIsSpeaking = speakers.some(
    (p) => p.identity !== room.localParticipant.identity
  );
  setPersonaState(getPersonaState({ status, muted, agentIsSpeaking }));
});
```

## Putting it all together

A minimal React component with all the steps above wired together:

```tsx theme={null}
import { useEffect, useRef, useState, useCallback } from "react";
import {
  Room,
  RoomEvent,
  createLocalAudioTrack,
  type LocalAudioTrack,
  type RemoteTrack,
} from "livekit-client";

const TRANSCRIPT_TOPIC = "slng.transcript.v1";

interface SessionData {
  livekit_url: string;
  livekit_token: string;
  call_id: string;
  max_session_seconds: number;
}

interface TranscriptItem {
  id: string;
  role: "user" | "assistant";
  content: string;
}

export default function VoiceSession() {
  const [status, setStatus] = useState<"idle" | "connecting" | "active" | "ended">("idle");
  const [muted, setMuted] = useState(false);
  const [transcript, setTranscript] = useState<TranscriptItem[]>([]);
  const roomRef = useRef<Room | null>(null);
  const micRef = useRef<LocalAudioTrack | null>(null);

  const start = useCallback(async () => {
    setStatus("connecting");

    // Get session from your backend
    const res = await fetch("/api/session", {
      method: "POST",
      headers: { "Content-Type": "application/json" },
      body: JSON.stringify({}),
    });
    const session: SessionData = await res.json();

    const room = new Room({ adaptiveStream: true, dynacast: true });
    roomRef.current = room;

    // Play agent audio
    room.on(RoomEvent.TrackSubscribed, (track: RemoteTrack) => {
      if (track.kind !== "audio") return;
      const el = track.attach() as HTMLAudioElement;
      el.autoplay = true;
      document.body.appendChild(el);
    });

    room.on(RoomEvent.TrackUnsubscribed, (track: RemoteTrack) => {
      track.detach().forEach((el) => el.remove());
    });

    // Transcript
    room.on(
      RoomEvent.DataReceived,
      (payload: Uint8Array, _p: unknown, _k: unknown, topic?: string) => {
        if (topic !== TRANSCRIPT_TOPIC) return;
        try {
          const msg = JSON.parse(new TextDecoder().decode(payload));
          if (msg.type === "conversation_item_added" && msg.item) {
            const { id, role, content } = msg.item;
            const text = Array.isArray(content) ? content.join("\n") : String(content);
            setTranscript((prev) =>
              prev.find((t) => t.id === id) ? prev : [...prev, { id, role, content: text }]
            );
          }
        } catch {
          // ignore malformed messages
        }
      }
    );

    room.on(RoomEvent.Disconnected, () => setStatus("ended"));

    await room.connect(session.livekit_url, session.livekit_token);

    const micTrack = await createLocalAudioTrack();
    micRef.current = micTrack;
    await room.localParticipant.publishTrack(micTrack);

    setStatus("active");
  }, []);

  const toggleMute = async () => {
    if (!micRef.current) return;
    muted ? await micRef.current.unmute() : await micRef.current.mute();
    setMuted((m) => !m);
  };

  const disconnect = useCallback(async () => {
    micRef.current?.stop();
    micRef.current = null;
    await roomRef.current?.disconnect();
    roomRef.current = null;
    setStatus("ended");
  }, []);

  // Cleanup on unmount
  useEffect(() => {
    return () => {
      micRef.current?.stop();
      roomRef.current?.disconnect();
    };
  }, []);

  return (
    <div>
      {status === "idle" && <button onClick={start}>Start conversation</button>}
      {status === "connecting" && <p>Connecting…</p>}

      {status === "active" && (
        <div>
          <button onClick={toggleMute}>{muted ? "Unmute" : "Mute"}</button>
          <button onClick={disconnect}>End call</button>
        </div>
      )}

      {status === "ended" && <p>Session ended.</p>}

      <ul>
        {transcript.map((item) => (
          <li key={item.id}>
            <strong>{item.role}:</strong> {item.content}
          </li>
        ))}
      </ul>
    </div>
  );
}
```

## Next steps

* Set up your agent with custom prompts and tools in the [Dashboard](/dashboard/agent-infra)
* See the [Voice Agents API](/voice-agents) for agent configuration options
* Add phone call support with [Telephony](/dashboard/telephony)
* Add a visual persona with [Vercel AI SDK](https://elements.ai-sdk.dev/components/persona) or [ElevenLabs UI](https://ui.elevenlabs.io/docs/components)


# LiveKit plugin for SLNG
Source: https://docs.slng.ai/agents/livekit-plugin

Use the livekit-plugins-slng Python package to connect LiveKit Agents to any STT or TTS model on the SLNG platform with a single configuration switch.

`livekit-plugins-slng` adds STT and TTS adapters for [LiveKit Agents](https://docs.livekit.io/agents/). It lets you use any model on the SLNG platform from within a LiveKit agent.

## Prerequisites

* Python 3.10+
* `livekit-agents>=1.5.1`
* A [LiveKit Agents](https://docs.livekit.io/agents/) project
* An SLNG key (get one at [app.slng.ai](https://app.slng.ai/api-keys))

## Installation

```bash theme={null}
uv add livekit-plugins-slng
# or
pip install livekit-plugins-slng
```

## Credentials

You need an SLNG key. The plugin reads it from the `SLNG_API_KEY` environment variable automatically:

```bash theme={null}
export SLNG_API_KEY="your-slng-api-key"
```

You can also pass it explicitly via `api_key`:

```python theme={null}
stt = slng.STT(api_key="your-slng-api-key", model="deepgram/nova:3")
```

<Note>
  `slng.STT` also accepts a legacy `api_token=` alias, but it is deprecated.
  Use `api_key` in new code.
</Note>

## Quickstart

Create an STT and TTS instance, then pass them to your LiveKit agent session:

```python theme={null}
from livekit.plugins import slng

stt = slng.STT(
    api_key="your-slng-api-key",
    model="deepgram/nova:3",
    region_override="eu-north-1",
    language="en",
)

tts = slng.TTS(
    api_key="your-slng-api-key",
    model="deepgram/aura:2",
    region_override=["eu-north-1", "us-east-1"],
    voice="aura-2-thalia-en",
    language="en",
)
```

## Region override

The plugin supports platform region routing through the `region_override` option on both `STT` and `TTS`.
This maps directly to the platform's `X-Region-Override` header.

You can pass either a single region:

```python theme={null}
stt = slng.STT(
    api_key="your-slng-api-key",
    model="deepgram/nova:3",
    region_override="eu-north-1",
)
```

Or multiple preferred regions in priority order:

```python theme={null}
tts = slng.TTS(
    api_key="your-slng-api-key",
    model="deepgram/aura:2",
    voice="aura-2-thalia-en",
    region_override=["eu-north-1", "us-east-1"],
)
```

See the full region list and override behavior at [docs.slng.ai/region-override](https://docs.slng.ai/region-override).

## Full voice agent example

This example wires up STT, TTS, and VAD into a complete LiveKit agent that greets the user on join:

```python theme={null}
from livekit.agents import Agent, AgentSession, JobContext, WorkerOptions, cli
from livekit.plugins import silero, slng

SLNG_API_KEY = "your-slng-api-key"


class MyAgent(Agent):
    async def on_enter(self):
        await self.session.say("Hello! How can I help?")


async def entrypoint(ctx: JobContext):
    await ctx.connect()

    stt = slng.STT(
        api_key=SLNG_API_KEY,
        model="deepgram/nova:3",
        language="en",
        sample_rate=16000,
        enable_partial_transcripts=True,
    )

    tts = slng.TTS(
        api_key=SLNG_API_KEY,
        model="deepgram/aura:2",
        voice="aura-2-thalia-en",
        language="en",
        sample_rate=24000,
    )

    # `turn_detection` and `allow_interruptions` still work in livekit-agents 1.5.x
    # but will be removed in v2.0. Use `turn_handling=TurnHandlingOptions(...)` going forward.
    session = AgentSession(
        stt=stt,
        tts=tts,
        vad=silero.VAD.load(),
        turn_detection="vad",
        allow_interruptions=True,
    )

    await session.start(agent=MyAgent(), room=ctx.room)


if __name__ == "__main__":
    cli.run_app(WorkerOptions(entrypoint_fnc=entrypoint))
```

## Model identifiers

Models follow the format `provider/model:variant`. Prefix with `slng/` to target an SLNG-hosted instance:

```
provider/model:variant          # third-party passthrough
slng/provider/model:variant     # SLNG-hosted
```

Examples:

```python theme={null}
model="deepgram/nova:3"              # Deepgram Nova 3 (passthrough)
model="slng/deepgram/nova:3-en"      # SLNG-hosted Deepgram Nova 3, English
model="elevenlabs/eleven-flash:2.5"  # ElevenLabs Flash v2.5 (passthrough)
```

See the [Models](/models/index) page for the full list of available models.

## STT reference

`slng.STT` streams speech-to-text over WebSocket. It supports multi-endpoint failover.

### Constructor

```python theme={null}
stt = slng.STT(
    api_key="your-slng-api-key",          # Required. SLNG API key. Falls back to SLNG_API_KEY env var.
    model="deepgram/nova:3",              # Model identifier. Default: "deepgram/nova:3"
    language="en",                         # Language code. Default: "en"
    sample_rate=16000,                     # Audio sample rate in Hz. Default: 16000
    encoding="pcm_s16le",                  # Audio encoding: "pcm_s16le" or "pcm_mulaw". Default: "pcm_s16le"
    buffer_size_seconds=0.064,             # Audio buffer size in seconds. Default: 0.064
    enable_partial_transcripts=True,       # Enable interim results. Default: True
    enable_diarization=False,              # Enable speaker identification. Default: False
    min_speakers=None,                     # Minimum speakers for diarization. Default: None
    max_speakers=None,                     # Maximum speakers for diarization. Default: None
    vad_threshold=0.5,                     # Voice activity detection threshold. Default: 0.5
    vad_min_silence_duration_ms=300,       # Minimum silence for VAD (ms). Default: 300
    vad_speech_pad_ms=30,                  # Speech padding for VAD (ms). Default: 30
    model_endpoint=None,                   # Optional explicit WebSocket endpoint URL
    model_endpoints=None,                  # Optional list of failover endpoints
    slng_base_url="api.slng.ai",           # Gateway host override (self-hosted or staging)
    region_override=None,                  # Optional region override, sent as X-Region-Override
    http_session=None,                     # Optional reused aiohttp.ClientSession
    # **model_options                      # Arbitrary model-specific kwargs (see below)
)
```

Any additional keyword arguments are forwarded as model-specific options. For example, `target_language_code="hi-IN"` to override language normalization for Sarvam STT models, or `enable_diarization=True` for Deepgram Nova models.

### Endpoint failover

Pass a list of endpoints to `model_endpoints`. If the first one fails, the plugin tries the next in order:

```python theme={null}
stt = slng.STT(
    api_key=SLNG_API_KEY,
    model_endpoints=[
        "wss://api.slng.ai/v1/stt/deepgram/nova:3",
        "wss://api.slng.ai/v1/stt/slng/deepgram/nova:3-en",
    ],
    language="en",
)
```

### Default endpoint

If `model_endpoint` is omitted, the plugin connects to:

```
wss://api.slng.ai/v1/stt/{model}
```

### Region override

To force routing toward one or more preferred platform regions, pass `region_override`.
This value is forwarded directly as the platform `X-Region-Override` header.

```python theme={null}
stt = slng.STT(
    api_key=SLNG_API_KEY,
    model="deepgram/nova:3",
    region_override=["eu-north-1", "us-east-1"],
)
```

See the full region list and override behavior at [docs.slng.ai/region-override](https://docs.slng.ai/region-override).

## TTS reference

`slng.TTS` streams text-to-speech over WebSocket with connection pooling.

### Constructor

```python theme={null}
tts = slng.TTS(
    api_key="your-slng-api-key",          # Required. SLNG API key. Falls back to SLNG_API_KEY env var.
    model="deepgram/aura:2",              # Model identifier. Default: "deepgram/aura:2"
    voice="aura-2-thalia-en",             # Voice identifier. Default: "default"
    language="en",                         # Language code. Default: "en"
    sample_rate=24000,                     # Audio sample rate in Hz. Default: 24000
    speed=1.0,                             # Speech speed multiplier. Default: 1.0
    model_endpoint=None,                   # Optional explicit WebSocket endpoint URL
    slng_base_url="api.slng.ai",           # Gateway host override (self-hosted or staging)
    region_override=None,                  # Optional region override, sent as X-Region-Override
    word_tokenizer=None,                   # Optional custom tokenize.WordTokenizer
    http_session=None,                     # Optional reused aiohttp.ClientSession
    # **model_options                      # Arbitrary model-specific kwargs (see below)
)
```

Additional keyword arguments are forwarded to the chosen model's init payload. Known keys by provider:

* **Rime Arcana**: `modelId`, `segment`, `speakingStyle`, `addBreathing`, `addDisfluencies`, `phonemizeBetweenBrackets`, `translateTo`.
* **Sarvam Bulbul**: `pace`, `temperature`, `output_audio_bitrate`, `min_buffer_size`, `max_chunk_length`, `target_language_code`.

### Streaming vs batch

* `tts.stream()` sends text word-by-word and returns audio chunks in real time. Use this for voice agents.
* `tts.synthesize(text)` does one-shot synthesis. Works fine for previews, but `stream()` is better for interactive agents.

### Default endpoint

If `model_endpoint` is omitted, the plugin connects to:

```
wss://api.slng.ai/v1/tts/{model}
```

### Region override

`TTS` supports the same `region_override` option and forwards it to the platform as `X-Region-Override`.

See the full region list and override behavior at [docs.slng.ai/region-override](https://docs.slng.ai/region-override).

### Voice selection

Pick a voice that matches your chosen model. See the [Voices](/voices/deepgram-aura) pages for what's available per provider.

## Provider notes

### Sarvam Bulbul v3 TTS

Works out of the box. The plugin auto-normalizes language codes to BCP-47 on the wire. Pass `language="hi"`, the plugin sends `"hi-IN"` to Sarvam. To override the normalization (e.g. force a different target language), pass `target_language_code="..."` in `model_options`.

### Sarvam Saaras v3 STT

Saaras on SLNG is HTTP-only (no WebSocket endpoint) and is therefore **not supported** by this plugin's realtime streaming path. For Hindi STT in a voice agent, use `slng/deepgram/nova:3-hi` or `slng/deepgram/nova:3-multi` instead.

### Rime Arcana

Requires a `voice` (speaker) that matches the chosen language. Passing `voice="default"` auto-resolves to a reasonable default per language.

<Note>
  The plugin outputs `linear16` PCM audio internally and registers itself with
  LiveKit on import. Both `STT` and `TTS` authenticate with `api_key`.
</Note>

<Tip>
  Most new SLNG platform models work without plugin updates, but providers with
  non-standard WebSocket message formats may require plugin support (for
  example, Sarvam Bulbul needed nested `data.audio` parsing).
</Tip>

## Next steps

* Browse available [Models](/models/index) for STT and TTS
* Check the [Voices](/voices/deepgram-aura) pages for voice options per provider
* See [Voice Agents](/voice-agents) for the SLNG-managed agents API


# Pipecat plugin for SLNG
Source: https://docs.slng.ai/agents/pipecat-plugin

Use the pipecat-slng Python package to connect a Pipecat pipeline to any STT or TTS model on the SLNG gateway by swapping a single model string.

`pipecat-slng` adds STT and TTS services for [Pipecat](https://github.com/pipecat-ai/pipecat). It routes
your pipeline through the SLNG gateway, so you can use any STT or TTS model on SLNG — Deepgram,
ElevenLabs, Rime, Sarvam, and more — behind one API key. Swap the `model` string to switch provider; no
other code changes needed.

<Note>
  Tested with Pipecat v1.3.0. [BYOK](#bring-your-own-key-byok) requires `pipecat-slng` 0.4.0 or later.
</Note>

## Prerequisites

* Python 3.11+
* `pipecat-ai>=1.3.0`
* A [Pipecat](https://github.com/pipecat-ai/pipecat) project
* An SLNG API key (get one at [app.slng.ai](https://app.slng.ai/api-keys))

## Installation

```bash theme={null}
uv add pipecat-slng
# or
pip install pipecat-slng
```

## Credentials

You need an SLNG API key. Read it from the `SLNG_API_KEY` environment variable:

```bash theme={null}
export SLNG_API_KEY="your-slng-api-key"
```

Then pass it to each service via `api_key`:

```python theme={null}
import os

from pipecat_slng import SlngSTTService

stt = SlngSTTService(
    api_key=os.getenv("SLNG_API_KEY"),
    model="slng/deepgram/nova:3-en",
)
```

## Quickstart

Create an STT and TTS service, then add them to your Pipecat pipeline:

```python theme={null}
import os

from pipecat_slng import SlngSTTService, SlngTTSService

stt = SlngSTTService(
    api_key=os.getenv("SLNG_API_KEY"),
    model="slng/deepgram/nova:3-en",
)

tts = SlngTTSService(
    api_key=os.getenv("SLNG_API_KEY"),
    model="slng/deepgram/aura:2-en",
    voice="aura-2-thalia-en",
)
```

`SlngSTTService` and `SlngTTSService` stream over WebSocket: low latency, with mid-utterance
interruption support. Common runtime knobs are top-level keyword arguments (`language`, `speed`,
`enable_vad`, `enable_partials`). For richer overrides, pass a `SlngSTTSettings(...)` or
`SlngTTSSettings(...)` to `settings=`.

## Region routing

Both services support gateway region routing. Pin requests to a specific datacenter with
`region_override`, or constrain them to a broad geographic zone with `world_part_override`. When both
are set, `region_override` wins.

```python theme={null}
stt = SlngSTTService(
    api_key=os.getenv("SLNG_API_KEY"),
    model="slng/deepgram/nova:3-en",
    region_override="eu-north-1",      # ap-southeast-2 | eu-north-1 | us-east-1
    world_part_override="eu",          # ap | eu | na
)
```

The WebSocket services send these as the `X-Region-Override` and `X-World-Part-Override` headers; the
HTTP service (below) sends them as the `region` and `world-part` query parameters.

See the full region list and override behavior at [docs.slng.ai/region-override](https://docs.slng.ai/region-override).

## Bring your own key (BYOK)

If you already have a contract with an upstream provider, pass your own provider key via
`provider_key`. All three services forward it as the `X-Slng-Provider-Key` header — on the WebSocket
upgrade for the streaming services, on each request for `SlngHttpTTSService` — so the provider bills
your account directly and no SLNG audio-minute fees apply, while the SLNG cache still applies on top.
See [Bring your own key](/execution-layer/byok) for caching behavior and the supported provider list.

```python theme={null}
import os

from pipecat_slng import SlngSTTService, SlngTTSService

stt = SlngSTTService(
    api_key=os.getenv("SLNG_API_KEY"),
    model="deepgram/nova:3",            # external route — no slng/ prefix
    provider_key=os.getenv("SLNG_PROVIDER_KEY"),
)

tts = SlngTTSService(
    api_key=os.getenv("SLNG_API_KEY"),
    model="deepgram/aura:2",            # external route — no slng/ prefix
    voice="aura-2-thalia-en",
    provider_key=os.getenv("SLNG_PROVIDER_KEY"),
)
```

<Warning>
  BYOK only works on **external** catalog routes — model strings without the `slng/` prefix, such as
  `deepgram/nova:3` or `deepgram/aura:2`. SLNG-hosted `slng/...` routes reject the header with an
  HTTP 400 ("BYOK is only supported for external STT/TTS routes").
</Warning>

If the upstream provider rejects your key, the failure surfaces as a `backend_connection_failed`
error frame over WebSocket, or as the upstream 401/403 with the `X-Slng-Auth-Source: client_key`
response header over HTTP. Since `pipecat-slng` 0.4.0, WebSocket connect-rejection errors include the
server's response body, so a misrouted BYOK request reports the reason rather than a bare `HTTP 400`.

## Full voice agent example

A complete cascade pipeline — Speech-to-Text → LLM → Text-to-Speech — using SLNG for STT and TTS and
OpenAI for the LLM. The bot introduces itself when a client connects:

```python theme={null}
import os

from dotenv import load_dotenv

from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMRunFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.llm_response_universal import (
    LLMContextAggregatorPair,
    LLMUserAggregatorParams,
)
from pipecat.runner.types import RunnerArguments, SmallWebRTCRunnerArguments
from pipecat.services.openai.responses.llm import OpenAIResponsesLLMService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams

from pipecat_slng import SlngSTTService, SlngTTSService

load_dotenv(override=True)


async def run_bot(transport: BaseTransport):
    slng_api_key = os.environ["SLNG_API_KEY"]

    stt = SlngSTTService(
        api_key=slng_api_key,
        model="slng/deepgram/nova:3-en",
        language=Language.EN,
        enable_vad=True,
        enable_partials=True,
        # region_override="eu-north-1",  # uncomment to pin to a datacenter
    )

    # Text-to-Speech (streaming WebSocket — low latency, supports interruption).
    # Deepgram Aura 2 supports `speed`; Rime / Sarvam don't (parameter-coverage
    # table on docs.slng.ai). Swap model= and voice= to change provider.
    tts = SlngTTSService(
        api_key=slng_api_key,
        model="slng/deepgram/aura:2-en",
        voice="aura-2-arcas-en",
        language=Language.EN,
        speed=1,
        # region_override="eu-north-1",
    )

    llm = OpenAIResponsesLLMService(
        api_key=os.getenv("OPENAI_API_KEY"),
        settings=OpenAIResponsesLLMService.Settings(
            model=os.getenv("OPENAI_MODEL", "gpt-4.1"),
            system_instruction=(
                "You are a helpful assistant in a voice conversation. "
                "Your responses will be spoken aloud, so avoid emojis, bullet points, "
                "or other formatting that can't be spoken."
            ),
        ),
    )

    context = LLMContext()
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
    )

    pipeline = Pipeline(
        [
            transport.input(),
            stt,
            user_aggregator,
            llm,
            tts,
            transport.output(),
            assistant_aggregator,
        ]
    )

    task = PipelineTask(
        pipeline,
        params=PipelineParams(enable_metrics=True, enable_usage_metrics=True),
    )

    @task.rtvi.event_handler("on_client_ready")
    async def on_client_ready(rtvi):
        context.add_message({"role": "user", "content": "Please introduce yourself."})
        await task.queue_frames([LLMRunFrame()])

    runner = PipelineRunner(handle_sigint=False)
    await runner.run(task)


async def bot(runner_args: RunnerArguments):
    match runner_args:
        case SmallWebRTCRunnerArguments():
            from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport

            transport = SmallWebRTCTransport(
                webrtc_connection=runner_args.webrtc_connection,
                params=TransportParams(audio_in_enabled=True, audio_out_enabled=True),
            )
            await run_bot(transport)


if __name__ == "__main__":
    from pipecat.runner.run import main

    main()
```

The full example, including the Daily transport branch, lives in
[`examples/bot.py`](https://github.com/slng-ai/pipecat-slng/blob/main/examples/bot.py). Run it with:

```bash theme={null}
cp .env.example .env   # set SLNG_API_KEY and OPENAI_API_KEY
uv run --extra example examples/bot.py
```

Then open `http://localhost:7860/client` and start talking. It uses the SmallWebRTC transport by
default; pass `-t daily` to use Daily instead (requires `pipecat-ai[daily]`). Setting
`SLNG_PROVIDER_KEY` (your own Deepgram key) in `.env` flips the example into
[BYOK](#bring-your-own-key-byok) mode on the external `deepgram/nova:3` / `deepgram/aura:2` routes.

## Model identifiers

Models follow the format `provider/model:variant`. Prefix with `slng/` to target an SLNG-hosted instance,
and suffix the language where the model exposes per-language variants:

```python theme={null}
model="slng/deepgram/nova:3-en"      # SLNG-hosted Deepgram Nova 3, English (STT)
model="slng/deepgram/aura:2-en"      # SLNG-hosted Deepgram Aura 2, English (TTS)
```

Model strings without the `slng/` prefix are **external** routes, proxied to the provider's own API:

```python theme={null}
model="deepgram/nova:3"              # Proxied to Deepgram Nova 3 (STT)
model="deepgram/aura:2"              # Proxied to Deepgram Aura 2 (TTS)
```

External routes are required for [BYOK](#bring-your-own-key-byok).

The plugin routes through the SLNG Unmute bridge, so the full list of models you can pass to `model=` is
the bridge's supported-models list — see [Supported models](/execution-layer/unified-api-models). Not every
model accepts every option (for example `speed` on TTS); check the
[parameter coverage](/execution-layer/unified-api-parameters) table before tuning.

## STT reference

`SlngSTTService` streams speech-to-text over WebSocket, connecting to
`wss://api.slng.ai/v1/bridges/unmute/stt/{model}`.

### Constructor

```python theme={null}
stt = SlngSTTService(
    api_key="your-slng-api-key",          # Required. SLNG API key.
    model="slng/deepgram/nova:3-en",      # Model identifier. Default: "slng/deepgram/nova:3-en"
    base_url="api.slng.ai",               # Gateway host (self-hosted or staging). Default: "api.slng.ai"
    encoding="linear16",                   # "linear16", "mp3", or "opus". Default: "linear16"
    sample_rate=None,                      # Audio sample rate in Hz. Default: the pipeline sample rate
    language=Language.EN,                  # Recognition language. Default: English
    enable_vad=True,                       # Enable server-side VAD. Default: True
    enable_partials=True,                  # Stream interim (partial) transcripts. Default: True
    region_override=None,                  # Pin to a datacenter, sent as X-Region-Override
    world_part_override=None,              # Constrain to a zone, sent as X-World-Part-Override
    provider_key=None,                     # Your own provider key (BYOK), sent as X-Slng-Provider-Key — external routes only
    settings=None,                         # Optional SlngSTTSettings for runtime updates
)
```

`Language` is imported from `pipecat.transcriptions.language`.

### Confidence filter

When the provider surfaces a confidence score, transcripts below `0.5` are dropped before reaching your
pipeline.

### Default endpoint

The plugin connects to:

```
wss://api.slng.ai/v1/bridges/unmute/stt/{model}
```

## TTS reference (streaming)

`SlngTTSService` streams text-to-speech over WebSocket, connecting to
`wss://api.slng.ai/v1/bridges/unmute/tts/{model}`. This is the recommended path for interactive voice
agents.

### Constructor

```python theme={null}
tts = SlngTTSService(
    api_key="your-slng-api-key",          # Required. SLNG API key.
    model="slng/deepgram/aura:2-en",      # Model identifier. Default: "slng/deepgram/aura:2-en"
    voice="aura-2-thalia-en",             # Voice identifier. Default: None (server default)
    base_url="api.slng.ai",               # Gateway host. Default: "api.slng.ai"
    encoding="linear16",                   # "linear16", "mp3", "opus", "mulaw", or "alaw". Default: "linear16"
    sample_rate=None,                      # Audio sample rate in Hz. Default: the pipeline sample rate
    language=Language.EN,                  # Synthesis language. Default: English
    speed=None,                            # Speech speed multiplier. Default: None (server default)
    region_override=None,                  # Pin to a datacenter, sent as X-Region-Override
    world_part_override=None,              # Constrain to a zone, sent as X-World-Part-Override
    provider_key=None,                     # Your own provider key (BYOK), sent as X-Slng-Provider-Key — external routes only
    settings=None,                         # Optional SlngTTSSettings for runtime updates
)
```

### Runtime settings updates

Changing `voice`, `speed`, or `language` mid-session (via Pipecat settings updates) reconnects the
WebSocket to re-run the init handshake. Expect a brief reconnect, not a silent no-op.

### Default endpoint

The plugin connects to:

```
wss://api.slng.ai/v1/bridges/unmute/tts/{model}
```

### Voice selection

Pick a voice that matches your chosen model. See the [Voices](/voices/deepgram-aura) pages for what's
available per provider.

## HTTP TTS (non-streaming fallback)

For simple request/response synthesis where streaming is not required, use `SlngHttpTTSService`. It
issues one HTTP `POST` per utterance and returns the full audio body in a single frame.

```python theme={null}
import os

from pipecat_slng import SlngHttpTTSService

tts = SlngHttpTTSService(
    api_key=os.getenv("SLNG_API_KEY"),
    model="slng/deepgram/aura:2-en",
    voice="aura-2-thalia-en",
)
```

<Warning>
  The HTTP bridge body accepts **only** `{text, voice}` — there is no `config` object. Encoding,
  `sample_rate`, `language`, and `speed` are therefore **not configurable over HTTP**; the server
  returns its default audio format. `language` and `speed` are kept for API parity with the WebSocket
  service but are not sent over the wire.
</Warning>

The service auto-detects WAV (decoded to raw PCM at the file's sample rate) and plain PCM (passed
through at the pipeline's sample rate). Compressed responses (MP3/Ogg) yield an `ErrorFrame` — use the
streaming `SlngTTSService` if you need codec control. Pass `aiohttp_session=` to reuse a shared
`aiohttp.ClientSession`; otherwise one is created internally.

Region routing on the HTTP service uses the `region` and `world-part` query parameters instead of
headers. [BYOK](#bring-your-own-key-byok) works here too: pass `provider_key` and it is sent as the
`X-Slng-Provider-Key` header on each request (external routes only).

## Good to know

<Note>
  Both WebSocket services output `linear16` PCM by default and authenticate with `api_key`. The package
  exports `SlngSTTService`, `SlngTTSService`, and `SlngHttpTTSService`, plus the `SlngSTTSettings` and
  `SlngTTSSettings` settings classes.
</Note>

<Tip>
  Prefer the streaming `SlngTTSService` for conversational agents — it supports mid-utterance
  interruption. Reserve `SlngHttpTTSService` for batch or non-interactive synthesis.
</Tip>

## Next steps

* Browse the [supported models](/execution-layer/unified-api-models) and [parameter coverage](/execution-layer/unified-api-parameters) for the Unmute bridge
* Read [Bring your own key](/execution-layer/byok) for BYOK caching behavior and supported providers
* Check the [Voices](/voices/deepgram-aura) pages for voice options per provider
* See [Voice Agents](/voice-agents) for the SLNG-managed agents API
* Using LiveKit instead? See the [LiveKit plugin](/agents/livekit-plugin)


# Get current account
Source: https://docs.slng.ai/api-reference/account/get-current-account

/api-reference/me/me.oas.json get /v1/me
Return the account, organization, and API key associated with the bearer token in the request. Use this to confirm which key is in use and which organization and plan tier it belongs to.



# Create agent
Source: https://docs.slng.ai/api-reference/agents/create-agent

/api-reference/agents/agents.oas.yaml post /v1/agents
Create a new voice agent.



# Delete agent
Source: https://docs.slng.ai/api-reference/agents/delete-agent

/api-reference/agents/agents.oas.yaml delete /v1/agents/{agent_id}
Soft-delete a voice agent.



# Duplicate agent
Source: https://docs.slng.ai/api-reference/agents/duplicate-agent

/api-reference/agents/agents.oas.yaml post /v1/agents/{agent_id}/duplicate
Create a server-side copy of an existing voice agent.

The duplicate copies the stored agent configuration, including prompts, models, tools,
template defaults, selected region, and outbound telephony settings.

The duplicate does not copy call history or the inbound connection. SLNG creates
and manages a runtime API key for the duplicated agent automatically.




# Get agent
Source: https://docs.slng.ai/api-reference/agents/get-agent

/api-reference/agents/agents.oas.yaml get /v1/agents/{agent_id}
Get a single voice agent by ID.



# List agents
Source: https://docs.slng.ai/api-reference/agents/list-agents

/api-reference/agents/agents.oas.yaml get /v1/agents
List all voice agents for your organisation.



# Replace agent
Source: https://docs.slng.ai/api-reference/agents/replace-agent

/api-reference/agents/agents.oas.yaml put /v1/agents/{agent_id}
Replace a voice agent (full update).



# Update agent (partial)
Source: https://docs.slng.ai/api-reference/agents/update-agent-partial

/api-reference/agents/agents.oas.yaml patch /v1/agents/{agent_id}
Partially update a voice agent.



# Cognigy STT
Source: https://docs.slng.ai/api-reference/bridges/cognigy-stt-bridge/cognigy-stt-bridge-http

POST /v1/bridges/cognigy/stt/{model_variant}
Transcribe audio via Cognigy Voice Gateway protocol bridge.



# Cognigy STT
Source: https://docs.slng.ai/api-reference/bridges/cognigy-stt-bridge/cognigy-stt-bridge-ws

Stream live audio to SLNG over the Cognigy Voice Gateway WebSocket protocol and receive real-time STT transcripts from any supported model.



# Cognigy TTS
Source: https://docs.slng.ai/api-reference/bridges/cognigy-tts-bridge/cognigy-tts-bridge-http

POST /v1/bridges/cognigy/tts/{model_variant}
Synthesize speech via Cognigy Voice Gateway protocol bridge.



# Cognigy TTS
Source: https://docs.slng.ai/api-reference/bridges/cognigy-tts-bridge/cognigy-tts-bridge-ws

Stream synthesized speech from SLNG over the Cognigy Voice Gateway WebSocket protocol using any supported text-to-speech model and voice.



# Jambonz STT
Source: https://docs.slng.ai/api-reference/bridges/jambonz-stt-bridge/jambonz-stt-bridge-http

POST /v1/bridges/jambonz/stt/{model_variant}
Transcribe audio via Jambonz custom STT protocol bridge. The model_variant path parameter specifies the target STT model (e.g., deepgram/nova:3, slng/openai/whisper:large-v3).



# Jambonz STT
Source: https://docs.slng.ai/api-reference/bridges/jambonz-stt-bridge/jambonz-stt-bridge-ws

Reference for the Jambonz custom WebSocket STT bridge channel, including init, audio, stop messages and the model_variant routing parameter.



# Jambonz TTS
Source: https://docs.slng.ai/api-reference/bridges/jambonz-tts-bridge/jambonz-tts-bridge-http

POST /v1/bridges/jambonz/tts/{model_variant}
Synthesize speech via Jambonz custom TTS protocol bridge. The model_variant path parameter specifies the target TTS model (e.g., deepgram/aura:2).



# Jambonz TTS
Source: https://docs.slng.ai/api-reference/bridges/jambonz-tts-bridge/jambonz-tts-bridge-ws

Reference for the Jambonz custom WebSocket TTS bridge channel, including stream, flush, stop messages, binary audio frames, and model_variant routing.



# Dispatch call
Source: https://docs.slng.ai/api-reference/calls/dispatch-call

/api-reference/agents/agents.oas.yaml post /v1/agents/{agent_id}/calls
Dispatch an outbound call for a voice agent.

Note: outbound calls require the agent to be configured with an outbound connection.




# Get call
Source: https://docs.slng.ai/api-reference/calls/get-call

/api-reference/agents/agents.oas.yaml get /v1/agents/{agent_id}/calls/{call_id}
Get details of a specific call.



# List calls
Source: https://docs.slng.ai/api-reference/calls/list-calls

/api-reference/agents/agents.oas.yaml get /v1/agents/{agent_id}/calls
List calls for a voice agent (paginated).



# API Reference
Source: https://docs.slng.ai/api-reference/overview

Every SLNG endpoint, grouped by capability: the Unified API, text-to-speech, speech-to-text, voice agents, batch, and orchestrator bridges.

Every SLNG endpoint, grouped by capability. Pick a section to see request and response details, or start with the Unified API to reach any provider through one request shape.

<CardGroup>
  <Card title="Unified API" icon="blend" href="/api-reference/unified-api/unmute-stt-bridge/unmute-stt-bridge-http">
    One request shape for every STT and TTS model. Swap providers by changing the URL. Includes parameter coverage and supported models.
  </Card>

  <Card title="Text-to-Speech" icon="audio-lines" href="/api-reference/tts/rime-arcana-v3/arcana-v3-english-http">
    Per-provider TTS endpoints over HTTP and WebSocket, plus pronunciation dictionaries.
  </Card>

  <Card title="Speech-to-Text" icon="ear" href="/api-reference/stt/deepgram-nova-3/nova-3-english-http">
    Per-provider STT endpoints for file transcription and real-time streaming.
  </Card>

  <Card title="Voice Agents" icon="bot" href="/api-reference/agents/list-agents">
    Create, configure, and dispatch SLNG voice agents, including outbound calls.
  </Card>

  <Card title="Batch" icon="https://mintcdn.com/slng/HKoD9TaAJTUAZCoE/images/providers/slng-icon.svg?fit=max&auto=format&n=HKoD9TaAJTUAZCoE&q=85&s=39ec73086f8c747b352b393a0200132c" href="/api-reference/batch">
    Submit and manage large transcription and synthesis jobs asynchronously.
  </Card>

  <Card title="Bridges" icon="cable" href="/api-reference/bridges/cognigy-stt-bridge/cognigy-stt-bridge-http">
    Connect Cognigy and Jambonz voice platforms to SLNG STT and TTS.
  </Card>
</CardGroup>


# Create web session
Source: https://docs.slng.ai/api-reference/sessions/create-web-session

/api-reference/agents/agents.oas.yaml post /v1/agents/{agent_id}/web-sessions
Create a browser session for a voice agent.

This is commonly used for in-browser testing without PSTN.




# Create batch job
Source: https://docs.slng.ai/api-reference/speechmatics/create-batch-job

/api-reference/batch/batch.oas.json post /v1/batch/jobs
Submit audio for asynchronous transcription. Supports file upload (`multipart/form-data`), URL input, and presigned S3 upload (`application/json`). For the presigned-upload flow, the first call (`mode: "presign"`) returns **200 OK** with an upload URL — the job is not created until step 3. All other submission paths return **202 Accepted** with `status: QUEUED`.



# Delete batch job
Source: https://docs.slng.ai/api-reference/speechmatics/delete-batch-job

/api-reference/batch/batch.oas.json delete /v1/batch/jobs/{jobId}
Delete a completed or failed job. Only jobs in a terminal status (`DONE` or `FAILED`) can be deleted.



# Get batch job
Source: https://docs.slng.ai/api-reference/speechmatics/get-batch-job

/api-reference/batch/batch.oas.json get /v1/batch/jobs/{jobId}
Returns the full details of a job (status, config, timestamps, error info). Poll until `status` reaches `DONE` or `FAILED`.



# Get batch job files
Source: https://docs.slng.ai/api-reference/speechmatics/get-batch-job-files

/api-reference/batch/batch.oas.json get /v1/batch/jobs/{jobId}/files
Returns signed download URLs for the input audio and the output transcripts of a completed job. Outputs are returned per available format (`json`, `txt`, `srt`); missing formats are omitted.



# List batch jobs
Source: https://docs.slng.ai/api-reference/speechmatics/list-batch-jobs

/api-reference/batch/batch.oas.json get /v1/batch/jobs
Returns a paginated list of jobs for your organization. Supports filtering by status, model, and submission date range, plus sorting.



# Nova 2
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-2/nova-2-http

POST /v1/stt/deepgram/nova:2
Transcribe audio using Deepgram Nova 2 with VAD and speaker diarization.

<HostingBanner type="thirdparty" />


# Nova 2
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-2/nova-2-ws

Stream real-time speech-to-text transcripts from Deepgram Nova 2 over WebSocket with voice activity detection, speaker diarization, and partial results.



# Nova 3 Medical
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3-medical/nova-3-medical-http

POST /v1/stt/deepgram/nova:3-medical
Transcribe medical audio using Deepgram Nova 3 Medical with specialized vocabulary.

<HostingBanner type="thirdparty" />


# Nova 3 Medical
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3-medical/nova-3-medical-ws

Stream real-time medical transcription from Deepgram Nova 3 Medical over WebSocket with healthcare-specific vocabulary, VAD, and speaker diarization.



# Nova 3 (English)
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-english-http

POST /v1/stt/slng/deepgram/nova:3-en
Transcribe English audio using SLNG-hosted Deepgram Nova 3.

<HostingBanner type="slng" />


# Nova 3 (English)
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-english-ws

Stream real-time English transcripts from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partials, finals, and speaker diarization.



# Nova 3 (Hindi)
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-hindi-http

POST /v1/stt/slng/deepgram/nova:3-hi
Transcribe Hindi audio using SLNG-hosted Deepgram Nova 3.

<HostingBanner type="slng" />


# Nova 3 (Hindi)
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-hindi-ws

Stream real-time Hindi speech-to-text from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partial and final transcripts and VAD.



# Nova 3
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-http

POST /v1/stt/deepgram/nova:3
Transcribe audio using Deepgram Nova 3 with VAD and speaker diarization.

<HostingBanner type="thirdparty" />


# Nova 3 (Indonesian)
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-indonesian-ws

Stream real-time Indonesian speech-to-text from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partial and final transcripts and VAD.



# Nova 3 (Kannada)
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-kannada-ws

Stream real-time Kannada speech-to-text from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partial and final transcripts and VAD.



# Nova 3 (Marathi)
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-marathi-ws

Stream real-time Marathi speech-to-text from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partial and final transcripts and VAD.



# Nova 3 (Multi-Language)
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-multi-language-http

POST /v1/stt/slng/deepgram/nova:3-multi
Transcribe multi-language audio using SLNG-hosted Deepgram Nova 3.

<HostingBanner type="slng" />


# Nova 3 (Multi-Language)
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-multi-language-ws

Stream real-time multilingual transcripts from SLNG-hosted Deepgram Nova 3 over WebSocket with automatic language detection across supported languages.



# Nova 3 (Spanish)
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-spanish-http

POST /v1/stt/slng/deepgram/nova:3-es
Transcribe Spanish audio using SLNG-hosted Deepgram Nova 3.

<HostingBanner type="slng" />


# Nova 3 (Spanish)
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-spanish-ws

Stream real-time Spanish speech-to-text from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partial and final transcripts and VAD.



# Nova 3 (Telugu)
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-telugu-ws

Stream real-time Telugu speech-to-text from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partial and final transcripts and VAD.



# Nova 3
Source: https://docs.slng.ai/api-reference/stt/deepgram-nova-3/nova-3-ws

Stream real-time speech-to-text transcripts from Deepgram Nova 3 over WebSocket with voice activity detection, speaker diarization, and partial results.



# Gradium STT default
Source: https://docs.slng.ai/api-reference/stt/gradium-stt/gradium-stt-default-ws

Real-time multilingual speech-to-text via streaming WebSocket



# Reson8 STT v1
Source: https://docs.slng.ai/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws

Real-time speech-to-text transcription using Reson8 via WebSocket. Supports streaming audio with word-level timestamps, confidence scores, and partial results.



# Saaras v3
Source: https://docs.slng.ai/api-reference/stt/sarvam-ai-saaras/saaras-v3-http

POST /v1/stt/sarvam/saaras:v3
Transcribe audio using Sarvam AI Saaras with domain-aware speech recognition for 23 languages and flexible output modes.

<HostingBanner type="thirdparty" />


# Saaras v3
Source: https://docs.slng.ai/api-reference/stt/sarvam-ai-saaras/saaras-v3-ws

"Stream real-time speech-to-text transcripts from Sarvam AI Saaras v3 over WebSocket with voice activity detection across 23 Indian languages. Session configuration is provided via query parameters on the WebSocket upgrade URL: `language-code`, `mode`, `sample_rate`, `input_audio_codec`, `high_vad_sensitivity`, `vad_signals`."



# Speech AI Real-time v4
Source: https://docs.slng.ai/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws

Stream real-time transcripts from Soniox Speech AI v4 over WebSocket with speaker diarization, language detection, and configurable endpoint detection.



# Cartesia Sonic 3
Source: https://docs.slng.ai/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws

Stream low-latency speech synthesis from Cartesia Sonic 3 over WebSocket with a multilingual catalog of voices and context-aware controls.



# Aura 2 (English)
Source: https://docs.slng.ai/api-reference/tts/deepgram-aura-2/aura-2-english-http

POST /v1/tts/slng/deepgram/aura:2-en
Synthesize English speech using SLNG-hosted Deepgram Aura 2.

<HostingBanner type="slng" />


# Aura 2 (English)
Source: https://docs.slng.ai/api-reference/tts/deepgram-aura-2/aura-2-english-ws

Stream low-latency conversational English text-to-speech from SLNG-hosted Deepgram Aura 2 over WebSocket, optimized for production voice agents.



# Aura 2
Source: https://docs.slng.ai/api-reference/tts/deepgram-aura-2/aura-2-http

POST /v1/tts/deepgram/aura:2
Synthesize speech using Deepgram Aura 2 for conversational voice agents.

<HostingBanner type="thirdparty" />


# Aura 2 (Spanish)
Source: https://docs.slng.ai/api-reference/tts/deepgram-aura-2/aura-2-spanish-http

POST /v1/tts/slng/deepgram/aura:2-es
Synthesize Spanish speech using SLNG-hosted Deepgram Aura 2.

<HostingBanner type="slng" />


# Aura 2 (Spanish)
Source: https://docs.slng.ai/api-reference/tts/deepgram-aura-2/aura-2-spanish-ws

Stream low-latency conversational Spanish text-to-speech from SLNG-hosted Deepgram Aura 2 over WebSocket, optimized for production voice agents.



# Aura 2
Source: https://docs.slng.ai/api-reference/tts/deepgram-aura-2/aura-2-ws

Stream low-latency conversational text-to-speech from Deepgram Aura 2 over WebSocket as raw binary frames, optimized for ultra-low-latency voice agents.



# Gradium TTS default
Source: https://docs.slng.ai/api-reference/tts/gradium-tts/gradium-tts-default-http

POST /v1/tts/gradium/tts:default
Real-time multilingual text-to-speech with streaming WebSocket and one-shot HTTP synthesis

<HostingBanner type="thirdparty" />


# Gradium TTS default
Source: https://docs.slng.ai/api-reference/tts/gradium-tts/gradium-tts-default-ws

Real-time multilingual text-to-speech with streaming WebSocket and one-shot HTTP synthesis



# Inworld Max 1.5
Source: https://docs.slng.ai/api-reference/tts/inworld-max-1-5/inworld-max-1-5-http

POST /v1/tts/slng/inworld/max:1.5
Synthesize speech using SLNG-hosted Inworld Max 1.5.

<HostingBanner type="slng" />


# Inworld Max 1.5
Source: https://docs.slng.ai/api-reference/tts/inworld-max-1-5/inworld-max-1-5-ws

Stream multilingual speech synthesis from SLNG-hosted Inworld Max 1.5 over WebSocket using SLNG's unified low-latency TTS protocol.



# Kugel 1 Turbo
Source: https://docs.slng.ai/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws

Stream low-latency high-quality speech from KugelAudio Kugel 1 Turbo over WebSocket with expressiveness controls and SLNG's unified TTS protocol.



# Kugel 1
Source: https://docs.slng.ai/api-reference/tts/kugel-1/kugel-1-ws

Stream high-quality speech synthesis from KugelAudio Kugel 1 over WebSocket with expressiveness controls and SLNG's unified TTS protocol.



# Kugel 2 Turbo
Source: https://docs.slng.ai/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws

Stream low-latency high-quality speech synthesis from KugelAudio Kugel 2 Turbo over WebSocket with expressiveness controls and SLNG's unified TTS protocol.



# Kugel 2
Source: https://docs.slng.ai/api-reference/tts/kugel-2/kugel-2-ws

Stream high-quality speech synthesis from KugelAudio Kugel 2 over WebSocket with expressiveness controls and SLNG's unified TTS protocol.



# Murf Falcon
Source: https://docs.slng.ai/api-reference/tts/murf-falcon/murf-falcon-ws

Stream high-quality multilingual speech synthesis from Murf Falcon over WebSocket with selectable encodings, sample rates, and SLNG's unified TTS protocol.



# Create pronunciation dictionary
Source: https://docs.slng.ai/api-reference/tts/pronunciation-dictionaries/create-pronunciation-dictionary-http

POST /v1/pronunciation/dictionaries
Create a reusable pronunciation dictionary for TTS rewrite rules.

<Note>For workflow examples, see the [Pronunciation dictionaries guide](/pronunciation-dictionaries).</Note>


# Delete pronunciation dictionary
Source: https://docs.slng.ai/api-reference/tts/pronunciation-dictionaries/delete-pronunciation-dictionary-http

DELETE /v1/pronunciation/dictionaries/{name}
Delete one pronunciation dictionary by name from the authenticated organization.

<Note>For workflow examples, see the [Pronunciation dictionaries guide](/pronunciation-dictionaries).</Note>


# Get pronunciation dictionary
Source: https://docs.slng.ai/api-reference/tts/pronunciation-dictionaries/get-pronunciation-dictionary-http

GET /v1/pronunciation/dictionaries/{name}
Read one pronunciation dictionary by name from the authenticated organization.

<Note>For workflow examples, see the [Pronunciation dictionaries guide](/pronunciation-dictionaries).</Note>


# List pronunciation dictionaries
Source: https://docs.slng.ai/api-reference/tts/pronunciation-dictionaries/list-pronunciation-dictionaries-http

GET /v1/pronunciation/dictionaries
List pronunciation dictionaries for the authenticated organization.

<Note>For workflow examples, see the [Pronunciation dictionaries guide](/pronunciation-dictionaries).</Note>


# Arcana v3 (English)
Source: https://docs.slng.ai/api-reference/tts/rime-arcana-v3/arcana-v3-english-http

POST /v1/tts/slng/rime/arcana:3-en
Synthesize English speech using Rime Arcana v3 TTS model.

<HostingBanner type="slng" />


# Arcana v3 (English)
Source: https://docs.slng.ai/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws

Text-to-Speech API for generating English speech using Rime Arcana v3 TTS model. Establishes a WebSocket connection for real-time text-to-speech.



# Arcana v3 (French)
Source: https://docs.slng.ai/api-reference/tts/rime-arcana-v3/arcana-v3-french-http

POST /v1/tts/slng/rime/arcana:3-fr
Synthesize French speech using Rime Arcana v3 TTS model.

<HostingBanner type="slng" />


# Arcana v3 (French)
Source: https://docs.slng.ai/api-reference/tts/rime-arcana-v3/arcana-v3-french-ws

Text-to-Speech API for generating French speech using Rime Arcana v3 TTS model. Establishes a WebSocket connection for real-time text-to-speech.



# Arcana v3 (Hindi)
Source: https://docs.slng.ai/api-reference/tts/rime-arcana-v3/arcana-v3-hindi-http

POST /v1/tts/slng/rime/arcana:3-hi
Synthesize Hindi speech using Rime Arcana v3 TTS model.

<HostingBanner type="slng" />


# Arcana v3 (Hindi)
Source: https://docs.slng.ai/api-reference/tts/rime-arcana-v3/arcana-v3-hindi-ws

Text-to-Speech API for generating Hindi speech using Rime Arcana v3 TTS model. Establishes a WebSocket connection for real-time text-to-speech.



# Arcana v3 (Spanish)
Source: https://docs.slng.ai/api-reference/tts/rime-arcana-v3/arcana-v3-spanish-http

POST /v1/tts/slng/rime/arcana:3-es
Synthesize Spanish speech using Rime Arcana v3 TTS model.

<HostingBanner type="slng" />


# Arcana v3 (Spanish)
Source: https://docs.slng.ai/api-reference/tts/rime-arcana-v3/arcana-v3-spanish-ws

Text-to-Speech API for generating Spanish speech using Rime Arcana v3 TTS model. Establishes a WebSocket connection for real-time text-to-speech.



# Bulbul Stream v3
Source: https://docs.slng.ai/api-reference/tts/sarvam-ai-bulbul-stream-v3/bulbul-stream-v3-http

POST /v1/tts/sarvam/bulbul-stream:v3
HTTP-streaming multilingual TTS for Indian languages with 30+ speaker voices. Returns raw audio bytes (chunked) in the codec selected via `output_audio_codec`. Unlike `sarvam/bulbul:v3`, no `X-Duration` header is sent and no JSON envelope is used.


<HostingBanner type="thirdparty" />


# Bulbul v3
Source: https://docs.slng.ai/api-reference/tts/sarvam-ai-bulbul-v3/bulbul-v3-http

POST /v1/tts/sarvam/bulbul:v3
Synthesize speech using Sarvam AI Bulbul with high-quality multilingual TTS for Indian languages and 30+ speaker voices.

<HostingBanner type="thirdparty" />


# Bulbul v3
Source: https://docs.slng.ai/api-reference/tts/sarvam-ai-bulbul-v3/bulbul-v3-ws

Stream multilingual Indian-language speech from Sarvam AI Bulbul v3 over WebSocket with 30+ speaker voices and SLNG's unified low-latency TTS protocol.



# Soniox TTS v1
Source: https://docs.slng.ai/api-reference/tts/soniox-tts-v1/soniox-tts-v1-http

POST /v1/tts/soniox/tts-rt:v1
Real-time text-to-speech with streaming WebSocket and one-shot HTTP synthesis

<HostingBanner type="thirdparty" />


# Soniox TTS v1
Source: https://docs.slng.ai/api-reference/tts/soniox-tts-v1/soniox-tts-v1-ws

Stream real-time speech synthesis from Soniox TTS v1 over WebSocket with low-latency incremental audio output and SLNG's unified TTS protocol.



# Unified STT
Source: https://docs.slng.ai/api-reference/unified-api/unmute-stt-bridge/unmute-stt-bridge-http

POST /v1/bridges/unmute/stt/{model_variant}
Transcribe audio via SLNG's native WebSocket protocol bridge. The model_variant path parameter specifies the target STT model (e.g., deepgram/nova:3, slng/openai/whisper:large-v3).



# Unified STT
Source: https://docs.slng.ai/api-reference/unified-api/unmute-stt-bridge/unmute-stt-bridge-ws

Stream audio to any SLNG-supported STT model over the unified WebSocket protocol with init, audio, finalize, partial, and final transcript messages.



# Unified TTS
Source: https://docs.slng.ai/api-reference/unified-api/unmute-tts-bridge/unmute-tts-bridge-http

POST /v1/bridges/unmute/tts/{model_variant}
Synthesize speech via SLNG's native WebSocket protocol bridge. The model_variant path parameter specifies the target TTS model (e.g., deepgram/aura:2).



# Unified TTS
Source: https://docs.slng.ai/api-reference/unified-api/unmute-tts-bridge/unmute-tts-bridge-ws

Stream synthesized audio from any SLNG-supported TTS model over the unified WebSocket protocol with init, text, flush, and binary audio frames.



# Authentication & API Keys
Source: https://docs.slng.ai/authentication

Create and manage SLNG keys in the Dashboard, then authenticate requests over HTTP and WebSocket, including key rotation and bringing your own provider key.

All requests authenticate with an SLNG key. Create and manage keys in the [Dashboard](https://app.slng.ai/api-keys).

| Placeholder    | Replace with                                                          |
| -------------- | --------------------------------------------------------------------- |
| `SLNG_API_KEY` | An SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys) |

## Create and delete keys

Keys are created and deleted from the [API Keys](https://app.slng.ai/api-keys) page in the Dashboard. The secret value is shown once, at creation time. Copy it into your secret store immediately, because you cannot retrieve it later.

<Warning>
  SLNG keys are secrets. Store them server-side, never embed them in client code, and delete any key that may have been exposed.
</Warning>

## One key, every host

You use the same SLNG key across SLNG hosts:

| API             | Host                         | Use for                                                 |
| --------------- | ---------------------------- | ------------------------------------------------------- |
| Execution layer | `https://api.slng.ai`        | Across all models in the platform                       |
| Models          | `https://api.slng.ai`        | Real-time TTS, STT, bridges, pronunciation dictionaries |
| Managed Agents  | `https://api.agents.slng.ai` | Create and manage voice agents under `/v1/agents`       |
| Batch API       | `https://api.batch.slng.ai`  | Asynchronous batch transcription endpoints              |

## Authenticate over HTTP

Pass the key as a bearer token in the `Authorization` header:

```bash highlight={2} theme={null}
curl https://api.slng.ai/v1/tts/slng/deepgram/aura:2 \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello from SLNG!"}' \
  --output hello.wav
```

## Authenticate over WebSocket

Pass the key on the WebSocket upgrade request, either as an `Authorization` header or as a `token` query parameter when the client cannot set headers:

```text theme={null}
wss://api.slng.ai/v1/tts/slng/deepgram/aura:2?token=SLNG_API_KEY
```

<Note>
  The browser WebSocket API does not support custom headers. Use the `token` query parameter from the browser, or set the `Authorization` header from a server-side client.
</Note>

## Rotate a key

Keys cannot be rotated in place. To replace a key without downtime:

<Steps>
  <Step title="Create the new key">
    Generate a new key in the Dashboard and store its secret value.
  </Step>

  <Step title="Roll callers over">
    Update each caller to use the new key: backend services and any local environments. Verify traffic on the new key before continuing.
  </Step>

  <Step title="Delete the old key">
    Once no caller is using the old key, delete it from the Dashboard. Any request still presenting the deleted key starts failing with `401 Unauthorized`.
  </Step>
</Steps>

Deleting a key invalidates it for all future requests. If a key may have been exposed, create a replacement first, then delete the compromised one.

## Bring your own provider key

To run synthesis or transcription against your own upstream provider account, add the `X-Slng-Provider-Key` header alongside your SLNG key. Read the full guide to [Bring Your Own Key setup](/execution-layer/byok).

## Errors

A missing or invalid key returns `HTTP 401`, or an `auth_error` frame over WebSocket. See [Error Codes & Troubleshooting](/reference/errors).


# How to use Batch API
Source: https://docs.slng.ai/batch-guide

Submit audio for asynchronous transcription on the SLNG Batch API using direct file upload, URL input, or presigned S3 upload. Supported formats and limits.

This guide covers the three ways to submit audio for batch transcription. For endpoint details and schemas, see the [Batch API reference](/api-reference/speechmatics/create-batch-job).

<Note>
  The Batch API is served from `https://api.batch.slng.ai`, not `https://api.slng.ai`, and uses the same bearer SLNG key.
</Note>

**Prerequisites:**

* An [SLNG key](/getting-started)
* Audio in a supported format: `wav`, `mp3`, `flac`, `aac`, `ogg`, `m4a`, `mp4`, `amr`, `mpeg`

## Placeholders

The snippets below use these placeholders. Replace them before running the code.

| Placeholder               | Replace with                                                               |
| ------------------------- | -------------------------------------------------------------------------- |
| `SLNG_API_KEY`            | An SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys)      |
| `myjob123` / `job8f3a...` | The `job_id` returned by `POST /v1/batch/jobs` (auto-generated if omitted) |
| `<presigned_url>`         | The presigned upload URL returned by the `mode: "presign"` flow            |
| `audio.wav` / `s3_key`    | Your local file path / the S3 key the platform returned at presign time    |

***

## Input Methods

### Method 1: File Upload

Upload the audio file directly using `multipart/form-data`.

```mermaid theme={null}
sequenceDiagram
    participant Client
    participant Batch API
    Client->>Batch API: POST /v1/batch/jobs<br/>multipart: file + config
    Note over Batch API: Queues transcription job
    Batch API-->>Client: 202 – job_id, status: QUEUED
```

```bash theme={null}
curl -X POST https://api.batch.slng.ai/v1/batch/jobs \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -F file=@audio.wav \
  -F transcription_config='{"language":"en"}'
```

### Method 2: URL Input

Provide a publicly accessible HTTPS URL. The system downloads the file (max 1 GB). Supports presigned S3/GCS URLs for private files.

```mermaid theme={null}
sequenceDiagram
    participant Client
    participant Batch API
    Client->>Batch API: POST /v1/batch/jobs<br/>JSON: input_url + config
    Note over Batch API: Downloads audio from URL
    Note over Batch API: Queues transcription job
    Batch API-->>Client: 202 – job_id, status: QUEUED
```

```bash theme={null}
curl -X POST https://api.batch.slng.ai/v1/batch/jobs \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input_url": "https://example.com/audio.wav",
    "transcription_config": { "language": "en" }
  }'
```

| Field                  | Type   | Required | Description                                              |
| ---------------------- | ------ | -------- | -------------------------------------------------------- |
| `input_url`            | string | yes      | HTTPS URL of the audio file                              |
| `transcription_config` | object | yes      | Transcription settings                                   |
| `job_id`               | string | no       | Alphanumeric job ID (auto-generated if omitted)          |
| `model_code`           | string | no       | Model to use (default: `slng/speechmatics/batch:15.0.0`) |
| `metadata`             | object | no       | Arbitrary key-value metadata                             |

### Method 3: Presigned Upload

Use this method for large files or when you need upload progress tracking. Three steps: request a presigned URL, upload the file directly to S3, then create the job referencing the upload.

```mermaid theme={null}
sequenceDiagram
    participant Client
    participant Batch API
    participant S3
    Client->>Batch API: POST /v1/batch/jobs<br/>JSON: mode=presign + filename
    Batch API-->>Client: 200 – job_id + presigned upload URL
    Client->>S3: PUT presigned URL<br/>binary audio file
    S3-->>Client: 200 OK
    Client->>Batch API: POST /v1/batch/jobs<br/>JSON: job_id + s3_key + config
    Note over Batch API: Queues transcription job
    Batch API-->>Client: 202 – job_id, status: QUEUED
```

<Steps>
  <Step title="Request a presigned S3 upload URL">
    ```bash theme={null}
    curl -X POST https://api.batch.slng.ai/v1/batch/jobs \
      -H "Authorization: Bearer SLNG_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "mode": "presign",
        "filename": "audio.wav",
        "transcription_config": { "language": "en" }
      }'
    ```

    Returns **200 OK** (no job is created yet). The response carries the `job_id`, the validated `transcription_config` (and any other config you sent, echoed back), the future S3 locations, and an `upload` object with the presigned `PUT` URL plus the headers your upload must send:

    ```json theme={null}
    {
      "job_id": "job8f3a...",
      "transcription_config": { "language": "en", "operating_point": "standard", "diarization": "none" },
      "input_s3_uri": "s3://slng-production-batch-input/inputs/job8f3a.../audio.wav",
      "output_s3_prefix": "s3://slng-production-batch-output/outputs/job8f3a.../",
      "upload": {
        "url": "https://slng-production-batch-input.s3.amazonaws.com/...",
        "s3_key": "inputs/job8f3a.../audio.wav",
        "s3_uri": "s3://slng-production-batch-input/inputs/job8f3a.../audio.wav",
        "expires_in": 1800,
        "headers": { "Content-Type": "application/octet-stream" }
      }
    }
    ```

    Carry the returned `transcription_config` (and any echoed `tracking` / `output_config`) verbatim into step 3.
  </Step>

  <Step title="Upload the file to the presigned URL">
    Send the bytes with the exact headers from `upload.headers` (typically `Content-Type: application/octet-stream`):

    ```bash theme={null}
    curl -X PUT "<presigned_url>" \
      -H "Content-Type: application/octet-stream" \
      --data-binary @audio.wav
    ```
  </Step>

  <Step title="Create the job">
    Reference the `job_id` and `s3_key` from step 1.

    ```bash theme={null}
    curl -X POST https://api.batch.slng.ai/v1/batch/jobs \
      -H "Authorization: Bearer SLNG_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "job_id": "job8f3a...",
        "s3_key": "inputs/job8f3a.../audio.wav",
        "transcription_config": { "language": "en" }
      }'
    ```
  </Step>
</Steps>

***

## Job Lifecycle

After submission, a job moves through these statuses:

`QUEUED` → `IN_PROGRESS` → `DECODING` → `POST_PROCESSING` → `DONE` / `FAILED`

A successfully deleted job moves to `DELETED` (terminal).

Poll `GET /v1/batch/jobs/{jobId}` until the status reaches `DONE` or `FAILED`. The response includes the full job record (config, timestamps, `error_message` on failures); see the [API reference](/api-reference/speechmatics/get-batch-job) for the schema.

```mermaid theme={null}
sequenceDiagram
    participant Client
    participant Batch API
    Client->>Batch API: GET /v1/batch/jobs/{jobId}
    Batch API-->>Client: status: IN_PROGRESS
    Note over Client: Wait and retry
    Client->>Batch API: GET /v1/batch/jobs/{jobId}
    Batch API-->>Client: status: DONE
    Client->>Batch API: GET /v1/batch/jobs/{jobId}/files
    Batch API-->>Client: Signed download URLs<br/>(JSON, TXT, SRT transcripts)
```

```bash theme={null}
curl https://api.batch.slng.ai/v1/batch/jobs/myjob123 \
  -H "Authorization: Bearer SLNG_API_KEY"
```

Once `DONE`, retrieve the transcript:

```bash theme={null}
curl https://api.batch.slng.ai/v1/batch/jobs/myjob123/files \
  -H "Authorization: Bearer SLNG_API_KEY"
```

This returns signed download URLs for the input audio and the output transcripts. Each output entry carries a `format` field: `json`, `txt`, or `srt`. Signed URLs expire after roughly one hour.

To list jobs instead of polling a single one, use `GET /v1/batch/jobs`. It supports pagination (`page`, `page_size`) plus filtering by `status`, `model_code`, and submission date range, and sorting by `submitted_at`, `status`, or `model_code`. See the [API reference](/api-reference/speechmatics/list-batch-jobs) for the full parameter list.

***

## Transcription Config

| Field              | Type    | Default    | Description                                          |
| ------------------ | ------- | ---------- | ---------------------------------------------------- |
| `language`         | string  | `en`       | Language code for the audio                          |
| `operating_point`  | string  | `standard` | Accuracy level: `standard` or `enhanced`             |
| `diarization`      | string  | `none`     | Speaker separation: `none`, `speaker`, or `channel`  |
| `domain`           | string  | —          | Domain-specific language model                       |
| `output_locale`    | string  | —          | Locale for formatting (dates, numbers)               |
| `enable_entities`  | boolean | —          | Detect and format entities (dates, times, addresses) |
| `additional_vocab` | array   | —          | Custom words to improve recognition                  |

Example with diarization and enhanced accuracy:

```json theme={null}
{
  "transcription_config": {
    "language": "en",
    "operating_point": "enhanced",
    "diarization": "speaker"
  }
}
```

***

## Limits

| Limit                       | Value                                         |
| --------------------------- | --------------------------------------------- |
| Max file size               | 1 GB                                          |
| Presigned upload URL expiry | 30 minutes                                    |
| Supported audio formats     | wav, mp3, flac, aac, ogg, m4a, mp4, amr, mpeg |
| URL input scheme            | HTTPS only                                    |

***

## Next Steps

<CardGroup>
  <Card title="Batch API reference" icon="code" href="/api-reference/speechmatics/create-batch-job">
    Endpoint details, request schemas, and response formats
  </Card>

  <Card title="Getting started" icon="rocket" href="/getting-started">
    Set up your SLNG key and make your first request
  </Card>
</CardGroup>


# SLNG changelog
Source: https://docs.slng.ai/changelog

Release notes for the SLNG speech and language API. New TTS and STT models, voice agent features, breaking changes, and bug fixes.

<Update label="June 16, 2026" description="API v0.53.0">
  ## Gradium STT and TTS

  [Gradium STT](/api-reference/stt/gradium-stt/gradium-stt-default-ws) streams real-time multilingual transcription over WebSocket, with `Flush` and `EndOfStream` controls for finalizing buffered audio. [Gradium TTS](/api-reference/tts/gradium-tts/gradium-tts-default-ws) ships alongside it for streaming WebSocket synthesis and one-shot [HTTP synthesis](/api-reference/tts/gradium-tts/gradium-tts-default-http).

  ## Kugel 2 Turbo TTS

  [Kugel 2 Turbo](/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws) is the new low-latency tier in the Kugel TTS family. Stream high-quality synthesis with expressiveness controls over the unified TTS WebSocket protocol, with word timestamps and per-chunk completion events.

  ## Rime Arcana v3 French

  [Rime Arcana v3 French](/api-reference/tts/rime-arcana-v3/arcana-v3-french-ws) joins the Arcana v3 lineup. Synthesize French speech via WebSocket or [HTTP](/api-reference/tts/rime-arcana-v3/arcana-v3-french-http) using speakers like `livet_aurelie`.

  ## ElevenLabs WebSocket controls

  The ElevenLabs TTS WebSocket endpoints, including [Flash v2.5](/api-reference/tts/eleven-flash-v2-5/elevenlabs-flash-v2-5-ws), [v3](/api-reference/tts/eleven-v3/elevenlabs-v3-ws), and [Multilingual v2](/api-reference/tts/multilingual-v2/elevenlabs-multilingual-v2-ws), accept new init parameters: `auto_mode` to cut latency by skipping chunk scheduling, `sync_alignment` to attach alignment data to each audio chunk, `enable_ssml_parsing` for inline SSML, `inactivity_timeout` (1–180 s), and `chunk_length_schedule`. Set `enable_logging: false` for zero-retention mode on enterprise plans on both WebSocket and HTTP endpoints.
</Update>

<Update label="June 12, 2026" description="API v0.52.3">
  ## Execution Layer documentation

  The docs portal is reframed around the [Execution Layer](/execution-layer), the three-stage path that sits between your orchestrator and the models. Read how [STT Routing](/execution-layer/stt-routing), [Tiered Decisioning](/execution-layer/tiered-decisioning), and [Output Assembly](/execution-layer/output-assembly) cut latency and model cost across a voice call. The new [How It Works](/execution-layer/how-it-works) page walks through a single turn end to end.

  ## Streamlined navigation and a single API Reference

  The top bar collapses to **Documentation**, **Execution Layer**, **API Reference**, and **Models**. Every endpoint now lives under one [API Reference](/api-reference/overview), grouped by Unified API, TTS, STT, Voice Agents, Batch, and Bridges, so you can find a model without switching tabs.

  ## Consolidated authentication and BYOK pages

  API key creation, rotation, and request authentication are merged into a single [Authentication & API Keys](/authentication) page. Bring-your-own-key setup for every supported provider now lives on one [BYOK](/execution-layer/byok) page covering caching behavior and provider key handling.
</Update>

<Update label="June 11, 2026">
  ## Pipecat plugin

  The [`pipecat-slng`](/agents/pipecat-plugin) Python package connects a [Pipecat](https://github.com/pipecat-ai/pipecat) pipeline to any STT or TTS model on the SLNG gateway. It ships `SlngSTTService` and `SlngTTSService` for low-latency streaming over WebSocket, plus `SlngHttpTTSService` for non-streaming synthesis. Swap the `model` string to switch provider or region without changing your pipeline code.
</Update>

<Update label="June 10, 2026" description="API v0.52.2">
  ## New Sarvam Bulbul and Soniox voices

  [Sarvam Bulbul v3](/api-reference/tts/sarvam-ai-bulbul-v3/bulbul-v3-ws) adds the Tamil voice `ta-IN-rahul` and the multilingual `shubh`, while `gu-IN-rahul` is retired. [Soniox TTS v1](/api-reference/tts/soniox-tts-v1/soniox-tts-v1-ws) adds four English voices: `Maya`, `Daniel`, `Noah`, and `Nina`.

  ## Updated Cartesia Sonic 3 voice metadata

  The 745-voice [Cartesia Sonic 3](/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws) catalog has refreshed metadata. Voice IDs are unchanged, so existing requests keep working.
</Update>

<Update label="June 3, 2026" description="API v0.52.1">
  ## Gateway spec refinements

  Patch-level updates to the unified gateway specification clean up schemas across the TTS, STT, and bridge surfaces. Existing requests and responses keep working without changes.
</Update>

<Update label="June 2, 2026" description="API v0.52.0">
  ## Inworld Max 1.5 TTS

  [Inworld Max 1.5](/api-reference/tts/inworld-max-1-5/inworld-max-1-5-ws) is available on the SLNG-hosted TTS API in `us-east-1`. Synthesize up to 2,000 characters per request across 16 languages, pick from 100+ named voices, and tune output with `temperature`, `language` (BCP-47), and word- or character-level timestamps.

  ## Asia South region for Nova 3 English and Rime Arcana v3

  [Deepgram Nova 3 English](/api-reference/stt/deepgram-nova-3/nova-3-english-ws) and [Rime Arcana v3 English](/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws) can now route to `asia-south1`. Set `X-Region-Override: asia-south1` to keep traffic in-region for users in India.

  ## Region rename for Nova 3 Indian languages

  The Hindi, Marathi, Kannada, Tamil, and Telugu variants of [Deepgram Nova 3](/api-reference/stt/deepgram-nova-3/nova-3-ws) now expose a single `asia-south1` region. The legacy `ap-south-1` value is no longer accepted on `X-Region-Override`; switch any pinned requests to `asia-south1`.
</Update>

<Update label="May 29, 2026" description="API v0.51.2">
  ## Supported LLMs for Voice Agents

  The `llm` field on [Voice Agents](/voice-agents) is now a closed set: `bedrock-mantle/nvidia.nemotron-super-3-120b`, `bedrock-mantle/nvidia.nemotron-nano-3-30b`, and `groq/openai/gpt-oss-120b`. Pick one of these IDs when you create or update an agent so requests route to a live model.

  ## Moonshot Kimi K2 removed from Voice Agents

  `groq/moonshotai/kimi-k2-instruct-0905` is no longer routable for Voice Agents. Switch existing agents and example payloads to `groq/openai/gpt-oss-120b` (or another model from the supported list) to keep calls working.
</Update>

<Update label="May 28, 2026" description="API v0.51.1">
  ## Segment correlation for Cartesia Sonic 3

  [Cartesia Sonic 3](/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws) audio chunks now carry a `flush_id`. The counter starts at `0` and increments each time you send a `text` input with `flush: true` or a standalone flush message. Use it to map streamed audio frames back to the text segment that produced them.

  ## Pronunciation hints on Cognigy and Jambonz TTS bridges

  The [Cognigy TTS bridge](/api-reference/bridges/cognigy-tts-bridge/cognigy-tts-bridge-ws) and [Jambonz TTS bridge](/api-reference/bridges/jambonz-tts-bridge/jambonz-tts-bridge-ws) accept an optional `pronunciation` object on `text` messages. Set `mode` (`ipa` or `ssml`), `name`, and `dictionary_id` to override how a term is spoken per chunk on providers that support [pronunciation dictionaries](/pronunciation-dictionaries).

  ## Binary audio frames on the Unmute TTS bridge

  The [Unmute TTS bridge](/api-reference/unified-api/unmute-tts-bridge/unmute-tts-bridge-ws) now sends raw binary WebSocket frames instead of JSON `audio_chunk`, `segment_start`, and `segment_end` envelopes. The encoding and sample rate match the values you pass in the init message, so you can write the bytes straight to your audio pipeline. The `clear` control message has been removed; error and `audio_end` payloads now carry their fields under a `data` envelope (with `message` and `code` duplicated at the top level for backward compatibility).
</Update>

<Update label="May 26, 2026" description="API v0.50.1">
  ## BYOK support for Kugel TTS

  You can now bring your own Kugel API key when calling [Kugel 1 Turbo](/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws), [Kugel 1](/api-reference/tts/kugel-1/kugel-1-ws), and [Kugel 2](/api-reference/tts/kugel-2/kugel-2-ws). Pass it on the `X-Slng-Provider-Key` header so Kugel bills your account directly, while the SLNG gateway's TTS cache still serves repeat requests. See [Bring your own key](/execution-layer/byok) for the full provider list.
</Update>

<Update label="May 23, 2026" description="API v0.50.0">
  ## HTTP streaming for Sarvam Bulbul v3

  [Sarvam AI Bulbul Stream v3](/api-reference/tts/sarvam-ai-bulbul-stream-v3/bulbul-stream-v3-http) is now available as a chunked HTTP endpoint. The response is raw audio bytes in the codec you set with `output_audio_codec` (there is no JSON envelope and no `X-Duration` header), so you can start playback as soon as the first chunk arrives. Use it to reach the same 30+ Indian-language voices as `bulbul:v3` with lower time-to-first-byte.
</Update>

<Update label="May 22, 2026" description="API v0.49.1">
  ## Streaming transcription for Sarvam Saaras v3

  Sarvam AI [Saaras v3](/api-reference/stt/sarvam-ai-saaras/saaras-v3-ws) is now available over WebSocket for real-time transcription across 23 Indian languages. Configure each session with query parameters on the upgrade URL (`language-code`, `mode`, `sample_rate`, `input_audio_codec`, `high_vad_sensitivity`, and `vad_signals`) to tune voice activity detection and audio handling per stream.
</Update>

<Update label="May 21, 2026" description="API v0.48.1">
  ## HTTP transcription for Nova 3 Indic languages

  Deepgram Nova 3 now exposes HTTP endpoints for [Kannada](/api-reference/stt/deepgram-nova-3/nova-3-kannada-http), [Marathi](/api-reference/stt/deepgram-nova-3/nova-3-marathi-http), [Tamil](/api-reference/stt/deepgram-nova-3/nova-3-tamil-http), and [Telugu](/api-reference/stt/deepgram-nova-3/nova-3-telugu-http). You can transcribe these languages with a single request (binary upload or `url` field) instead of opening a WebSocket.

  ## Soniox TTS language coverage

  [Soniox TTS](/voices/soniox) now ships voices for 60+ languages, including Afrikaans, Bengali, Bulgarian, Catalan, Czech, Dutch, Greek, Gujarati, Hebrew, Indonesian, Kannada, Malay, Marathi, Norwegian, Tamil, Telugu, and more. Set the `language` field to any supported ISO 639-1 code on the [Soniox TTS HTTP endpoint](/api-reference/tts/soniox-tts-v1/soniox-tts-v1-http) to pick a voice catalog.

  ## Runtime variables for voice agents

  Voice agents can now declare `runtime_variables` so the model can capture values during a call and reuse them later in webhook URLs or system tool arguments. The built-in `set_runtime_variables` tool writes the values, which persist for the lifetime of the call or web session. See [Voice agents](/voice-agents) for the setup pattern.

  ## New agent regions and world parts

  The [region override](/region-override) catalog now includes the `eu-non-eu` and `me` world parts, plus the `asia-south1`, `asia-southeast2`, and `australia-southeast1` regions. Pin requests to Sydney, Jakarta, or a non-EU European region with `X-Region-Override`, or stay inside the Middle East with `X-World-Part-Override: me`.

  ## Voice agents no longer need a separate API key

  Voice agent create and duplicate requests no longer accept `slng_api_key`. Agents now use the API key you authenticate the request with. Drop the field from your payloads. Agent duplication also stops copying the inbound connection and call history; reconnect inbound routing on the copy if you need it.

  ## Deepgram Aura 2 region availability

  SLNG-hosted [Deepgram Aura 2 English](/api-reference/tts/deepgram-aura-2/aura-2-english-http) is no longer available in `us-east-1`. Route English TTS to `eu-north-1`. [Aura 2 Spanish](/api-reference/tts/deepgram-aura-2/aura-2-spanish-http) drops the `na` world part and now serves only `eu`.
</Update>

<Update label="May 20, 2026" description="API v0.46.0">
  ## Pronunciation dictionaries for TTS

  You can now create reusable [pronunciation dictionaries](/pronunciation-dictionaries) and attach them to any SLNG TTS request. Define rewrite rules once for brand names, acronyms, or domain terms, then reference the dictionary from HTTP, WebSocket, or Unified TTS calls. Manage dictionaries through the new [pronunciation dictionary endpoints](/api-reference/tts/pronunciation-dictionaries/create-pronunciation-dictionary-http).

  ## Full voice catalogs on provider pages

  Provider voice pages now list every voice in the catalog instead of capping the table at ten per language. The [Cartesia Sonic 3](/voices/cartesia-sonic-3) page shows all 745 voices, [Sarvam Bulbul](/voices/sarvam-bulbul) shows 405, [Deepgram Aura](/voices/deepgram-aura) shows 91, [Soniox](/voices/soniox) shows 120, [Murf](/voices/murf) shows 111, and [Kugel](/voices/kugel) shows 100. You can search and copy any voice ID directly from the provider page.
</Update>

<Update label="May 19, 2026" description="API v0.44.2">
  ## Batch API reference now matches the gateway

  The [Batch API reference](/api-reference/speechmatics/create-batch-job) and [Batch API guide](/batch-guide) are realigned with the live `api.batch.slng.ai` gateway. Request and response schemas, supported audio formats, and the three submission flows (direct upload, URL input, and presigned S3 upload) reflect what the service actually accepts.
</Update>

<Update label="May 16, 2026" description="API v0.44.1">
  ## URL-based audio for HTTP transcription

  The [Whisper Large v3](/api-reference/stt/whisper-large-v3/whisper-large-v3-http), [Cognigy STT bridge](/api-reference/bridges/cognigy-stt-bridge/cognigy-stt-bridge-http), [Jambonz STT bridge](/api-reference/bridges/jambonz-stt-bridge/jambonz-stt-bridge-http), and [Unmute STT bridge](/api-reference/unified-api/unmute-stt-bridge/unmute-stt-bridge-http) HTTP endpoints now accept a `url` field pointing to a publicly accessible audio file. Send a JSON body with `url` and `language` instead of a multipart upload when your audio is already hosted somewhere.

  ## Deepgram Nova 3 English region change

  SLNG-hosted [Deepgram Nova 3 English](/api-reference/stt/deepgram-nova-3/nova-3-english-http) is no longer available in `eu-north-1`. Route English transcription to `australia-southeast1` or `us-east-1` instead.
</Update>

<Update label="May 15, 2026" description="API v0.43.3">
  ## voiceai CLI

  The new [`voiceai` CLI](/sdks/cli) runs text-to-speech and speech-to-text from a terminal. Install it with `curl`, Homebrew, or `npm`, then pipe audio between SLNG models and other tools without writing an HTTP client.

  ## JavaScript and Python SDKs

  The typed [JavaScript SDK](/sdks/javascript) (`voiceai-sdk` on npm) supports Node, Bun, and Deno. The [Python SDK](/sdks/python) (`voiceai-sdk` on PyPI) ships sync and async clients for Python 3.9+. Both wrap the full STT and TTS surface so you can drop the raw `fetch` and WebSocket plumbing.

  ## Agent skills for coding agents

  The [`slng-ai/skills`](/sdks/skills) pack teaches Claude Code and similar coding agents to call SLNG directly. Point your agent at the skills repo and it can pick models, build init messages, and stream audio for you.

  ## LiveKit Agents plugin

  The [`livekit-plugins-slng`](/agents/livekit-plugin) Python package connects [LiveKit Agents](https://docs.livekit.io/agents/) to any STT or TTS model on the SLNG gateway with a single configuration switch. You can swap providers or regions without changing your agent code.

  ## Embed a voice agent on the web

  A new [browser embed guide](/agents/embed-web) walks through adding a SLNG voice session to any web page. It uses LiveKit, a React frontend, and a backend proxy that keeps your API key off the client.
</Update>

<Update label="May 14, 2026" description="API v0.43.2">
  ## Rime Arcana v3 Spanish

  [Rime Arcana v3 (Spanish)](/api-reference/tts/rime-arcana-v3/arcana-v3-spanish-ws) is available as a new TTS endpoint, with both streaming WebSocket and one-shot HTTP synthesis. Choose from ten Spanish voices (`aurelio`, `celestino`, `lark`, `luz`, `mar`, `nova`, `pola`, `seraphina`, `sirius`, and `ursa`) and pass `model: rime/arcana:3-es` on init.

  ## Rime Arcana v3 adds eu-north-1

  [Arcana v3 English](/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws), [Hindi](/api-reference/tts/rime-arcana-v3/arcana-v3-hindi-ws), and Spanish are now available in `eu-north-1`. You can route Arcana v3 synthesis to North Europe for lower latency in that region.

  ## Deepgram Nova 3 adds asia-south1

  [Deepgram Nova 3](/api-reference/stt/deepgram-nova-3/nova-3-multi-language-ws) Tamil, Telugu, Marathi, and Kannada are now available in `asia-south1`, in addition to `ap-south-1`. You can route South Asian language transcription to the Mumbai GCP region.

  ## Deepgram Nova 3 Spanish region change

  Deepgram Nova 3 Spanish is no longer available in `ap-southeast-2`. Use `australia-southeast1` or `us-east-1` instead.

  ## Soniox TTS region override removed

  The `x-region` header is no longer accepted on [Soniox TTS v1](/api-reference/tts/soniox-tts-v1/soniox-tts-v1-ws) requests. Soniox TTS runs only in `na`, so requests are routed there automatically.
</Update>

<Update label="May 13, 2026" description="API v0.42.2">
  ## Expanded Murf Falcon voice catalog

  The [Murf Falcon](/voices/murf) voice catalog now lists 133 voices across more than 20 locales, including new entries for Bengali, Tamil, Telugu, Gujarati, Kannada, Punjabi, Japanese, Korean, Portuguese, Dutch, Polish, Greek, Croatian, and Scottish English. You can browse voices by full locale code and copy the `voice_id` for use in your init message.

  ## Simplified Unmute TTS bridge requests

  The [Unmute TTS bridge](/api-reference/unified-api/unmute-tts-bridge/unmute-tts-bridge-http) no longer requires a `model` field on HTTP or WebSocket init messages. The model is now inferred from the `{model_variant}` path. Send only `voice` and `text` for HTTP requests, or `voice` plus optional `config` on the WebSocket init.
</Update>

<Update label="May 7, 2026" description="API v0.42.1">
  ## Rime Coda Indonesian TTS

  [Rime Coda](/api-reference/tts/rime-coda/coda-indonesian-ws) is available as a new TTS model in the `asia-southeast2` (Jakarta) region. It synthesizes Bahasa Indonesian with low latency across four voices (`pujianti_plesmita`, `siswoko_sigit`, `taryadi_dani`, and `usmany_tatianna`) and supports streaming WebSocket and one-shot HTTP synthesis.

  ## Region and world-part query parameters on bridges

  The Cognigy, Jambonz, and Unmute HTTP bridges now accept `?region=` and `?world-part=` query parameters, mirroring the `X-Region-Override` and `X-World-Part-Override` headers. Use the query form when your platform cannot set custom headers; if both are present, the header wins. See [Integrations overview](/integrations/overview#region-and-world-part-overrides) for details.
</Update>

<Update label="May 6, 2026" description="API v0.41.2">
  ## Cartesia Sonic 3, Murf Falcon, Kugel, Soniox, Reson8, and Sarvam in the Unified API

  The [Unified API](/execution-layer/unified-api-models) now routes to Cartesia Sonic 3, Murf Falcon, KugelAudio Kugel 1/1-Turbo/2, Soniox TTS v1, Soniox Speech AI v4, Reson8 STT v1, and Sarvam Saaras v3. You can swap between these providers using a single request shape: pass identifiers like `cartesia/sonic:3`, `murf/murftts:falcon`, `kugelaudio/kugel:2`, `soniox/tts-rt:v1`, `soniox/speech-ai:rt-v4`, or `reson8/reson8stt:v1`.

  ## Webhook tools support custom HTTP methods and raw payloads

  [Voice agent webhook tools](/examples/agents-config#system-triggered-webhooks) now accept `http_method` (`POST`, `PUT`, `PATCH`, or `DELETE`) and `webhook_format` (`envelope` or `raw`). Set `webhook_format` to `raw` to send only the tool arguments when the receiving service cannot parse the SLNG envelope.

  ## Tool execution tracking for voice agents

  You can record webhook, template, human-transfer, and built-in tool activity against a call by posting to the [tool executions endpoint](/api-reference/calls/submit-tool-execution). Each record carries the outcome, duration, and HTTP status, and submitted executions surface on the [call detail response](/api-reference/calls/get-call) for debugging or analytics.

  ## ElevenLabs Flash v2.5 adds Asia Pacific region

  [ElevenLabs Flash v2.5](/api-reference/tts/eleven-flash-v2-5/elevenlabs-flash-v2-5-ws) is now available in `ap`, in addition to `eu`. You can route synthesis to Asia Pacific endpoints for lower latency in that region.

  ## Nova 3 multi-language adds eu-north-1

  [Deepgram Nova 3 multi-language](/api-reference/stt/deepgram-nova-3/nova-3-multi-language-ws) is now available in `eu-north-1` as a specific region (in addition to the broader `eu` world part), giving you direct routing to North Europe.

  ## Deepgram Aura 2 English region change

  [Deepgram Aura 2 English](/api-reference/tts/deepgram-aura-2/aura-2-english-ws) is no longer available in `ap-southeast-2`. Use `eu-north-1` or `us-east-1` instead.

  ## Nova 3 Hindi region change

  [Deepgram Nova 3 Hindi](/api-reference/stt/deepgram-nova-3/nova-3-hindi-ws) is no longer available in `ap-southeast-2`. Use `asia-south1` instead.
</Update>

<Update label="April 30, 2026" description="API v0.40.3">
  ## Soniox TTS v1 general availability

  [Soniox TTS](/api-reference/tts/soniox-tts-v1/soniox-tts-v1-ws) graduates from preview to v1. Update your client to call `tts-rt:v1` and set `model` to `tts-rt-v1`. The `v1-preview` path and `tts-rt-v1-preview` model identifier are retired.

  ## Deepgram Aura 2 voice selection now required

  The `model` field is now required on every [Deepgram Aura 2 English](/api-reference/tts/deepgram-aura-2/aura-2-english-ws) and [Spanish](/api-reference/tts/deepgram-aura-2/aura-2-spanish-ws) request. The previous defaults (`aura-2-thalia-en` and `aura-2-celeste-es`) no longer apply, so you must pick a voice explicitly.
</Update>

<Update label="April 29, 2026" description="API v0.40.1">
  ## Kugel 2 TTS

  [Kugel 2](/api-reference/tts/kugel-2/kugel-2-ws) is available as a new TTS model in `eu`. It offers 87 voices with expressiveness control across 26 languages, including Arabic, Chinese, Hindi, Japanese, Korean, and Vietnamese.

  ## Soniox TTS v1-preview

  [Soniox TTS v1-preview](/api-reference/tts/soniox-tts-v1/soniox-tts-v1-ws) is available as a new TTS model in `na`, with both streaming WebSocket and one-shot HTTP synthesis. Browse the voice catalog on the [Soniox TTS voices](/voices/soniox) page.

  ## Voice catalog pages for Cartesia Sonic 3 and Murf Falcon

  You can now browse [Cartesia Sonic 3](/voices/cartesia-sonic-3) and [Murf Falcon](/voices/murf) voices with audio samples directly in the docs. Each entry shows the `voice_id` to pass in your init message.

  ## Nova 3 multi-language adds EU region

  [Deepgram Nova 3 multi-language](/api-reference/stt/deepgram-nova-3/nova-3-multi-language-ws) is now available in `eu`, in addition to `ap-southeast-2` and `us-east-1`. You can route multilingual transcription to European endpoints for lower latency.

  ## Nova 3 Hindi region change

  [Deepgram Nova 3 Hindi](/api-reference/stt/deepgram-nova-3/nova-3-hindi-ws) is no longer available in `ap-south-1`. Use `ap-southeast-2` or `asia-south1` instead.
</Update>

<Update label="April 25, 2026" description="API v0.38.0">
  ## Soniox Speech AI Real-time v4

  Soniox Speech AI moves to v4. Use the [Speech AI Real-time v4](/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws) endpoint for streaming transcription with speaker diarization, automatic language identification, and configurable endpoint detection across 60+ languages. The v3 endpoint has been retired. Point clients at the new path to continue receiving native Soniox token frames.

  ## LiveKit plugin compatibility refresh

  The [LiveKit Agents plugin](/agents/livekit-plugin) now targets `livekit-agents>=1.5.1` and Python 3.10+. You can pass model-specific options as keyword arguments. For example, `whisper_params` for Whisper, `target_language_code` for Sarvam STT, or `modelId` and `speakingStyle` for Rime Arcana. New `slng_base_url` and `http_session` arguments let you point at a self-hosted gateway and reuse an `aiohttp.ClientSession`.

  ## Sarvam Saaras v3 STT not supported in LiveKit plugin

  Saaras is HTTP-only on SLNG and has no WebSocket endpoint, so it cannot run through the LiveKit plugin's realtime path. For Hindi voice agents, use `slng/deepgram/nova:3-hi` or `slng/deepgram/nova:3-multi`. See the [LiveKit plugin provider notes](/agents/livekit-plugin#provider-notes) for details.
</Update>

<Update label="April 24, 2026" description="API v0.37.0">
  ## Expanded regions for Murf Falcon TTS

  [Murf Falcon](/api-reference/tts/murf-falcon/murf-falcon-ws) is now available in `ap`, `eu-non-eu`, `me`, and `na`, in addition to the existing `eu` world part. You can now route synthesis closer to users across the Americas, Asia Pacific, and the Middle East.

  ## Asia Pacific region for Soniox Speech AI Real-time v3

  [Soniox Speech AI Real-time v3](/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws) adds the `ap` world part alongside `eu` and `na`. Route transcription to Asia Pacific endpoints for lower latency in that region.
</Update>

<Update label="April 23, 2026" description="API v0.36.0">
  ## URL and presigned S3 inputs for Batch STT

  You can now submit audio to the [Batch STT API](/batch-guide) without uploading a file on every request. Pass a publicly accessible `input_url`, or request a presigned S3 URL, upload directly, then create the job with the returned `s3_key`. Both methods accept an optional `metadata` object for attaching arbitrary key-value pairs to a job.

  ## Batch API usage guide

  A new [Batch API guide](/batch-guide) walks through the three input methods (file upload, URL input, and presigned S3 upload) with request flows and sample payloads.

  ## Deepgram Aura 2 English in eu-north-1

  [Deepgram Aura 2 English TTS](/api-reference/tts/deepgram-aura-2/aura-2-english-ws) is now available in `eu-north-1`, in addition to `ap-southeast-2` and `us-east-1`.

  ## Whisper Large v3 Compressed removed

  The Whisper Large v3 Compressed STT model has been retired from the catalog. Use [Whisper Large v3](/api-reference/stt/whisper-large-v3/whisper-large-v3-ws) for multilingual transcription going forward.
</Update>

<Update label="April 22, 2026" description="API v0.32.0">
  ## Runtime variables for voice agents

  Voice agents can now capture values during a call and reuse them in webhook URLs and system tool arguments. Define a `runtime_variables` array on your agent, and the model sets values through the built-in `set_runtime_variables` tool. See the [agent configuration examples](/examples/agents-config#runtime-variables) for setup details.

  ## Webhook HTTP method and payload format

  Webhook tools on voice agents now accept `http_method` (POST, PUT, PATCH, or DELETE) and `webhook_format` (`envelope` or `raw`). Use `raw` to send only the tool arguments as the request body, skipping the SLNG metadata envelope. Both fields are documented in the [Voice Agents API reference](/api-reference/agents/create-agent).

  ## Expanded regions for Rime Arcana v2 and Cartesia Sonic 3

  [Rime Arcana v2 TTS](/api-reference/tts/rime-arcana-v2/arcana-v2-english-ws) is now available in `eu-north-1` and `us-east-1`, in addition to `ap-southeast-2`. [Cartesia Sonic 3 TTS](/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws) is now available in all three world parts: `ap`, `eu`, and `na`.

  ## New regions for Deepgram Nova 3 English and Hindi

  [Nova 3 English](/api-reference/stt/deepgram-nova-3/nova-3-english-ws) is now available in `ap-south-1` and `us-east-1`. [Nova 3 Hindi](/api-reference/stt/deepgram-nova-3/nova-3-hindi-ws) adds `asia-south1` alongside existing regions.

  ## Utterance end events on Unmute STT Bridge

  The [Unmute STT Bridge](/api-reference/unified-api/unmute-stt-bridge/unmute-stt-bridge-ws) now emits `utterance_end` events when the upstream model signals the end of a spoken utterance. This gives you an explicit boundary marker for segmenting transcription output.

  ## Native token stream for Soniox Speech AI

  [Soniox Speech AI Real-time v3](/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws) now returns native Soniox token frames instead of normalized transcripts. You receive interim and final tokens directly, including `<end>` and `<fin>` endpoint markers when endpoint detection is enabled.
</Update>

<Update label="April 20, 2026" description="API v0.31.3">
  ## Tool personalization for voice agents

  You can now use `{{variable}}` placeholders in runtime tool fields: webhook URLs, system webhook argument values, human transfer phone numbers, and built-in timezones. Values resolve when the tool executes, not at session start, so a missing tool variable does not block the call. Supported surfaces, validation rules, and examples are documented on the [Configuration & Tools](/examples/agents-config#tool-personalization) page.

  ## Tool execution tracking on agent calls

  A new [tool executions endpoint](/api-reference/calls/submit-tool-execution) lets you record webhook, template, human transfer, and built-in tool activity against a call. Execution records (including outcome, duration, and HTTP status) also appear in the [call detail response](/api-reference/calls/get-call).
</Update>

<Update label="April 18, 2026" description="API v0.31.2">
  ## Cartesia Sonic 3 TTS

  [Cartesia Sonic 3](/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws) is available as a new TTS provider. It supports low-latency streaming synthesis over WebSocket with context-aware generation controls.

  ## Reson8 STT

  [Reson8 STT v1](/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws) is available as a new STT provider. It supports real-time transcription over WebSocket with word-level timestamps, confidence scores, and partial results in nine languages including Dutch, French, German, and Spanish.

  ## Deepgram Nova 3 Indic language endpoints

  Four new SLNG-hosted Deepgram Nova 3 language variants are available in `ap-south-1` (Mumbai): [Kannada](/api-reference/stt/deepgram-nova-3/nova-3-kannada-ws), [Marathi](/api-reference/stt/deepgram-nova-3/nova-3-marathi-ws), [Tamil](/api-reference/stt/deepgram-nova-3/nova-3-tamil-ws), and [Telugu](/api-reference/stt/deepgram-nova-3/nova-3-telugu-ws). Each has a dedicated WebSocket endpoint for that language.

  ## Soniox Speech AI version correction

  The Soniox STT endpoint is now correctly labeled [Speech AI Real-time v3](/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws). URLs and navigation have been updated accordingly.
</Update>

<Update label="April 15, 2026" description="API v0.22.1">
  ## Batch speech-to-text API

  You can now transcribe audio files asynchronously with the new [Batch STT API](/api-reference/batch). Upload a file, poll the job status, and download the transcript when ready. Supported formats include wav, mp3, flac, aac, ogg, m4a, mp4, amr, and mpeg. Powered by Speechmatics.
</Update>

<Update label="April 11, 2026" description="API v0.22.0">
  ## Murf Falcon TTS

  [Murf Falcon](/api-reference/tts/murf-falcon/murf-falcon-ws) is available as a new TTS provider. It supports multilingual speech synthesis over WebSocket with multiple encodings and sample rates.

  ## Unified API documentation

  The new [Unified API](/execution-layer/unified-api) section explains how to use one endpoint pattern for every STT and TTS model. Swap providers by changing only the URL path. Your auth, request format, and code stay the same. Includes guides on [parameter coverage](/execution-layer/unified-api-parameters) and [supported models](/execution-layer/unified-api-models).

  ## Integrations hub

  A new [Integrations](/integrations/overview) page lists third-party platforms you can connect to SLNG. LiveKit, Cognigy, and Jambonz each have dedicated setup paths.

  ## Whisper Large v3 endpoint consolidated

  The separate Whisper Large v3 Compressed endpoint has been removed. Use the standard [Whisper Large v3](/api-reference/stt/whisper-large-v3/whisper-large-v3-ws) endpoint, which now handles compressed audio directly.
</Update>

<Update label="April 9, 2026" description="API v0.20.0">
  ## Language selection for Nova 3 STT

  SLNG-hosted Deepgram Nova 3 STT endpoints accept a `language` parameter in the WebSocket `init` config. Supported locales by variant:

  * **English**: `en`, `en-au`, `en-us`, `en-nz`, `en-gb`, `en-in`
  * **Spanish**: `es`, `es-us`, `es-419`, `es-ar`, `es-mx`, `es-es`
  * **Hindi**: `hi`, `en`
  * **Multi-language**: `multi`

  The Hindi variant also accepts `en`, so you can transcribe English audio without switching endpoints. See the [Speech-to-Text models page](/models/stt) for the full parameter list.

  ## More sample rates for Rime Arcana TTS

  [Rime Arcana](/voices/rime-arcana) now supports 8, 16, 22.05, 24 (default), 32, 44.1, and 48 kHz. You can match your audio pipeline directly without resampling.

  ## Simplified endpointing parameter

  The `endpointing` parameter on Deepgram STT endpoints now accepts only an integer (milliseconds of silence before finalizing speech). Set it to `0` to disable. Default remains `10`.
</Update>

<Update label="April 8, 2026" description="API v0.19.0">
  ## Graceful WebSocket session close

  Send `{ "type": "close" }` on any [WebSocket](/websockets) connection to shut down cleanly. The server finishes processing remaining audio, then closes. This replaces the previous `cancel` behavior and works across TTS, STT, and [bridges](/execution-layer/unified-api).

  ## Keepalive for STT streams

  Send `{ "type": "keepalive" }` on STT WebSocket connections to prevent idle timeouts during pauses. Useful for voice agent sessions where the user goes silent but the connection should stay open.

  ## Endpointing controls for Deepgram Nova STT

  Two new parameters on [Deepgram Nova STT models](/models/stt) for tuning speech segmentation:

  * **`endpointing`**: milliseconds of silence before finalizing speech. Set to `false` to disable. Default: `10`.
  * **`utterance_end_ms`**: milliseconds of silence between words before an `UtteranceEnd` event. Range: 200–5000 ms, default: 1000 ms.

  ## India region for Nova 3 Hindi

  Deepgram Nova 3 Hindi is now available in `ap-south-1` (Mumbai), alongside `ap-southeast-2` (Sydney). Use the `X-Region-Override` header to route to the closest region. See [models by region](/models/by-region).
</Update>


# Agent Infra
Source: https://docs.slng.ai/dashboard/agent-infra

Use Agent Infra in the SLNG Dashboard to create voice agents from templates, configure prompts and models, test in-browser, and monitor live call traffic.

Agent Infra is where you create and operate voice agents:

* [Agent Infra](https://app.slng.ai/agent-infra)

## Create an agent

* [New agent](https://app.slng.ai/agent-infra/new)
* Start from a template (Healthcare, Insurance, Financial Services, Hospitality & Travel) or create from scratch
* Configure the system prompt, greeting(s), models, and tools
* Duplicate an existing agent when you want to reuse its stored configuration
* If you plan to dispatch outbound calls or use human transfer tools, attach an outbound connection (see [Telephony](/dashboard/telephony))

<Note>
  Personalization is available in two places when you create an agent:

  * [Template variables](/examples/agents-config#template-variables) for prompts and greetings
  * [Tool personalization](/examples/agents-config#tool-personalization) for supported tool fields such as
    webhook URLs, system webhook argument values, human transfer phone numbers, and built-in
    timezones

  Webhook text controls such as descriptions, result instructions, and forced pre-action message
  text stay static and do not support runtime personalization.
</Note>

<Tip>
  Use this mental model when configuring agents in the Dashboard:

  * Prompt and greeting variables are checked at session start
  * Tool-only personalization is checked only when that tool runs

  That means a call can still start even if a tool-only value is missing, but the tool itself will
  fail if it executes without a valid rendered value.
</Tip>

<Tip>
  Tool fields that support personalization now show a <b>Personalizable</b> indicator in the
  editor. Hover it to see the supported syntax, when the value is validated, the required final
  format, and an example. For the full rules and examples, see
  [Tool personalization](/examples/agents-config#tool-personalization).
</Tip>

<Tip>
  For webhook URLs, personalization is limited to path segments and query parameter values. The
  host, port, credentials, fragments, and query parameter names must remain literal.
</Tip>

<Tip>
  You can also manage agents programmatically. See the [Create agent](/api-reference/agents/create-agent), [Update agent](/api-reference/agents/update-agent-partial), and [List agents](/api-reference/agents/list-agents) API endpoints.
</Tip>

## Test in browser

Use the built-in test page for a web (non-telephony) session:

* `https://app.slng.ai/agent-infra/<agent_id>/test`

<Frame>
  <img alt="Agent Infra built-in test page" />
</Frame>

You can also create web sessions via the API. See [Agent API examples](/examples/agents-api#test-with-a-web-session).

## Calls

Each agent has a dedicated calls page where you can monitor and review all call activity:

* Calls list: `https://app.slng.ai/agent-infra/<agent_id>/calls`
* Call details: `https://app.slng.ai/agent-infra/<agent_id>/calls/<call_id>`

### Call list

The calls list shows all calls for an agent (both inbound and outbound), with the most recent calls first. You can filter by status to find active, completed, or failed calls.

<Frame>
  <img alt="Agent Infra calls list showing call history" />
</Frame>

### Call details

Each call record includes:

* **Status**: current call state (e.g., dispatched, active, completed, failed)
* **Phone number**: the E.164 number involved in the call
* **Template arguments**: the values passed for template variables (e.g., `patient_name`, `practice_name`)
* **Rendered prompt**: the final system prompt after template variables are resolved
* **Timestamps**: when the call was created and last updated
* **Session report**: when available, includes transcript and session-level metadata

<Frame>
  <img alt="Agent Infra call details showing status, transcript, and metadata" />
</Frame>

### Dispatching outbound calls

You can dispatch outbound calls from the Agent Infra UI or programmatically via the API. Outbound calls require the agent to have an outbound SIP trunk configured. See [Telephony](/dashboard/telephony).

<Tip>
  For code examples, see [Agent Call Examples](/examples/agents-calls).
</Tip>

<Note>
  Everything in Agent Infra maps to public API endpoints. See the <b>Voice Agents API</b> tab for a complete reference.
</Note>


# Telephony
Source: https://docs.slng.ai/dashboard/telephony

Set up SIP trunks and phone-number connections in the SLNG Dashboard for outbound and inbound voice agent calls, including BYOC and managed providers.

Connect phone numbers to your voice agents for outbound and inbound calls. Telephony is configured in the [Telephony](https://app.slng.ai/telephony) section of the Dashboard.

## Outbound calling

Outbound calls require an outbound connection.

<Steps>
  <Step title="Create an outbound connection">
    Open [Create outbound connection](https://app.slng.ai/telephony/outbound/new) in the Dashboard and configure your trunk or provider.
  </Step>

  <Step title="Attach it to your agent">
    In **Agent Infra**, attach the outbound connection to the agent that will place calls.
  </Step>
</Steps>

<Note>
  Without an outbound connection, call dispatch via the API (`POST /v1/agents/{agent_id}/calls`) fails.
</Note>

## Inbound calling (optional)

To route inbound calls to a specific agent, create an inbound connection:

* [Create inbound connection](https://app.slng.ai/telephony/inbound/new)


# SLNG Voice Agent API examples
Source: https://docs.slng.ai/examples/agents-api

Code samples for the SLNG Voice Agent API in JavaScript and Python. Create, list, update, test, and delete voice agents through the agent lifecycle.

Working code for the agent lifecycle. For prompt design, tool configuration, and template variables, see [Configuring voice agents](/examples/agents-config).

## Placeholders

Every snippet below uses these placeholders. Replace them before running the code.

| Placeholder                                         | Replace with                                                                                                                     |
| --------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------- |
| `SLNG_API_KEY`                                      | An SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys). Use it as the bearer token in the `Authorization` header. |
| `AGENT_ID` / `550e8400-e29b-41d4-a716-446655440000` | The agent's UUID returned by `POST /v1/agents`                                                                                   |
| `region: "eu-central"`                              | A Voice Agents logical region. See [Agent regions](/voice-agents#agent-regions)                                                  |

## Create an agent

<CodeGroup>
  ```javascript JavaScript theme={null}
  const resp = await fetch("https://api.agents.slng.ai/v1/agents", {
    method: "POST",
    headers: {
      Authorization: "Bearer SLNG_API_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      name: "Appointment Reminder",
      system_prompt:
        "You are a friendly appointment reminder for {{clinic_name}}. " +
        "Confirm the patient upcoming visit or help them reschedule. " +
        "Keep responses to one or two sentences.",
      greeting: "Hi {{patient_name}}, this is a reminder from {{clinic_name}} about your upcoming appointment.",
      language: "en",
      region: "eu-central",
      models: {
        stt: "slng/deepgram/nova:3-en",
        llm: "groq/openai/gpt-oss-120b",
        tts: "slng/deepgram/aura:2-en",
        tts_voice: "aura-2-thalia-en",
      },
      template_defaults: {
        clinic_name: "Downtown Health Clinic",
        patient_name: "there",
      },
    }),
  });

  const agent = await resp.json();
  console.log(agent.id);
  ```

  ```python Python theme={null}
  import requests

  resp = requests.post(
      "https://api.agents.slng.ai/v1/agents",
      headers={"Authorization": "Bearer SLNG_API_KEY"},
      json={
          "name": "Appointment Reminder",
          "system_prompt": (
              "You are a friendly appointment reminder for {{clinic_name}}. "
              "Confirm the patient upcoming visit or help them reschedule. "
              "Keep responses to one or two sentences."
          ),
          "greeting": "Hi {{patient_name}}, this is a reminder from {{clinic_name}} about your upcoming appointment.",
          "language": "en",
          "region": "eu-central",
          "models": {
              "stt": "slng/deepgram/nova:3-en",
              "llm": "groq/openai/gpt-oss-120b",
              "tts": "slng/deepgram/aura:2-en",
              "tts_voice": "aura-2-thalia-en",
          },
          "template_defaults": {
              "clinic_name": "Downtown Health Clinic",
              "patient_name": "there",
          },
      },
  )

  agent = resp.json()
  print(agent["id"])
  ```

  ```bash cURL theme={null}
  curl -X POST https://api.agents.slng.ai/v1/agents \
    -H "Authorization: Bearer SLNG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "name": "Appointment Reminder",
      "system_prompt": "You are a friendly appointment reminder for {{clinic_name}}. Confirm the patient upcoming visit or help them reschedule. Keep responses to one or two sentences.",
      "greeting": "Hi {{patient_name}}, this is a reminder from {{clinic_name}} about your upcoming appointment.",
      "language": "en",
      "region": "eu-central",
      "models": {
        "stt": "slng/deepgram/nova:3-en",
        "llm": "groq/openai/gpt-oss-120b",
        "tts": "slng/deepgram/aura:2-en",
        "tts_voice": "aura-2-thalia-en"
      },
      "template_defaults": {
        "clinic_name": "Downtown Health Clinic",
        "patient_name": "there"
      }
    }'
  ```
</CodeGroup>

## Test with a web session

Web sessions let you talk to your agent from a browser. No phone number or SIP trunk required. The response includes LiveKit credentials you can use with any [LiveKit client SDK](https://docs.livekit.io/client-sdk-js/).

<CodeGroup>
  ```javascript JavaScript theme={null}
  const resp = await fetch(
    `https://api.agents.slng.ai/v1/agents/${agent.id}/web-sessions`,
    {
      method: "POST",
      headers: {
        Authorization: "Bearer SLNG_API_KEY",
        "Content-Type": "application/json",
      },
      body: JSON.stringify({
        arguments: { patient_name: "Maria", clinic_name: "Greenfield Family Medicine" },
      }),
    },
  );

  const session = await resp.json();
  // session.livekit_url:   WebSocket URL to connect to
  // session.livekit_token: access token for the room
  // session.room_name:     LiveKit room name
  // session.call_id:       use this to look up the call later
  // session.max_session_seconds: how long the session stays open
  ```

  ```python Python theme={null}
  resp = requests.post(
      f"https://api.agents.slng.ai/v1/agents/{agent['id']}/web-sessions",
      headers={"Authorization": "Bearer SLNG_API_KEY"},
      json={
          "arguments": {"patient_name": "Maria", "clinic_name": "Greenfield Family Medicine"},
      },
  )

  session = resp.json()
  # session["livekit_url"]:   WebSocket URL to connect to
  # session["livekit_token"]: access token for the room
  # session["room_name"]:     LiveKit room name
  # session["call_id"]:       use this to look up the call later
  # session["max_session_seconds"]: how long the session stays open
  ```

  ```bash cURL theme={null}
  curl -X POST https://api.agents.slng.ai/v1/agents/AGENT_ID/web-sessions \
    -H "Authorization: Bearer SLNG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "participant_name": "Test user",
      "arguments": {
        "patient_name": "Maria"
      }
    }'
  ```
</CodeGroup>

Both fields are optional. `arguments` overrides `template_defaults` on the agent, and `participant_name` sets a display name in the LiveKit room.

## Update an agent

PATCH updates only the fields you send. Use PUT if you want to replace the entire configuration.

<CodeGroup>
  ```javascript JavaScript theme={null}
  const resp = await fetch(
    `https://api.agents.slng.ai/v1/agents/${agent.id}`,
    {
      method: "PATCH",
      headers: {
        Authorization: "Bearer SLNG_API_KEY",
        "Content-Type": "application/json",
      },
      body: JSON.stringify({
        greeting: "Hello {{patient_name}}, thanks for picking up.",
        models: {
          stt: "slng/deepgram/nova:3-en",
          llm: "groq/openai/gpt-oss-120b",
          tts: "slng/deepgram/aura:2-en",
          tts_voice: "aura-2-thalia-en",
          llm_kwargs: { temperature: 0.3 },
        },
      }),
    },
  );

  const updated = await resp.json();
  ```

  ```python Python theme={null}
  resp = requests.patch(
      f"https://api.agents.slng.ai/v1/agents/{agent['id']}",
      headers={"Authorization": "Bearer SLNG_API_KEY"},
      json={
          "greeting": "Hello {{patient_name}}, thanks for picking up.",
          "models": {
              "stt": "slng/deepgram/nova:3-en",
              "llm": "groq/openai/gpt-oss-120b",
              "tts": "slng/deepgram/aura:2-en",
              "tts_voice": "aura-2-thalia-en",
              "llm_kwargs": {"temperature": 0.3},
          },
      },
  )

  updated = resp.json()
  ```

  ```bash cURL theme={null}
  curl -X PATCH https://api.agents.slng.ai/v1/agents/AGENT_ID \
    -H "Authorization: Bearer SLNG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "greeting": "Hello {{patient_name}}, thanks for picking up.",
      "models": {
        "stt": "slng/deepgram/nova:3-en",
        "llm": "groq/openai/gpt-oss-120b",
        "tts": "slng/deepgram/aura:2-en",
        "tts_voice": "aura-2-thalia-en",
        "llm_kwargs": { "temperature": 0.3 }
      }
    }'
  ```
</CodeGroup>

## Duplicate an agent

Use duplication when you want to copy an existing agent configuration as-is, including prompts,
models, tools, template defaults, selected region, and outbound telephony settings.

The duplicate does not copy call history or the inbound connection.

After duplicating an agent:

* Reconnect inbound routing if the duplicate should receive calls.
* Verify the outbound trunk before dispatching calls.
* Test the duplicate with a web session or a test call.

<CodeGroup>
  ```javascript JavaScript theme={null}
  const duplicated = await fetch(
    `https://api.agents.slng.ai/v1/agents/${agent.id}/duplicate`,
    {
      method: "POST",
      headers: {
        Authorization: "Bearer SLNG_API_KEY",
        "Content-Type": "application/json",
      },
      body: JSON.stringify({
        name: `${agent.name} Copy`,
      }),
    },
  ).then((r) => r.json());

  console.log(duplicated.id);
  ```

  ```python Python theme={null}
  duplicated = requests.post(
      f"https://api.agents.slng.ai/v1/agents/{agent['id']}/duplicate",
      headers={"Authorization": "Bearer SLNG_API_KEY"},
      json={
          "name": f"{agent['name']} Copy",
      },
  ).json()

  print(duplicated["id"])
  ```

  ```bash cURL theme={null}
  curl -X POST https://api.agents.slng.ai/v1/agents/AGENT_ID/duplicate \
    -H "Authorization: Bearer SLNG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "name": "Appointment Reminder Copy"
    }'
  ```
</CodeGroup>

## List and inspect agents

<CodeGroup>
  ```javascript JavaScript theme={null}
  // List all agents
  const agents = await fetch("https://api.agents.slng.ai/v1/agents", {
    headers: { Authorization: "Bearer SLNG_API_KEY" },
  }).then((r) => r.json());

  for (const a of agents) {
    console.log(`${a.name} (${a.id})`);
  }

  // Get a single agent and check its template variables
  const agent = await fetch(`https://api.agents.slng.ai/v1/agents/${agents[0].id}`, {
    headers: { Authorization: "Bearer SLNG_API_KEY" },
  }).then((r) => r.json());

  console.log(agent.template_variables);
  // { clinic_name: { required: true, default: "Downtown Health Clinic" }, ... }
  ```

  ```python Python theme={null}
  # List all agents
  agents = requests.get(
      "https://api.agents.slng.ai/v1/agents",
      headers={"Authorization": "Bearer SLNG_API_KEY"},
  ).json()

  for a in agents:
      print(f"{a['name']} ({a['id']})")

  # Get a single agent and check its template variables
  agent = requests.get(
      f"https://api.agents.slng.ai/v1/agents/{agents[0]['id']}",
      headers={"Authorization": "Bearer SLNG_API_KEY"},
  ).json()

  print(agent["template_variables"])
  # {"clinic_name": {"required": true, "default": "Downtown Health Clinic"}, ...}
  ```
</CodeGroup>

## Delete an agent

Returns `204 No Content` on success.

<CodeGroup>
  ```javascript JavaScript theme={null}
  await fetch(`https://api.agents.slng.ai/v1/agents/${agent.id}`, {
    method: "DELETE",
    headers: { Authorization: "Bearer SLNG_API_KEY" },
  });
  ```

  ```python Python theme={null}
  requests.delete(
      f"https://api.agents.slng.ai/v1/agents/{agent['id']}",
      headers={"Authorization": "Bearer SLNG_API_KEY"},
  )
  ```

  ```bash cURL theme={null}
  curl -X DELETE https://api.agents.slng.ai/v1/agents/AGENT_ID \
    -H "Authorization: Bearer SLNG_API_KEY"
  ```
</CodeGroup>


# Dispatching outbound calls
Source: https://docs.slng.ai/examples/agents-calls

Send outbound voice agent calls on SLNG with E.164 numbers, SIP trunks, template variables, and call status webhooks. JavaScript and Python code examples.

You need an SLNG key and an agent created via the [API](/examples/agents-config) or [Agent Infra](/dashboard/agent-infra). See [Configuring voice agents](/examples/agents-config) for system prompt and tool setup.

<Warning>
  Outbound calls require the agent to be configured with an outbound SIP trunk (<code>sip\_outbound\_trunk\_id</code>).
  Configure this in the Dashboard Telephony page and attach it to your agent.
</Warning>

## Placeholders

Use these values in the examples:

| Placeholder    | Replace with                                             |
| -------------- | -------------------------------------------------------- |
| `SLNG_API_KEY` | An SLNG key with access to the Voice Agents API          |
| `AGENT_ID`     | The ID of an agent configured with an outbound SIP trunk |
| `+14155551234` | The destination phone number in E.164 format             |

## Basic Call Dispatch

Send a single outbound call by providing the agent ID and a phone number in E.164 format.

<CodeGroup>
  ```javascript JavaScript theme={null}
  const API_KEY = "SLNG_API_KEY";
  const BASE_URL = "https://api.agents.slng.ai";

  async function dispatchCall(agentId, phoneNumber, args = {}) {
    const response = await fetch(`${BASE_URL}/v1/agents/${agentId}/calls`, {
      method: "POST",
      headers: {
        Authorization: `Bearer ${API_KEY}`,
        "Content-Type": "application/json",
      },
      body: JSON.stringify({
        phone_number: phoneNumber,
        arguments: args,
      }),
    });

    if (!response.ok) {
      const error = await response.json().catch(() => ({}));
      throw new Error(`Failed to dispatch call: ${error.error || error.detail || response.status}`);
    }

    return response.json();
  }

  // Basic call
  const result = await dispatchCall(
    "AGENT_ID",
    "+14155551234",
  );
  console.log(`Call dispatched: ${result.call_id}`);
  ```

  ```python Python theme={null}
  import requests

  API_KEY = "SLNG_API_KEY"
  BASE_URL = "https://api.agents.slng.ai"

  def dispatch_call(agent_id, phone_number, arguments=None):
      response = requests.post(
          f"{BASE_URL}/v1/agents/{agent_id}/calls",
          headers={
              "Authorization": f"Bearer {API_KEY}",
              "Content-Type": "application/json"
          },
          json={
              "phone_number": phone_number,
              "arguments": arguments or {}
          }
      )
      response.raise_for_status()
      return response.json()

  # Basic call
  result = dispatch_call(
      "AGENT_ID",
      "+14155551234"
  )
  print(f"Call dispatched: {result['call_id']}")
  ```

  ```bash cURL theme={null}
  curl -X POST https://api.agents.slng.ai/v1/agents/AGENT_ID/calls \
    -H "Authorization: Bearer SLNG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "phone_number": "+14155551234"
    }'
  ```
</CodeGroup>

## Calls with Template Variables

If your agent's system prompt or greeting contains `{{variables}}`, pass them via the `arguments` field. These override any `template_defaults` set on the agent.

`arguments` is bounded to 32 keys, with keys up to 64 characters, values up to 1024 characters,
and a combined value payload up to 8192 characters.

<CodeGroup>
  ```javascript JavaScript theme={null}
  // Agent system_prompt uses: {{patient_name}}, {{practice_name}}
  const API_KEY = "SLNG_API_KEY";
  const BASE_URL = "https://api.agents.slng.ai";

  const response = await fetch(`${BASE_URL}/v1/agents/AGENT_ID/calls`, {
    method: "POST",
    headers: {
      Authorization: `Bearer ${API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      phone_number: "+14155551234",
      arguments: {
        patient_name: "Maria",
        practice_name: "Greenfield Family Medicine",
      },
    }),
  });

  if (!response.ok) {
    const error = await response.json().catch(() => ({}));
    throw new Error(`Failed to dispatch call: ${error.error || error.detail || response.status}`);
  }

  const result = await response.json();
  console.log(`Call dispatched: ${result.call_id}`);
  ```

  ```python Python theme={null}
  import requests

  API_KEY = "SLNG_API_KEY"
  BASE_URL = "https://api.agents.slng.ai"

  # Agent system_prompt uses: {{patient_name}}, {{practice_name}}
  response = requests.post(
      f"{BASE_URL}/v1/agents/AGENT_ID/calls",
      headers={
          "Authorization": f"Bearer {API_KEY}",
          "Content-Type": "application/json",
      },
      json={
          "phone_number": "+14155551234",
          "arguments": {
              "patient_name": "Maria",
              "practice_name": "Greenfield Family Medicine",
          },
      },
  )
  response.raise_for_status()

  result = response.json()
  print(f"Call dispatched: {result['call_id']}")
  ```

  ```bash cURL theme={null}
  curl -X POST https://api.agents.slng.ai/v1/agents/AGENT_ID/calls \
    -H "Authorization: Bearer SLNG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "phone_number": "+14155551234",
      "arguments": {
        "patient_name": "Maria",
        "practice_name": "Greenfield Family Medicine"
      }
    }'
  ```
</CodeGroup>

## Batch Call Dispatch

When you need to call a list of contacts, you can loop through them one at a time or fire multiple calls in parallel with a concurrency cap.

### Sequential Dispatch

```javascript theme={null}
async function dispatchBatch(agentId, contacts) {
  const results = [];

  for (const contact of contacts) {
    try {
      const result = await dispatchCall(agentId, contact.phone, contact.args);
      results.push({
        phone: contact.phone,
        success: true,
        call_id: result.call_id,
      });

      // Small delay between calls to avoid rate limiting
      await new Promise((resolve) => setTimeout(resolve, 500));
    } catch (error) {
      results.push({
        phone: contact.phone,
        success: false,
        error: error.message,
      });
    }
  }

  return results;
}

// Usage
const contacts = [
  {
    phone: "+14155551234",
    args: { patient_name: "Maria", practice_name: "Greenfield Family Medicine" },
  },
  {
    phone: "+14155555678",
    args: { patient_name: "John", practice_name: "Greenfield Family Medicine" },
  },
  {
    phone: "+14155559012",
    args: { patient_name: "Jane", practice_name: "Greenfield Family Medicine" },
  },
];

const results = await dispatchBatch(
  "AGENT_ID",
  contacts,
);
console.log("Batch results:", results);
```

### Parallel Dispatch (with concurrency limit)

Process calls in chunks to stay within rate limits while dispatching faster than sequential.

<CodeGroup>
  ```javascript JavaScript theme={null}
  async function dispatchBatchParallel(agentId, contacts, concurrency = 5) {
    const results = [];

    // Process in chunks
    for (let i = 0; i < contacts.length; i += concurrency) {
      const chunk = contacts.slice(i, i + concurrency);

      const chunkResults = await Promise.allSettled(
        chunk.map((contact) =>
          dispatchCall(agentId, contact.phone, contact.args)
            .then((result) => ({
              phone: contact.phone,
              success: true,
              call_id: result.call_id,
            }))
            .catch((error) => ({
              phone: contact.phone,
              success: false,
              error: error.message,
            })),
        ),
      );

      results.push(...chunkResults.map((r) => r.value || r.reason));
    }

    return results;
  }
  ```

  ```python Python theme={null}
  import asyncio
  import aiohttp

  API_KEY = "SLNG_API_KEY"
  BASE_URL = "https://api.agents.slng.ai"

  async def dispatch_call_async(session, agent_id, phone_number, arguments=None):
      async with session.post(
          f"{BASE_URL}/v1/agents/{agent_id}/calls",
          headers={
              "Authorization": f"Bearer {API_KEY}",
              "Content-Type": "application/json"
          },
          json={
              "phone_number": phone_number,
              "arguments": arguments or {}
          }
      ) as response:
          if response.status == 200:
              data = await response.json()
              return {"phone": phone_number, "success": True, "call_id": data["call_id"]}
          else:
              error = await response.json()
              return {
                  "phone": phone_number,
                  "success": False,
                  "error": error.get("error") or error.get("detail") or str(error),
              }

  async def dispatch_batch(agent_id, contacts, concurrency=5):
      semaphore = asyncio.Semaphore(concurrency)

      async def limited_dispatch(session, contact):
          async with semaphore:
              return await dispatch_call_async(
                  session, agent_id, contact["phone"], contact.get("args")
              )

      async with aiohttp.ClientSession() as session:
          tasks = [limited_dispatch(session, contact) for contact in contacts]
          return await asyncio.gather(*tasks)

  # Usage
  contacts = [
      {"phone": "+14155551234", "args": {"customer_name": "John Smith"}},
      {"phone": "+14155555678", "args": {"customer_name": "Jane Doe"}},
      {"phone": "+14155559012", "args": {"customer_name": "Bob Wilson"}},
  ]

  results = asyncio.run(dispatch_batch("AGENT_ID", contacts))
  for result in results:
      if result["success"]:
          print(f"✓ {result['phone']}: {result['call_id']}")
      else:
          print(f"✗ {result['phone']}: {result['error']}")
  ```
</CodeGroup>

## Common Use Cases

Outbound voice agents work well for automated calls that follow a predictable structure. Common examples include:

* **Appointment reminders**: confirm or reschedule upcoming visits
* **Payment collection**: notify customers of outstanding balances
* **Survey and feedback**: gather post-purchase or post-service input
* **Lead qualification**: follow up on inbound interest and route warm leads to sales

Use [template variables](#calls-with-template-variables) to personalize each call with contact-specific details like names, dates, and amounts.


# Configuring SLNG voice agents
Source: https://docs.slng.ai/examples/agents-config

Configure SLNG voice agents. Write effective system prompts, wire up tools and webhooks, and use template variables to personalize calls at dispatch time.

The [API reference](/api-reference) covers every field on the agent object. This page covers the parts that need more context than a schema can give: agent fields, model configuration, system prompt structure, tools, and template variables.

You can manage agents through the API or through [Agent Infra](/dashboard/agent-infra). For working code examples (create, update, delete), see [Agent API examples](/examples/agents-api).

## Agent fields

### Required fields

| Field           | Type   | Description                                                         |
| --------------- | ------ | ------------------------------------------------------------------- |
| `name`          | string | Unique agent name (max 255 chars)                                   |
| `system_prompt` | string | System prompt with Handlebars template support                      |
| `greeting`      | string | Default greeting                                                    |
| `language`      | string | Language code (e.g., "en", "es", "fr")                              |
| `region`        | string | Deployment region. See [Agent regions](/voice-agents#agent-regions) |
| `models`        | object | Model configuration (see [Models](#models))                         |

### Common optional fields

| Field                   | Type    | Default           | Description                                        |
| ----------------------- | ------- | ----------------- | -------------------------------------------------- |
| `inbound_greeting`      | string  | `null`            | Greeting override for inbound calls                |
| `outbound_greeting`     | string  | `null`            | Greeting override for outbound calls               |
| `sip_inbound_trunk_id`  | string  | `null`            | Inbound connection ID (for inbound calls)          |
| `sip_outbound_trunk_id` | string  | `null`            | Outbound connection ID (for outbound calls)        |
| `enable_interruptions`  | boolean | `true`            | Allow user to interrupt agent speech               |
| `idle_nudges`           | object  | language defaults | Silence recovery prompts and final hangup behavior |
| `tools`                 | array   | `[]`              | Tools available to the agent                       |
| `template_defaults`     | object  | `{}`              | Default values for template variables              |

## Models

The `models` object configures the STT, LLM, and TTS models used by the agent runtime:

```json theme={null}
{
  "models": {
    "stt": "slng/deepgram/nova:3-en",
    "llm": "groq/openai/gpt-oss-120b",
    "tts": "slng/deepgram/aura:2-en",
    "tts_voice": "aura-2-thalia-en",
    "stt_kwargs": {},
    "llm_kwargs": {},
    "tts_kwargs": {}
  }
}
```

### Supported LLMs

`llm` accepts one of the following model IDs:

| Model          | ID                                            |
| -------------- | --------------------------------------------- |
| Nemotron Super | `bedrock-mantle/nvidia.nemotron-super-3-120b` |
| Nemotron Nano  | `bedrock-mantle/nvidia.nemotron-nano-3-30b`   |
| GPT OSS 120b   | `groq/openai/gpt-oss-120b`                    |

### Fallbacks and timeouts

```json theme={null}
{
  "models": {
    "stt": "slng/deepgram/nova:3-en",
    "llm": "groq/openai/gpt-oss-120b",
    "tts": "slng/deepgram/aura:2-en",
    "tts_voice": "aura-2-thalia-en",
    "fallbacks": {
      "stt": ["slng/deepgram/nova:3-multi"],
      "llm": ["groq/openai/gpt-oss-120b"],
      "tts": [
        { "model": "slng/deepgram/aura:2-en", "voice": "aura-2-asteria-en" }
      ]
    },
    "stt_final_timeout_s": 4.0,
    "llm_first_token_timeout_s": 6.0,
    "tts_first_audio_timeout_s": 4.0,
    "failure_audio_enabled": true
  }
}
```

## Writing a system prompt

A system prompt tells the agent who it is, how to talk, and what to do on the call. We recommend splitting it into five sections:

| Section                        | Purpose                                                         |
| ------------------------------ | --------------------------------------------------------------- |
| **Identity**                   | Name, role, and reason for calling                              |
| **Style**                      | Tone, sentence length, filler words                             |
| **Response guidelines**        | One question at a time, how to handle mishearing, interruptions |
| **Task and conversation flow** | Step-by-step script with `<wait for response>` markers          |
| **Guardrails**                 | Topics to avoid, how to handle off-script questions             |

<Accordion title="Full example: healthcare outreach agent">
  ```text theme={null}
  [Identity]
  - Your name is Sarah, and you are a patient outreach coordinator for {{practice_name}}.
  - You are calling existing patients who are due for upcoming or overdue appointments, including annual physicals, follow-up visits, and preventive screenings.
  - Your goal is to help the patient schedule their next visit conveniently and answer basic questions about appointment availability.

  [Style]
  - Warm, caring, and conversational. You genuinely want to help the patient stay on top of their health.
  - Keep every response to 1-2 sentences. This is a phone call, not a lecture.
  - Use contractions and natural speech. Say "you're" not "you are," say "it's" not "it is."
  - Use softeners like "of course," "absolutely," "no problem," and "sure thing."
  - You may use light filler phrases like "Let me see..." or "So..." sparingly to sound natural.
  - Never use markdown, bullet points, numbered lists, or any text formatting in your responses. Everything you say will be read aloud by a text-to-speech engine and must sound completely natural as spoken language.

  [Response Guidelines]
  - Ask only one question at a time. Never stack multiple questions in a single response.
  - Wait for the patient to respond before continuing.
  - If something is unclear, politely ask for clarification.
  - Never fabricate appointment availability, medical information, or provider details.
  - Speak dates and times naturally. Say "Tuesday, March eleventh at two thirty in the afternoon" not "3/11 at 14:30."
  - When reading back any information like phone numbers or dates, normalize for speech. Say "five five five, eight six seven, five three oh nine" not "5558675309."
  - If you are not sure you heard the patient correctly, repeat back what you understood and ask for confirmation before proceeding. Speech-to-text can mishear, so always verify names, dates, and times.
  - If the patient interrupts you mid-sentence, stop speaking immediately and listen. Do not try to finish your previous thought. Acknowledge their input and adjust accordingly.

  [Task & Conversation Flow]

  1. Greet the patient by name using the greeting message. Confirm you are speaking to the right person. <wait for response>

  2. If the person confirms they are the patient, continue to step 3. If they say it is someone else or a wrong number, apologize politely and end the call.

  3. Let the patient know they are due for a visit. Say something like "I see it's been a while since your last appointment, and we'd love to get you in for a checkup." Ask if they would be interested in scheduling. <wait for response>

  4. If the patient says yes, ask what days of the week generally work best for them. <wait for response>

  5. Based on their preference, offer two specific options. Use realistic example slots such as "We have a Tuesday, March eleventh at ten in the morning, or a Thursday, March thirteenth at two thirty in the afternoon. Either of those work for you?" <wait for response>

  6. Once the patient picks a time, repeat back the full appointment details including the day, date, and time and ask them to confirm. This step is important. <wait for response>

  7. If confirmed, let them know they are all set. Mention that they may receive a reminder closer to the date. Ask if they have any questions before you go. <wait for response>

  8. If the patient says they are not interested or want to wait, respect their decision. Let them know they can call the office anytime when they are ready, and wish them well.

  9. If the patient asks about a specific doctor or provider, let them know you can check availability for that provider and adjust the offered times accordingly.

  10. If the patient asks medical questions such as symptoms, medications, or test results, let them know you are not able to provide medical advice but their care team would be happy to help with that during their visit.

  [Guardrails]
  - Never provide medical advice, diagnose symptoms, or discuss test results.
  - Never access, share, or discuss specific medical records, prescriptions, or treatment details.
  - Never pressure the patient into scheduling. If they decline, accept it gracefully.
  - Do not discuss billing, insurance coverage, or payment information. If asked, let them know the office billing team can help with those questions.
  - If the patient asks about something outside your scope, say something like "That's a great question. The team at the office would be the best ones to help with that."
  - If the conversation drifts off topic, gently guide it back by saying "I appreciate that. So regarding getting your visit on the calendar, would you like to pick a time?"
  - If the patient repeats "hello" or "hi" multiple times, respond with "I'm here, can you hear me alright?"
  - If there is prolonged silence, prompt gently with "Are you still there?" or "Take your time, I'm here whenever you're ready."
  - Never mention or imply that you are an AI, a bot, or an automated system unless directly asked.
  ```
</Accordion>

A few things worth calling out:

* **Keep it spoken.** The output goes through TTS, so write the way you'd actually talk. No markdown formatting, no numbered lists in the agent's responses.
* **One question per turn.** Stacking questions confuses both the caller and the STT model.
* **Use `<wait for response>` markers.** They make the conversation flow explicit for the LLM.
* **Normalize for speech.** Phone numbers, dates, and times should be written out the way you'd say them aloud.

## Tools

Agents support four tool types. You pass them in the `tools` array when creating or updating an agent.

### Template tools

Two built-in templates: `hangup` and `voicemail_detection`. These handle call control without any backend setup.

```json theme={null}
{
  "type": "template",
  "id": "dc4d6391-dc51-44e3-a816-bf65948290a2",
  "template": "hangup",
  "execution_policy": {
    "pre_action_message": {
      "enabled": true,
      "text": "Thank you for your time. Have a great day."
    }
  }
}
```

The `execution_policy.pre_action_message` tells the agent to say something before executing the tool. For `hangup`, the agent will speak the text and then end the call.

You can override the default tool prompt with the `prompt` field if you want to change when the LLM decides to use the tool.

### Current date/time tool

Use the `current_datetime` built-in when the agent needs reliable time-sensitive context without calling your backend.

```json theme={null}
{
  "type": "built_in",
  "id": "f0d84ac5-7988-460c-995d-2ad9621c09bb",
  "built_in": "current_datetime",
  "timezone": "Europe/Madrid",
  "prompt": "Use this whenever you need the current local date, time, day, or UTC offset for the caller."
}
```

At runtime this becomes a `get_current_datetime` tool and returns a JSON object with:

* `timezone`
* `local_datetime`
* `local_date`
* `local_time`
* `day_of_week`
* `utc_offset`
* `is_dst`

Like webhook tools, you can also configure it with `"source": "system"` and `system.triggers` if you want the runtime to inject current date/time context automatically on events like `call_start`.

### Webhook tools

Webhook tools call your backend over HTTP. The LLM decides when to invoke them based on the `name` and `description` you provide. Parameters follow JSON Schema.

```json theme={null}
{
  "type": "webhook",
  "id": "d8f8c1d7-3cf0-4c95-bb06-f28a2a1d2b50",
  "name": "check_order",
  "description": "Look up the status of a customer order",
  "url": "https://api.yourcompany.com/orders/lookup",
  "parameters": {
    "type": "object",
    "properties": {
      "order_id": { "type": "string", "description": "The order ID" },
      "customer_email": {
        "type": "string",
        "description": "Customer email for verification"
      }
    },
    "required": ["order_id", "customer_email"]
  },
  "auth": { "type": "bearer", "token": "your-api-token" },
  "timeout_seconds": 10
}
```

**Authentication**: Two options:

* `"auth": { "type": "bearer", "token": "..." }` sends an `Authorization: Bearer <token>` header
* `"auth": { "type": "hmac", "secret": "..." }` sends an `X-Signature-256` header (HMAC-SHA256 of the request body)

Secrets are write-only. The API never returns them.

**Fire-and-forget**: Set `"wait_for_response": false` when you don't need the result back in the conversation, like logging a call event to your CRM.

**Result visibility**: Use `"show_results_to_llm": false` when a webhook should run but the successful response body should stay hidden from the model. Use `llm_result_instructions` to tell the model how to use a successful response when it is visible. `llm_result_instructions` is static configuration and does not support runtime personalization.

**URL personalization**: Webhook URLs may use `{{variables}}`, but only in path segments and query parameter values. The scheme, host, port, credentials, fragments, and query parameter names must remain literal.

### System-triggered webhooks

By default, webhook tools are `"source": "contextual"`: the LLM calls them during conversation. Set `"source": "system"` to trigger them automatically on specific events instead.

```json theme={null}
{
  "type": "webhook",
  "id": "a1b2c3d4-5678-9abc-def0-123456789abc",
  "name": "post_call_summary",
  "description": "Send a call summary to the CRM after the call ends",
  "url": "https://api.yourcompany.com/call-summaries",
  "parameters": { "type": "object", "properties": {} },
  "source": "system",
  "wait_for_response": false,
  "system": {
    "triggers": [{ "event": "call_end" }],
    "arguments": [
      {
        "name": "call_id",
        "type": "string",
        "required": true,
        "source": { "type": "call_id" }
      },
      {
        "name": "transcript",
        "type": "transcript_messages",
        "required": true,
        "source": { "type": "transcript_messages", "max_messages": 200 }
      }
    ]
  }
}
```

Available trigger events: `call_start`, `first_user_message`, `call_end`, `tool_succeeded`, `tool_failed`. For `tool_succeeded` and `tool_failed`, you also need to set `source_tool_id` to specify which tool's outcome fires the trigger.

Arguments can pull from several sources:

| Source type                      | What it provides                                           |
| -------------------------------- | ---------------------------------------------------------- |
| `constant`                       | A fixed value you define                                   |
| `transcript_messages`            | Recent conversation transcript (bounded by `max_messages`) |
| `call_id`, `room_name`, `job_id` | IDs from the current session                               |
| `agent_id`, `agent_name`         | The agent's own metadata                                   |
| `phone_number`                   | Caller's phone number                                      |
| `first_user_message`             | The first thing the caller said                            |
| `call_end_reason`                | Why the call ended                                         |

System webhook `description`, `llm_result_instructions`, and `execution_policy.pre_action_message.text`
must remain static. Only `url` and `system.arguments[*].source.template` support runtime
personalization for webhook tools.

### Human transfer

Transfers the caller to a phone number. Requires an outbound SIP trunk on the agent.

```json theme={null}
{
  "type": "human_transfer",
  "id": "b2c3d4e5-6789-abcd-ef01-234567890abc",
  "name": "transfer_to_support",
  "description": "Transfer the caller to a live support agent",
  "phone_number": "+14155559999",
  "execution_policy": {
    "pre_action_message": {
      "enabled": true,
      "text": "Let me connect you to a live support specialist."
    }
  }
}
```

The LLM uses the `name` and `description` to decide when to transfer, just like webhook tools.

### Idle nudges

`idle_nudges` configures what the runtime should do when the caller goes silent for too long.

```json theme={null}
{
  "idle_nudges": {
    "enabled": true,
    "first_nudge_delay_seconds": 15,
    "second_nudge_delay_seconds": 30,
    "hangup_delay_seconds": 15,
    "first_nudge_text": "Are you still there?",
    "second_nudge_text": "I’m still here if you need a moment.",
    "final_hangup_text": "I’m going to disconnect for now. Feel free to call us back anytime."
  }
}
```

If you omit `idle_nudges`, the backend can apply language-specific defaults when returning the agent configuration.

## Tool personalization

Tool personalization uses the same `{{variable}}` syntax as prompts and greetings, but only on runtime-safe tool fields. Tool fields are validated when the tool runs rather than when the call starts.

* **Prompt and greeting variables** are start-critical. Missing values can block the session.
* **Tool-only variables** are runtime-only. Missing or invalid values fail the tool, not the call.

Supported surfaces in v1:

| Tool surface                             | Supports personalization | Notes                                                                                                                                      |
| ---------------------------------------- | ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------ |
| Contextual webhook `url`                 | Yes                      | Only in path segments and query parameter values. Scheme, host, port, credentials, fragments, and query parameter names must stay literal. |
| System webhook `url`                     | Yes                      | Only in path segments and query parameter values. Scheme, host, port, credentials, fragments, and query parameter names must stay literal. |
| System webhook argument values           | Yes                      | Scalar values only in v1 (`string`, `integer`, `number`, `boolean`)                                                                        |
| System webhook `description`             | No                       | Must stay static                                                                                                                           |
| System webhook `llm_result_instructions` | No                       | Must stay static                                                                                                                           |
| System webhook pre-action message text   | No                       | Must stay static                                                                                                                           |
| Human transfer `phone_number`            | Yes                      | Must resolve to E.164                                                                                                                      |
| Built-in `timezone`                      | Yes                      | Must resolve to an IANA timezone                                                                                                           |
| Auth secrets                             | No                       | Secrets remain literal-only                                                                                                                |

```json theme={null}
{
  "tools": [
    {
      "type": "webhook",
      "id": "2e4e8759-8467-4a53-9c96-0e08112ea13d",
      "name": "lookup_catalog_item",
      "description": "Load item details before continuing.",
      "url": "https://api.example.com/catalog/{{item_id}}/webhook?case={{case_id}}",
      "parameters": { "type": "object", "properties": {} },
      "source": "system",
      "system": {
        "triggers": [{ "event": "call_end" }],
        "arguments": [
          { "name": "retry_count", "type": "integer", "source": { "type": "template", "template": "{{max_retries}}" } },
          { "name": "vip", "type": "boolean", "source": { "type": "template", "template": "{{is_vip}}" } }
        ]
      }
    },
    {
      "type": "human_transfer",
      "id": "af5265b7-4a93-4bf5-a56a-7ccb0f3c0145",
      "name": "transfer_to_support",
      "phone_number": "+34{{local_number}}"
    },
    {
      "type": "built_in",
      "id": "0d2fdfe8-0375-4283-bfe0-e6013ed1df59",
      "built_in": "current_datetime",
      "timezone": "Europe/{{timezone_city}}"
    }
  ]
}
```

Validation rules:

* URLs must resolve to a full `http://` or `https://` URL while preserving the configured origin.
* URL placeholders are allowed only in path segments and query parameter values, and rejected in scheme, host, port, user info, fragments, and query parameter names.
* `phone_number` must resolve to E.164, for example `+34600111222`.
* `timezone` must resolve to an IANA timezone, for example `Europe/Madrid`.
* Templated system argument values are scalar-only in v1. Arrays must remain literal constants.
* `description`, `llm_result_instructions`, and pre-action message text are static configuration and do not support runtime personalization.

Runtime `arguments` are bounded:

* Maximum 32 keys
* Maximum key length 64 characters
* Maximum value length 1024 characters
* Maximum combined value length 8192 characters
* Template substitution only. Expressions and formulas are not supported.

## Template variables

Use `{{variable_name}}` anywhere in the `system_prompt` or `greeting` to inject values at runtime.

There are two layers:

1. **`template_defaults`**: Default values set on the agent itself. These apply to every call unless overridden.
2. **`arguments`**: Per-call overrides passed when [dispatching a call](/examples/agents-calls#calls-with-template-variables).

```json theme={null}
// On the agent
{
  "system_prompt": "You are an outreach coordinator for {{practice_name}}. You are calling {{patient_name}}.",
  "greeting": "Hi, is this {{patient_name}}?",
  "template_defaults": {
    "practice_name": "Greenfield Family Medicine",
    "patient_name": "there"
  }
}
```

```json theme={null}
// When dispatching a call: overrides template_defaults
{
  "phone_number": "+14155551234",
  "arguments": {
    "patient_name": "Maria"
  }
}
```

In this example, `patient_name` resolves to "Maria" (from the call arguments) and `practice_name` resolves to "Greenfield Family Medicine" (from the agent defaults).

The API response includes a `template_variables` field that lists every `{{variable}}` found in the prompt, along with whether it has a default value. This is useful for validating your templates before dispatching calls.

Per-call `arguments` are limited to 32 keys, with keys up to 64 characters, values up to 1024
characters, and a combined value payload up to 8192 characters.

## Runtime variables

Use `runtime_variables` when the model needs to capture call-scoped values during the conversation
and reuse them later in tool configuration.

These values:

* exist only for the active call or web session
* are set by the model through the built-in `set_runtime_variables` tool
* can be referenced in webhook URLs and system tool template arguments using the same
  `{{variable_name}}` syntax

```json theme={null}
{
  "runtime_variables": [
    {
      "name": "order_id",
      "description": "Customer order identifier gathered during the call."
    },
    {
      "name": "issue_type",
      "description": "Short label for the support issue."
    }
  ]
}
```

## Next steps

<CardGroup>
  <Card title="Agent API examples" icon="code" href="/examples/agents-api">
    Create, test, update, and delete agents with code.
  </Card>

  <Card title="Dispatching calls" icon="phone" href="/examples/agents-calls">
    Outbound calls, template variables, and batch dispatch.
  </Card>
</CardGroup>


# Speech-to-text HTTP examples
Source: https://docs.slng.ai/examples/stt-http

Code samples in curl, Python, and Node.js for basic transcription, word timestamps, and diarization.

These examples use the Deepgram Nova model; see the [Speech-to-Text models](/models/stt) for other models and endpoints.

## Placeholders

The snippets below use these placeholders. Replace them before running the code.

| Placeholder    | Replace with                                                          |
| -------------- | --------------------------------------------------------------------- |
| `SLNG_API_KEY` | An SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys) |

## Basic File Transcription

Upload an audio file (MP3, WAV, FLAC, OGG, M4A, or WebM) and get back the transcribed text. Here is a sample file you can use:

<AudioPlayer title="Micro Machines sample" description="Download this file to try the example below." />

<CodeGroup>
  ```bash cURL theme={null}
  curl https://api.slng.ai/v1/stt/slng/deepgram/nova:3-en \
    -H "Authorization: Bearer SLNG_API_KEY" \
    -F "audio=@micro-machines.wav"
  ```

  ```javascript JavaScript theme={null}
  const formData = new FormData();
  formData.append("audio", audioFile); // File from <input type="file">

  const response = await fetch(
    "https://api.slng.ai/v1/stt/slng/deepgram/nova:3-en",
    {
      method: "POST",
      headers: {
        Authorization: "Bearer SLNG_API_KEY",
      },
      body: formData,
    },
  );

  const result = await response.json();
  console.log("Transcription:", result.results.channels[0].alternatives[0].transcript);
  ```

  ```python Python theme={null}
  import requests

  url = "https://api.slng.ai/v1/stt/slng/deepgram/nova:3-en"
  headers = {"Authorization": "Bearer SLNG_API_KEY"}

  with open("micro-machines.wav", "rb") as audio_file:
      response = requests.post(url, headers=headers, files={"audio": audio_file})

  result = response.json()
  print("Transcription:", result["results"]["channels"][0]["alternatives"][0]["transcript"])
  ```
</CodeGroup>

You should get a response like this:

```json theme={null}
{
  "metadata": {
    "request_id": "e5fed572-6eac-4b70-81f3-21ba1641dd12",
    "duration": 29.888374,
    "channels": 1,
    "model_info": {
      "1abfe86b-e047-4eed-858a-35e5625b41ee": {
        "name": "2-general-nova",
        "version": "2024-01-06.5664",
        "arch": "nova-2"
      }
    }
  },
  "results": {
    "channels": [
      {
        "alternatives": [
          {
            "transcript": "is the micro machine man presenting the most midget miniature motocator of micro machine...",
            "confidence": 0.9823751,
            "words": [
              { "word": "is", "start": 0.16, "end": 0.32, "confidence": 0.998 },
              { "word": "the", "start": 0.32, "end": 0.40, "confidence": 0.613 },
              { "word": "micro", "start": 0.40, "end": 0.64, "confidence": 0.727 },
              ...
            ]
          }
        ]
      }
    ]
  }
}
```

***

## Going further

You can pass additional form fields to customize the transcription:

* **Language**: If you know the language, pass `language=en` (or `es`, `fr`, etc.). Not all models auto-detect, so setting this explicitly can improve accuracy.
* **Diarization**: Pass `diarize=true` to identify different speakers in a multi-speaker recording. The response will include a `speaker` field on each word. PLease check the models documentation for specific diarization config.
* **Punctuation**: Pass `punctuate=true` to add punctuation to the transcript automatically.

For the full parameter list per model, see the [Speech-to-Text API reference](/api-reference/stt/deepgram-nova-3/nova-3-ws).

***

## Next Steps

<CardGroup>
  <Card title="Live STT demo" icon="play" href="https://slng-stt-demo.onrender.com/">
    Try real-time speech recognition in your browser, no setup needed
  </Card>

  <Card title="STT WebSocket examples" icon="bolt" href="/examples/stt-websocket">
    Real-time transcription as users speak
  </Card>

  <Card title="Speech-to-Text models" icon="ear" href="/models/stt">
    Browse all STT models and endpoints
  </Card>

  <Card title="STT API reference" icon="code-xml" href="/api-reference/stt/deepgram-nova-3/nova-3-ws">
    Endpoint-specific parameters
  </Card>
</CardGroup>


# Speech-to-text WebSocket examples
Source: https://docs.slng.ai/examples/stt-websocket

Code samples in Python and Node.js for basic transcription, word timestamps, and diarization.

You need a working knowledge of the [WebSocket protocol](/websockets). These examples use the Deepgram Nova model; see the [Speech-to-Text models](/models/stt) for other models and endpoints.

WebSockets let you transcribe in real-time as users speak and receive interim results for immediate feedback. If you only need to transcribe pre-recorded files, [HTTP is simpler](/examples/stt-http).

## Placeholders

The snippets below use these placeholders. Replace them before running the code.

| Placeholder     | Replace with                                                                                                                              |
| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| `SLNG_API_KEY`  | An SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys). The snippets read it from the `SLNG_API_KEY` environment variable. |
| `recording.wav` | A local WAV or raw PCM audio file to transcribe                                                                                           |

## Message Flow

Every STT WebSocket session follows this pattern:

```mermaid theme={null}
sequenceDiagram
    participant Client
    participant SLNG
    Client->>SLNG: Connect wss://api.slng.ai/v1/stt/slng/deepgram/nova:3-en
    SLNG-->>Client: Connection open
    Client->>SLNG: { type: "init", config }
    SLNG-->>Client: { type: "ready", session_id: "..." }
    Client->>SLNG: binary audio data
    SLNG-->>Client: { type: "partial_transcript", transcript: "..." }
    Client->>SLNG: binary audio data
    SLNG-->>Client: { type: "final_transcript", transcript: "..." }
    Client->>SLNG: { type: "finalize" }
    Client->>SLNG: { type: "close" }
```

For the full list of message types and parameters, see the [WebSocket protocol reference](/websockets).

***

## Quick Start

Connect, initialize a session, stream an audio file, and print the transcription. You need a WAV or raw PCM file to test with. Any short speech recording works.

<CodeGroup>
  ```javascript JavaScript theme={null}
  // npm install ws
  const WebSocket = require("ws");
  const fs = require("fs");

  const API_KEY = process.env.SLNG_API_KEY;
  const AUDIO_FILE = process.argv[2] || "input.wav";

  const ws = new WebSocket("wss://api.slng.ai/v1/stt/slng/deepgram/nova:3-en", {
    headers: { Authorization: `Bearer ${API_KEY}` },
  });

  ws.on("open", () => {
    // 1. Initialize session
    ws.send(
      JSON.stringify({
        type: "init",
        config: {
          language: "en",
          sample_rate: 16000,
          encoding: "linear16",
        },
      }),
    );
  });

  ws.on("message", (data) => {
    const message = JSON.parse(data.toString());

    if (message.type === "ready") {
      console.log("Session ready:", message.session_id);

      // 2. Read and stream audio file in chunks
      const audio = fs.readFileSync(AUDIO_FILE);
      const CHUNK_SIZE = 4096;
      for (let i = 0; i < audio.length; i += CHUNK_SIZE) {
        ws.send(audio.slice(i, i + CHUNK_SIZE));
      }

      // 3. Signal end of audio
      ws.send(JSON.stringify({ type: "close" }));
    } else if (message.type === "partial_transcript") {
      console.log("Interim:", message.transcript);
    } else if (message.type === "final_transcript") {
      console.log("Final:", message.transcript);
    } else if (message.type === "error") {
      console.error("Error:", message.message);
      ws.close();
    }
  });

  ws.on("close", () => {
    console.log("Connection closed");
  });
  ```

  ```python Python theme={null}
  # pip install websockets
  import asyncio
  import json
  import os
  import sys
  import websockets

  CHUNK_SIZE = 4096

  async def stt_quickstart():
      api_key = os.environ["SLNG_API_KEY"]
      audio_file = sys.argv[1] if len(sys.argv) > 1 else "input.wav"
      uri = "wss://api.slng.ai/v1/stt/slng/deepgram/nova:3-en"
      headers = {"Authorization": f"Bearer {api_key}"}

      async with websockets.connect(uri, extra_headers=headers) as ws:
          # 1. Initialize session
          await ws.send(json.dumps({
              "type": "init",
              "config": {
                  "language": "en",
                  "sample_rate": 16000,
                  "encoding": "linear16",
              },
          }))

          # Wait for ready before streaming audio
          ready = json.loads(await ws.recv())
          print(f"Session ready: {ready['session_id']}")

          # 2. Read and stream audio file in chunks
          with open(audio_file, "rb") as f:
              while chunk := f.read(CHUNK_SIZE):
                  await ws.send(chunk)

          # 3. Signal end of audio
          await ws.send(json.dumps({"type": "close"}))

          # 4. Receive transcription results
          async for message in ws:
              data = json.loads(message)
              if data["type"] == "partial_transcript":
                  print(f"Interim: {data['transcript']}")
              elif data["type"] == "final_transcript":
                  print(f"Final: {data['transcript']}")
              elif data["type"] == "error":
                  print(f"Error: {data['message']}")
                  break

  asyncio.run(stt_quickstart())
  ```
</CodeGroup>

Run with:

<CodeGroup>
  ```bash JavaScript theme={null}
  node stt.js recording.wav
  ```

  ```bash Python theme={null}
  python stt.py recording.wav
  ```
</CodeGroup>

***

## Going further

The WebSocket protocol supports several options you can set in the `init` config or take advantage of in the response:

* **Interim vs final transcripts**: Partial transcripts update in real-time as the user speaks. Final transcripts are confirmed segments that won't change. Use partials for live captions and finals for processing.
* **Language**: Pass a `language` code in the init config for better accuracy. Not all models auto-detect.
* **Endpointing**: Controls how quickly the API finalizes a transcript after silence. Useful for voice agents where you want fast turn-taking.
* **Close vs finalize**: Send `{ "type": "close" }` when you are done to end the session. Use `{ "type": "finalize" }` to flush results mid-session without disconnecting.
* **Keep-alive**: For long-running sessions with periods of silence, send `{ "type": "keepalive" }` periodically to prevent idle disconnection.

For the full parameter list per model, see the [Speech-to-Text API reference](/api-reference/stt/deepgram-nova-3/nova-3-ws).

***

## Next Steps

<CardGroup>
  <Card title="Live STT demo" icon="play" href="https://slng-stt-demo.onrender.com/">
    Try real-time speech recognition in your browser, no setup needed
  </Card>

  <Card title="STT HTTP examples" icon="code-xml" href="/examples/stt-http">
    Simpler integration for pre-recorded files
  </Card>

  <Card title="WebSocket protocol" icon="plug" href="/websockets">
    Full message types, parameters, and error codes
  </Card>

  <Card title="STT API reference" icon="ear" href="/api-reference/stt/deepgram-nova-3/nova-3-ws">
    Endpoint-specific parameters
  </Card>
</CardGroup>


# Text-to-speech HTTP examples
Source: https://docs.slng.ai/examples/tts-http

Generate speech audio with the SLNG TTS HTTP API. Code samples in curl, Python, and Node.js for basic requests, voice selection, and streaming responses.

<Tip>
  Want to try TTS without setting up code? [Open the live demo](https://examples-gbcy.onrender.com) and test different models and voices in your browser.
</Tip>

These examples use the Deepgram Aura model; swap the endpoint path to use a different provider.

## Placeholders

The snippets below use these placeholders. Replace them before running the code.

| Placeholder    | Replace with                                                          |
| -------------- | --------------------------------------------------------------------- |
| `SLNG_API_KEY` | An SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys) |

## Basic Request

Send text and receive a complete audio file in WAV format:

<CodeGroup>
  ```bash cURL theme={null}
  curl https://api.slng.ai/v1/tts/slng/deepgram/aura:2-en \
    -H "Authorization: Bearer SLNG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "aura-2-thalia-en",
      "text": "Hello from sunny Barcelona!"
    }' \
    --output hello.wav
  ```

  ```javascript JavaScript theme={null}
  const response = await fetch(
    "https://api.slng.ai/v1/tts/slng/deepgram/aura:2-en",
    {
      method: "POST",
      headers: {
        Authorization: "Bearer SLNG_API_KEY",
        "Content-Type": "application/json",
      },
      body: JSON.stringify({
        model: "aura-2-thalia-en",
        text: "Hello from sunny Barcelona!",
      }),
    },
  );

  const audioData = await response.arrayBuffer();
  // Play or save audioData
  ```

  ```python Python theme={null}
  import requests

  url = "https://api.slng.ai/v1/tts/slng/deepgram/aura:2-en"
  headers = {
      "Authorization": "Bearer SLNG_API_KEY",
      "Content-Type": "application/json"
  }
  data = {
      "model": "aura-2-thalia-en",
      "text": "Hello from sunny Barcelona!",
  }

  response = requests.post(url, headers=headers, json=data)
  audio_data = response.content

  # Save to file
  with open("output.wav", "wb") as f:
      f.write(audio_data)
  ```
</CodeGroup>

It will sound like this:

<AudioPlayer title="Hello from sunny Barcelona!" />

***

## More Examples

### With Voice Selection (Deepgram Aura)

Beyond the audio generation, each model supports different parameters.

For example, to specify a voice in Deepgram Aura:

```bash highlight={6} theme={null}
curl https://api.slng.ai/v1/tts/slng/deepgram/aura:2-en \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello from sunny Barcelona!",
    "model": "aura-2-theia-en"
  }' \
  --output hello-theia.wav
```

For the complete parameter reference, see the [Text-to-Speech](/api-reference/tts/deepgram-aura-2/aura-2-english-ws) API reference.

### With a Different Model

Each model has its own endpoint and may use different parameters. For example, Rime Arcana uses `speaker` instead of `model`:

```bash highlight={1} theme={null}
curl https://api.slng.ai/v1/tts/slng/rime/arcana:3-en \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello from Rime Arcana!",
    "speaker": "astra"
  }' \
  --output hello-arcana.wav
```

For all available models, endpoints, and their parameters, see the [TTS models page](/models/tts).

To control how brand names, acronyms, and domain-specific terms are spoken, add a [pronunciation dictionary](/pronunciation-dictionaries) to your TTS request.

For voice catalogs with audio samples, browse the [Voices](/voices/deepgram-aura) section in the sidebar.

***

## Next Steps

<CardGroup>
  <Card title="Live TTS demo" icon="play" href="https://examples-gbcy.onrender.com">
    Try TTS in your browser, no setup needed
  </Card>

  <Card title="TTS WebSocket examples" icon="bolt" href="/examples/tts-websocket">
    Stream audio in real time for voice agents
  </Card>

  <Card title="Text-to-Speech models" icon="audio-lines" href="/models/tts">
    Browse all TTS models and endpoints
  </Card>

  <Card title="Pronunciation dictionaries" icon="book-open-text" href="/pronunciation-dictionaries">
    Reuse pronunciation rules across TTS requests
  </Card>

  <Card title="TTS API reference" icon="code-xml" href="/api-reference/tts/deepgram-aura-2/aura-2-english-ws">
    Endpoint-specific parameters
  </Card>
</CardGroup>


# Text-to-speech WebSocket examples
Source: https://docs.slng.ai/examples/tts-websocket

Stream speech with the SLNG TTS WebSocket API. Python and Node.js code samples for sub-100ms latency, mid-sentence interrupt, and continuous text input.

You need a working knowledge of the [WebSocket protocol](/websockets). These examples use the Deepgram Aura model; swap the endpoint path to use a different provider.

WebSockets let you stream audio with sub-100ms latency and stop mid-sentence, which is what you need for voice agent conversations. If you only need to generate audio files, [HTTP is simpler](/examples/tts-http).

## Placeholders

The snippets below use these placeholders. Replace them before running the code.

| Placeholder    | Replace with                                                                                                                              |
| -------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| `SLNG_API_KEY` | An SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys). The snippets read it from the `SLNG_API_KEY` environment variable. |

## Message Flow

Every TTS WebSocket session follows this pattern:

```mermaid theme={null}
sequenceDiagram
    participant Client
    participant SLNG
    Client->>SLNG: Connect wss://api.slng.ai/v1/tts/slng/deepgram/aura:2-en
    SLNG-->>Client: Connection open
    Client->>SLNG: { type: "init", model, voice, config }
    SLNG-->>Client: { type: "ready", session_id: "..." }
    Client->>SLNG: { type: "text", text: "Hello!" }
    SLNG-->>Client: audio chunk
    SLNG-->>Client: audio chunk
    Client->>SLNG: { type: "flush" }
    SLNG-->>Client: audio chunk
    SLNG-->>Client: { type: "flushed" }
    Client->>SLNG: { type: "close" }
```

For the full list of message types and parameters, see the [WebSocket protocol reference](/websockets). To keep acronyms, names, and domain terms consistent during synthesis, set a session default or per-turn [pronunciation dictionary](/pronunciation-dictionaries).

***

## Quick Start

Connect, initialize a session, send text, and save the audio to a file.

Both examples write a `output.pcm` file containing raw 16-bit PCM audio at 24 kHz. You can play it with [ffplay](https://ffmpeg.org/ffplay.html):

```bash theme={null}
ffplay -f s16le -ar 24000 -ac 1 output.pcm
```

<CodeGroup>
  ```javascript JavaScript theme={null}
  // npm install ws
  const WebSocket = require("ws");
  const fs = require("fs");

  const API_KEY = process.env.SLNG_API_KEY;
  const ws = new WebSocket("wss://api.slng.ai/v1/tts/slng/deepgram/aura:2-en", {
    headers: { Authorization: `Bearer ${API_KEY}` },
  });

  const audioChunks = [];

  ws.on("open", () => {
    // 1. Initialize session
    ws.send(
      JSON.stringify({
        type: "init",
        model: "aura:2-en",
        voice: "aura-2-thalia-en",
        config: {
          encoding: "linear16",
          sample_rate: 24000,
        },
      }),
    );

    // 2. Send text to convert
    ws.send(
      JSON.stringify({
        type: "text",
        text: "Hello! This is a WebSocket TTS example.",
      }),
    );

    // 3. Flush to get remaining audio
    ws.send(JSON.stringify({ type: "flush" }));
  });

  ws.on("message", (data, isBinary) => {
    if (isBinary) {
      audioChunks.push(data);
    } else {
      const message = JSON.parse(data.toString());
      if (message.type === "ready") {
        console.log("Session ready:", message.session_id);
      } else if (message.type === "flushed") {
        console.log("All audio received, saving to output.pcm");
        fs.writeFileSync("output.pcm", Buffer.concat(audioChunks));
        ws.close();
      } else if (message.type === "error") {
        console.error("Error:", message.message);
        ws.close();
      }
    }
  });
  ```

  ```python Python theme={null}
  # pip install websockets
  import asyncio
  import json
  import os
  import websockets

  async def tts_quickstart():
      api_key = os.environ["SLNG_API_KEY"]
      uri = "wss://api.slng.ai/v1/tts/slng/deepgram/aura:2-en"
      headers = {"Authorization": f"Bearer {api_key}"}

      async with websockets.connect(uri, extra_headers=headers) as ws:
          # 1. Initialize session
          await ws.send(json.dumps({
              "type": "init",
              "model": "aura:2-en",
              "voice": "aura-2-thalia-en",
              "config": {
                  "encoding": "linear16",
                  "sample_rate": 24000,
              },
          }))

          # 2. Send text to convert
          await ws.send(json.dumps({
              "type": "text",
              "text": "Hello! This is a WebSocket TTS example.",
          }))

          # 3. Flush to get remaining audio
          await ws.send(json.dumps({"type": "flush"}))

          # 4. Receive audio chunks until flushed
          audio_chunks = []
          async for message in ws:
              if isinstance(message, bytes):
                  audio_chunks.append(message)
              else:
                  data = json.loads(message)
                  if data["type"] == "ready":
                      print(f"Session ready: {data['session_id']}")
                  elif data["type"] == "flushed":
                      print("All audio received, saving to output.pcm")
                      break
                  elif data["type"] == "error":
                      print(f"Error: {data['message']}")
                      break

          with open("output.pcm", "wb") as f:
              for chunk in audio_chunks:
                  f.write(chunk)

  asyncio.run(tts_quickstart())
  ```
</CodeGroup>

***

## More Examples

### Batch Text Streaming

Send multiple sentences for smoother speech instead of one large block. This is a complete example you can run independently.

<CodeGroup>
  ```javascript JavaScript theme={null}
  // npm install ws
  const WebSocket = require("ws");
  const fs = require("fs");

  const API_KEY = process.env.SLNG_API_KEY;
  const ws = new WebSocket("wss://api.slng.ai/v1/tts/slng/deepgram/aura:2-en", {
    headers: { Authorization: `Bearer ${API_KEY}` },
  });

  const text =
    "The sun rose over the mountains. Birds began to sing in the trees. A gentle breeze carried the scent of wildflowers across the valley.";
  const audioChunks = [];

  ws.on("open", () => {
    ws.send(
      JSON.stringify({
        type: "init",
        model: "aura:2-en",
        voice: "aura-2-thalia-en",
        config: { encoding: "linear16", sample_rate: 24000 },
      }),
    );

    // Stream sentences one at a time
    const sentences = text.split(". ");
    for (const sentence of sentences) {
      ws.send(
        JSON.stringify({
          type: "text",
          text: sentence.endsWith(".") ? sentence : sentence + ".",
        }),
      );
    }

    ws.send(JSON.stringify({ type: "flush" }));
  });

  ws.on("message", (data, isBinary) => {
    if (isBinary) {
      audioChunks.push(data);
    } else {
      const message = JSON.parse(data.toString());
      if (message.type === "flushed") {
        console.log("All audio received, saving to output.pcm");
        fs.writeFileSync("output.pcm", Buffer.concat(audioChunks));
        ws.close();
      }
    }
  });
  ```

  ```python Python theme={null}
  # pip install websockets
  import asyncio
  import json
  import os
  import websockets

  async def tts_batch_streaming():
      api_key = os.environ["SLNG_API_KEY"]
      uri = "wss://api.slng.ai/v1/tts/slng/deepgram/aura:2-en"
      headers = {"Authorization": f"Bearer {api_key}"}

      text = (
          "The sun rose over the mountains. "
          "Birds began to sing in the trees. "
          "A gentle breeze carried the scent of wildflowers across the valley."
      )

      async with websockets.connect(uri, extra_headers=headers) as ws:
          await ws.send(json.dumps({
              "type": "init",
              "model": "aura:2-en",
              "voice": "aura-2-thalia-en",
              "config": {"encoding": "linear16", "sample_rate": 24000},
          }))

          # Stream sentences one at a time
          sentences = text.split(". ")
          for sentence in sentences:
              if not sentence.endswith("."):
                  sentence += "."
              await ws.send(json.dumps({
                  "type": "text",
                  "text": sentence,
              }))

          await ws.send(json.dumps({"type": "flush"}))

          # Receive audio chunks until flushed
          audio_chunks = []
          async for message in ws:
              if isinstance(message, bytes):
                  audio_chunks.append(message)
              else:
                  data = json.loads(message)
                  if data["type"] == "flushed":
                      print("All audio received, saving to output.pcm")
                      break

          with open("output.pcm", "wb") as f:
              for chunk in audio_chunks:
                  f.write(chunk)

  asyncio.run(tts_batch_streaming())
  ```
</CodeGroup>

***

## Next Steps

<CardGroup>
  <Card title="Live TTS demo" icon="play" href="https://examples-gbcy.onrender.com">
    Try real-time TTS in your browser, no setup needed
  </Card>

  <Card title="WebSocket protocol" icon="plug" href="/websockets">
    Full message types, parameters, and error codes
  </Card>

  <Card title="Pronunciation dictionaries" icon="book-open-text" href="/pronunciation-dictionaries">
    Reuse pronunciation rules across TTS requests
  </Card>

  <Card title="TTS HTTP examples" icon="file-audio" href="/examples/tts-http">
    Simpler integration for non-streaming use cases
  </Card>

  <Card title="TTS API reference" icon="audio-lines" href="/api-reference/tts/deepgram-aura-2/aura-2-english-ws">
    Endpoint-specific parameters
  </Card>
</CardGroup>


# Adaptive Execution
Source: https://docs.slng.ai/execution-layer/adaptive

Not every turn deserves the same execution path. The execution layer adapts on four dimensions, from geography and compliance to cost, latency, and workload.

Not every turn deserves the same execution path. The layer adapts on four dimensions.

## Geography

Route to the nearest region. Data stays in-jurisdiction. A caller in Frankfurt hits EU infrastructure. A caller in Mumbai hits AP South. No configuration needed: this is the default behavior.

Override with `X-Region-Override` when you need a specific datacenter, or `X-World-Part-Override` when you need to stay within a geographic zone. See [Regional Execution](/region-override).

## Compliance

Execution constraints determine where data and models can operate. Healthcare, banking, and insurance workloads have requirements about where audio can be processed and where transcripts can exist. Regional execution respects these constraints per request.

## Cost and latency

Cached path, local inference, or full reasoning, based on the input. The layer makes this decision per turn:

* A greeting that has been said a thousand times: cached path.
* A simple acknowledgment: local inference, no LLM call.
* A complex question requiring reasoning: full inference path.

Same API call from your side. The path is selected for you.

## Workload

Adapt based on model availability, caller context, and interaction characteristics. If a primary model shows elevated latency, traffic can route to a fallback. If a caller's language is better served by a specific STT model, the routing adapts.

## The result

A system where cost and latency decrease with usage, while reliability increases. Every call improves routing decisions and cache coverage for the next one.

Regulated industries (healthcare, banking, insurance) see the strongest compounding effect. Their workflows have high repetition within each customer's use cases, and the layer learns those patterns.


# Bring your own key
Source: https://docs.slng.ai/execution-layer/byok

Pass your own provider key on requests so billing runs against your provider account, while the SLNG cache still applies on top.

If you already have a contract with a text-to-speech provider, you can keep it. Bring Your Own Key (BYOK) lets you pass your own provider key on requests. Your key is forwarded upstream, so billing and rate limits run against your provider account, and [output assembly](/execution-layer/output-assembly) still applies on top.

## Placeholders

The snippets below use these placeholders. Replace them before running the code.

| Placeholder         | Replace with                                                          |
| ------------------- | --------------------------------------------------------------------- |
| `SLNG_API_KEY`      | An SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys) |
| `YOUR_PROVIDER_KEY` | A provider key issued by the upstream TTS provider you are calling    |

## How output assembly applies

Assembly runs before your request is forwarded, so a cache hit never reaches the upstream provider:

* **Cache hit**: the cached audio is returned, no provider call, and no billing event.
* **Cache miss**: the request is sent upstream with your key, the provider bills your account, and the response is cached for future requests.

## Supported providers

| Provider | Model                                                                                                                                                                  |
| -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Cartesia | [Sonic 3](/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws)                                                                                                     |
| Deepgram | [Aura 2](/api-reference/tts/deepgram-aura-2/aura-2-english-ws)                                                                                                         |
| Kugel    | [Kugel 1 Turbo](/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws), [Kugel 1](/api-reference/tts/kugel-1/kugel-1-ws), [Kugel 2](/api-reference/tts/kugel-2/kugel-2-ws) |
| Murf     | [Falcon](/api-reference/tts/murf-falcon/murf-falcon-ws)                                                                                                                |
| Sarvam   | [Bulbul](/api-reference/tts/sarvam-ai-bulbul-v3/bulbul-v3-ws)                                                                                                          |
| Soniox   | [TTS RT v1](/api-reference/tts/soniox-tts-v1/soniox-tts-v1-ws)                                                                                                         |

## Send a BYOK request

Add the `X-Slng-Provider-Key` header alongside your standard SLNG `Authorization` header.

### HTTP

```bash highlight={3} theme={null}
curl -X POST "https://api.slng.ai/v1/tts/sarvam/bulbul:v3" \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -H "X-Slng-Provider-Key: YOUR_PROVIDER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "I brought my own key to the party.",
    "target_language_code": "en-IN",
    "speaker": "shubh",
    "model": "bulbul:v3"
  }'
```

### WebSocket

Set `X-Slng-Provider-Key` as a header on the WebSocket upgrade request. The message flow after the upgrade is unchanged.

```http theme={null}
X-Slng-Provider-Key: YOUR_PROVIDER_KEY
```

<Note>
  The browser WebSocket API does not support custom headers. Set the provider key from a server-side WebSocket client.
</Note>

## Error handling

### HTTP

If the upstream provider rejects your key, the provider's error response is returned with this header:

```http theme={null}
X-Slng-Auth-Source: client_key
```

That header tells you the failure came from your provider key, not from SLNG.

### WebSocket

Auth failures surface as a WebSocket error frame after the upgrade is accepted, for example `backend_connection_failed`, with the upstream 401 or 403 detail included.

## Billing

The upstream provider bills your account directly for BYOK requests. No audio-minute fees apply to BYOK traffic.

## Next steps

<CardGroup>
  <Card title="Output assembly" icon="database" href="/execution-layer/output-assembly">
    How assembled-from-cache output cuts cost and latency on repeated text.
  </Card>

  <Card title="Drop-in gateway" icon="plug" href="/integrations/gateway">
    Route your existing stack through SLNG.
  </Card>
</CardGroup>


# How It Works
Source: https://docs.slng.ai/execution-layer/how-it-works

SLNG runs three stages between your orchestrator and the models, one for each part of the voice pipeline. Each removes a category of unnecessary compute.

SLNG runs three stages between your orchestrator and the models you use, one for each part of the voice pipeline. Each removes a category of unnecessary compute.

## Request lifecycle of a single turn

When a caller speaks:

1. **Audio arrives** from the caller via your orchestrator.
2. **STT Routing** selects the transcription model based on language, accent, noise profile, and cost constraints.
3. **Transcript** goes to your orchestrator's LLM, or to SLNG's tiered decisioning.
4. **Tiered Decisioning** determines whether the turn needs full inference, local inference, or can be resolved without calling the LLM.
5. **The response** (LLM, cached, or deterministic) is sent to TTS.
6. **Output Assembly** checks cache, assembles from segments where possible, and generates only what is new.
7. **Audio returns** to the caller.

These stages do not have to run in strict sequence. Assembly can begin before the LLM has finished its full response.

## Three stages

### STT Routing `PRIVATE BETA`

The first stage. When audio arrives, it is routed to the right STT model for that specific interaction. A Hindi caller in Mumbai gets a different model than an English caller in New York. A noisy environment may route to a model with better noise handling. The layer balances accuracy, latency, and cost per turn.

See [STT Routing](/execution-layer/stt-routing) for details.

### Tiered Decisioning

The second stage. Not every turn needs full LLM inference. A consent disclosure repeated for the hundredth time does not need a reasoning model. It needs a deterministic, low-latency response.

Intelligence is allocated where it is needed and skipped where it is not.

See [Tiered Decisioning](/execution-layer/tiered-decisioning) for details.

### Output Assembly

The third stage. TTS on the execution layer is assembly, not generation. When a turn produces text for speech, the layer checks whether this output, or parts of it, has been assembled before. A miss is synthesized, cached, and served from cache next time.

See [Output Assembly](/execution-layer/output-assembly) for details.

## Regional execution

All three stages run across a global edge network. By default, requests route to the lowest-latency region. You can pin to specific regions for compliance or performance.

See [Regional Execution](/region-override) for details.

## Continuous improvement

As more calls flow through the layer, routing decisions sharpen, cache coverage grows, and tier allocation becomes more accurate. Every call makes the next one more efficient.


# The Execution Layer
Source: https://docs.slng.ai/execution-layer/index

The execution layer gives you control of your voice calls. It reduces latency and model cost across the pipeline, using your existing tools, while improving reliability.

This layer is built to give you control of your voice calls. It reduces latency and model cost across the voice pipeline, using your existing tools, while improving reliability.

## The problem

A 16-turn voice call makes 48 model calls: STT, LLM, and TTS on every turn. Without an execution layer, each of those 48 runs from scratch. At 1M calls per month, that is 48M inference calls, every one generated fresh regardless of whether the output has been produced before.

The same consent disclosure. The same hold message. The same greeting. Generated from scratch, every time.

## What the execution layer changes

Every turn is routed through the execution path it actually needs. Three stages, one for each part of the voice pipeline:

| Stage                  | What it does                                                                                  |
| ---------------------- | --------------------------------------------------------------------------------------------- |
| **STT Routing**        | Route input to the right transcription model, based on language, accent, noise, and cost.     |
| **Tiered Decisioning** | Determine whether the turn needs full LLM reasoning, local inference, or no inference at all. |
| **Output Assembly**    | Assemble TTS output from cache and synthesis. Don't generate what already exists.             |

These stages run across a global network of edge points, with regional execution that keeps data in-jurisdiction.

## The system improves under load

Every call through the system improves routing decisions and cache coverage for the next one. Cost and latency decrease with usage. Reliability increases.

* More calls, more cache coverage, fewer model calls, lower cost
* More patterns observed, better routing decisions, lower latency
* More providers configured, more failover options, higher reliability

## What customers see

| Metric                      | Improvement                 |
| --------------------------- | --------------------------- |
| End-to-end latency per turn | Up to 48% reduction         |
| Total pipeline cost         | Up to 57% reduction         |
| Call completion rate        | Zero dropped, zero downtime |

## How to integrate

SLNG works with the orchestrator and models you already use. The endpoints sit between your orchestrator and your providers.

<CardGroup>
  <Card title="How It Works" icon="route" href="/execution-layer/how-it-works">
    Architecture and the request lifecycle.
  </Card>

  <Card title="Adaptive Execution" icon="shuffle" href="/execution-layer/adaptive">
    How path selection works.
  </Card>

  <Card title="Integrations" icon="cable" href="/integrations/overview">
    Connect your orchestrator.
  </Card>
</CardGroup>


# Output Assembly
Source: https://docs.slng.ai/execution-layer/output-assembly

TTS on the execution layer is assembly, not generation. Output is served from cache when possible and synthesized only when genuinely new.

TTS on the execution layer is assembly, not generation.

When a turn produces text for speech, it is not blindly forwarded to a TTS model. The layer determines the way to produce the audio: serving from cache when possible, generating only what is genuinely new. The goal is to not generate what already exists.

## The principle

In a traditional voice pipeline, every TTS request is a fresh synthesis call. The same greeting, the same compliance disclosure, the same hold message, generated from scratch every time, billed every time.

Output assembly changes this. When audio has been produced before for the same request, it is served instantly, with no upstream model call and no provider billing. When it has not, it is generated, and the result is available for future requests.

## How it improves over time

Output assembly is not a static cache. It improves as call volume grows:

* **Coverage expands with usage.** Every new phrase your agents speak adds to the cache.
* **Repetition compounds.** Voice agents naturally repeat greetings, confirmations, disclosures, hold messages, and error handling.
* **Industry patterns accelerate improvement.** Regulated industries see the fastest improvement because their workflows have high repetition.
* **Cost decreases structurally.** As coverage grows, fewer turns hit the upstream model.

## What this means

| Without output assembly                     | With output assembly                              |
| ------------------------------------------- | ------------------------------------------------- |
| Every TTS request is a fresh synthesis call | Only novel text triggers synthesis                |
| Cost is constant per turn                   | Cost per turn decreases as coverage grows         |
| Latency depends on the model every time     | Cached responses return from the edge             |
| Switching TTS models means starting over    | Pronunciation rules carry over across model swaps |

## Cache isolation

Every cache entry is scoped and isolated by:

* **Region**: cache is local to the region where the request executes.
* **Customer**: your cache is yours. No data is shared across SLNG customers.
* **Use case**: different agents, voices, and configurations maintain separate cache namespaces.

Your audio, your data, your cache, fully isolated.

## Pronunciation dictionaries

Before text reaches any TTS model, pronunciation rewrite rules normalize brand names, acronyms, and domain terms, regardless of which model synthesizes the audio. Your rules carry over when you swap TTS models. See [Pronunciation Dictionaries](/pronunciation-dictionaries) for the full API.

## BYOK (Bring Your Own Key)

With [BYOK](/execution-layer/byok), you pass your own provider key on TTS requests. Output assembly still applies: a cache hit never reaches the provider, so you are not billed; a miss uses your key for synthesis and caches the result. Your existing provider contracts and volume discounts stay intact.

## Configuration

Output assembly is automatic. Every TTS request goes through it. You shape the behavior through:

* **Model and voice selection**: determines the cache namespace.
* **Pronunciation dictionaries**: control text rewriting before synthesis.
* **BYOK**: use your own provider keys with the same assembly logic.
* **Region**: determines which edge cache is consulted first.

Timeout settings for the TTS stage:

| Setting                     | Default | Description                                                     |
| --------------------------- | ------- | --------------------------------------------------------------- |
| `tts_first_audio_timeout_s` | 4.0     | Maximum wait for first audio from the TTS model before failover |
| `failure_audio_enabled`     | true    | Play a failure audio clip if all TTS paths fail                 |


# STT Routing
Source: https://docs.slng.ai/execution-layer/stt-routing

The first stage of the execution layer routes each turn's audio to the transcription model best suited to it, balancing accuracy, latency, and cost.

<Note>
  STT Routing is in `PRIVATE BETA`. The behavior described here is being rolled
  out gradually. [Contact us](mailto:support@slng.ai) for access.
</Note>

The first stage of the execution layer. When audio arrives, it is routed to the right STT model for that specific interaction.

A Hindi caller in Mumbai gets a different model than an English caller in New York. A noisy environment may route to a model with better noise handling. The layer balances accuracy, latency, and cost per turn.

## How it routes

Routing weighs several inputs together, not in isolation:

* **Language and accent** of the audio
* **Noise profile** of the environment
* **Regional availability** of models
* **Cost and latency** constraints

For voice agent calls, routing happens per turn. Each turn can route to the model best suited to that specific audio segment.

## Today

Until STT Routing is generally available, you select the STT model explicitly on each request. See the [Speech-to-Text Overview](/stt/overview) for the current model list and how to choose.

## Related

<CardGroup>
  <Card title="Speech-to-Text Overview" icon="ear" href="/stt/overview">
    The models available today and how to pick one.
  </Card>

  <Card title="How It Works" icon="route" href="/execution-layer/how-it-works">
    Where STT routing sits in the pipeline.
  </Card>
</CardGroup>


# Tiered Decisioning
Source: https://docs.slng.ai/execution-layer/tiered-decisioning

Not every turn in a voice call needs full LLM inference. SLNG allocates reasoning where it's needed and resolves repeatable turns through shorter paths.

<Note>
  The LLM-tiering behavior on this page is being rolled out and verified.
  [Contact us](mailto:support@slng.ai) to discuss availability for your account.
</Note>

Not every turn in a voice call needs full LLM inference.

A consent disclosure repeated for the hundredth time. A hold message. A standard greeting. An acknowledgment like "got it, one moment." These do not need a reasoning model. They need a deterministic, low-latency response.

Tiered decisioning allocates intelligence where it is needed and skips it where it is not.

## Adaptive execution paths

In a traditional voice pipeline, every turn takes the same path: audio in, STT, LLM, TTS, audio out. The same pipeline and the same cost, whether the caller asked a complex question or said "yes."

The execution layer constructs the path for each turn based on the full context of the conversation: what was said, what has been said before, how the call is progressing, and what the turn actually requires. The decision is not just which model to call, but whether to call a model at all, which stages to invoke, and how to assemble the response.

Same API call from your side. The path is constructed for you.

## Paths adapt in real time

Within a single call, the path can change turn by turn. The first turn might need full reasoning to understand intent. The next few might resolve through shorter paths as the conversation enters a familiar pattern. Then a turn introduces new complexity and the path expands again.

The decision factors are compound (language, intent, similarity to prior turns, availability of cached responses, model load, regional constraints) and they are evaluated together.

## How it improves over time

The layer learns from every call:

* **Path intelligence sharpens with volume.** Early on, more turns take the full path as a safe default. Over time, a growing proportion route through faster, cheaper paths.
* **Your call patterns shape your optimization.** A healthcare scheduling agent develops different path intelligence than a financial-services collections agent.
* **Improvement is continuous.** You do not retrain anything. The layer observes outcomes and the next call benefits.

## What this means

| Without tiered decisioning                        | With tiered decisioning                                   |
| ------------------------------------------------- | --------------------------------------------------------- |
| Every turn hits the LLM                           | Only turns that need reasoning hit the LLM                |
| Latency is constant regardless of turn complexity | Simple turns resolve faster through a shorter path        |
| Cost scales linearly with call volume             | Cost per call decreases as the layer learns your patterns |

## Configuration

LLM model selection and failover are configured on the voice agent:

```json theme={null}
{
  "models": {
    "llm": "groq/moonshotai/kimi-k2-instruct-0905",
    "fallbacks": {
      "llm": ["groq/moonshotai/kimi-k2-instruct-0905"]
    },
    "llm_first_token_timeout_s": 6.0
  }
}
```

| Setting                     | Default | Description                                                   |
| --------------------------- | ------- | ------------------------------------------------------------- |
| `llm_first_token_timeout_s` | 6.0     | Maximum wait for the first token from the LLM before failover |

See [Configuration & Tools](/examples/agents-config#models) for the full model configuration reference.


# SLNG Unified API
Source: https://docs.slng.ai/execution-layer/unified-api

The SLNG Unified API gives you one request format for every STT and TTS model. Swap Deepgram, Rime, Cartesia, and more by changing the URL.

One endpoint pattern for every STT and TTS model on the platform. Switch providers by changing the URL path. Your code, auth, and request format don't change.

## Swap models by changing the URL

Every request uses the same base URL. The only part that changes is the model path:

|                               | Base URL                             | Model path                    |
| ----------------------------- | ------------------------------------ | ----------------------------- |
| Deepgram Nova 3 (proxied)     | `api.slng.ai/v1/bridges/unmute/stt/` | **`deepgram/nova:3`**         |
| Deepgram Nova 3 (SLNG-hosted) | `api.slng.ai/v1/bridges/unmute/stt/` | **`slng/deepgram/nova:3-en`** |
| Deepgram Aura 2               | `api.slng.ai/v1/bridges/unmute/tts/` | **`slng/deepgram/aura:2-en`** |
| Rime Arcana v3                | `api.slng.ai/v1/bridges/unmute/tts/` | **`slng/rime/arcana:3-en`**   |

Authentication, request body, and response format are identical. Only the path differs.

## Why a unified interface

Most voice AI stacks lock you into one provider's SDK, request format, and response structure. The Unified API removes that friction.

| Without SLNG Unified API                | With SLNG Unified API                          |
| --------------------------------------- | ---------------------------------------------- |
| One SDK per provider                    | One HTTP/WebSocket endpoint for all            |
| Different request schemas               | Same request body across providers             |
| Provider-specific error handling        | Consistent error responses                     |
| Weeks to evaluate a new model           | Change the URL path, test immediately          |
| Manual upgrades when better models ship | New models available as soon as SLNG adds them |

Common patterns:

* **A/B testing**: route a percentage of traffic to a different model path with no code change.
* **Failover**: switch providers by changing the model path; request format and error handling stay the same.
* **Latency optimization**: deploy across regions and route each one to the lowest-latency model.
* **Rapid prototyping**: try a new model by changing the URL.

The Unified API doesn't hide provider capabilities. Pass voice identifiers, sample rates, encodings, language codes, and speed settings through the `config` object. See [Parameters coverage](/execution-layer/unified-api-parameters) for the full list.

## Works over HTTP and WebSocket

The same model path works with both protocols:

| Protocol  | URL                                                                 |
| --------- | ------------------------------------------------------------------- |
| HTTP      | `https://api.slng.ai/v1/bridges/unmute/tts/slng/deepgram/aura:2-en` |
| WebSocket | `wss://api.slng.ai/v1/bridges/unmute/tts/slng/deepgram/aura:2-en`   |

Use HTTP for batch jobs and file conversion. Use WebSocket for real-time streaming and voice agents. See [HTTP vs. WebSocket](/protocols) for details.

## Get started

### Prerequisites

* An SLNG key ([get one here](https://app.slng.ai/api-keys))
* `curl` installed (or any HTTP client)

### Authentication

All requests require a Bearer token:

```bash theme={null}
Authorization: Bearer SLNG_API_KEY
```

### Text-to-Speech

Generate speech from text. Here's a request using Rime Arcana v3:

```bash theme={null}
curl -X POST https://api.slng.ai/v1/bridges/unmute/tts/slng/rime/arcana:3-en \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voice": "luna",
    "text": "Hello from the SLNG Unified API!"
  }' \
  --output hello.wav
```

This saves a WAV file. You can set encoding and sample rate through the `config` object.

To make acronyms, product names, and domain terms speak consistently across TTS models, attach a [pronunciation dictionary](/pronunciation-dictionaries) to the request.

<Note>
  The model is inferred from the URL path. Do not include a duplicate `model` field in the request body unless an endpoint reference explicitly requires it.
</Note>

Switch to Deepgram Aura 2 by changing the URL path and adapting the voice.

```bash highlight={1} theme={null}
curl -X POST https://api.slng.ai/v1/bridges/unmute/tts/slng/deepgram/aura:2-en \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voice": "aura-2-asteria-en",
    "text": "Hello from the SLNG Unified API!"
  }' \
  --output hello.wav
```

### Speech-to-Text

Transcribe audio with SLNG-hosted Deepgram Nova 3:

```bash theme={null}
curl -X POST https://api.slng.ai/v1/bridges/unmute/stt/slng/deepgram/nova:3-en \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -F "audio=@recording.wav" \
  -F "language=en"
```

Switch to proxied Deepgram Nova 3 for 17-language coverage. Only the URL changes:

```bash highlight={1} theme={null}
curl -X POST https://api.slng.ai/v1/bridges/unmute/stt/deepgram/nova:3 \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -F "audio=@recording.wav" \
  -F "language=en"
```

### WebSocket streaming

The same model paths work over WebSocket for real-time streaming. Connect to `wss://` instead of posting to `https://`.

<Note>
  The browser WebSocket API does not support custom headers. Pass the SLNG key as a query parameter or use a server-side WebSocket client. The example below uses the Node.js `ws` library.
</Note>

```javascript theme={null}
import WebSocket from "ws";

const ws = new WebSocket(
  "wss://api.slng.ai/v1/bridges/unmute/tts/slng/deepgram/aura:2-en",
  { headers: { Authorization: "Bearer SLNG_API_KEY" } }
);

ws.on("open", () => {
  ws.send(JSON.stringify({
    voice: "aura-2-asteria-en",
    text: "Streaming audio in real time."
  }));
});

ws.on("message", (data) => {
  // Binary frames contain audio chunks
  if (Buffer.isBuffer(data)) {
    process.stdout.write(data);
  }
});
```

For browser-based WebSocket examples, see [TTS over WebSocket](/examples/tts-websocket).

## Next steps

<CardGroup>
  <Card title="Parameters coverage" icon="table-properties" href="/execution-layer/unified-api-parameters">
    See which parameters each provider supports.
  </Card>

  <Card title="Supported models" icon="cpu" href="/execution-layer/unified-api-models">
    Browse all models available through the Unified API.
  </Card>

  <Card title="HTTP vs. WebSocket" icon="arrow-left-right" href="/protocols">
    When to use each protocol and their trade-offs.
  </Card>
</CardGroup>


# Supported models
Source: https://docs.slng.ai/execution-layer/unified-api-models

Full list of TTS and STT models reachable through the SLNG Unified API. Deepgram Nova and Aura, Rime Arcana, ElevenLabs, Cartesia, Sarvam, and more.

Every model on the SLNG platform works through the Unified API. Some run on SLNG infrastructure (SLNG-hosted), others are proxied to the provider's own API.

<Info>
  SLNG-hosted models use the `slng/` prefix in the model identifier. They are optimized for low latency in specific regions and billed through your SLNG account with no separate provider account needed.
</Info>

## Text-to-Speech

<AccordionGroup>
  <Accordion title="Rime Arcana v3" icon="waveform">
    **Provider:** Rime | **Hosting:** SLNG | **Languages:** English, Hindi

    Natural prosody with improved voice quality over v1. French and Spanish support planned.

    | Identifier              | Description |
    | ----------------------- | ----------- |
    | `slng/rime/arcana:3-en` | English     |
    | `slng/rime/arcana:3-hi` | Hindi       |

    Best for: conversational agents, high-quality voice output.
  </Accordion>

  <Accordion title="Rime Arcana v1" icon="waveform">
    **Provider:** Rime | **Hosting:** SLNG | **Languages:** Arabic, English, French, German, Spanish

    150+ voices across 5 languages. Uses unversioned identifiers (`arcana:` instead of `arcana:3-`).

    | Identifier            | Description |
    | --------------------- | ----------- |
    | `slng/rime/arcana:en` | English     |
    | `slng/rime/arcana:es` | Spanish     |
    | `slng/rime/arcana:fr` | French      |
    | `slng/rime/arcana:de` | German      |
    | `slng/rime/arcana:ar` | Arabic      |

    Best for: broad language coverage, high-volume production.
  </Accordion>

  <Accordion title="Deepgram Aura 2" icon="waveform">
    **Provider:** Deepgram | **Hosting:** SLNG + Deepgram | **Languages:** English, Spanish

    Available both SLNG-hosted (low latency) and proxied to Deepgram (more languages). The `model` field is required to pick a voice; there is no default.

    | Identifier                | Description                       |
    | ------------------------- | --------------------------------- |
    | `slng/deepgram/aura:2-en` | SLNG-hosted (English)             |
    | `slng/deepgram/aura:2-es` | SLNG-hosted (Spanish)             |
    | `deepgram/aura:2`         | Proxied to Deepgram (7 languages) |

    Best for: low-latency voice apps, multilingual IVR.
  </Accordion>

  <Accordion title="Cartesia Sonic 3" icon="waveform">
    **Provider:** Cartesia | **Hosting:** Cartesia | **Languages:** 40+

    Streaming TTS with controls for speed, volume, and emotion.

    | Identifier         | Description         |
    | ------------------ | ------------------- |
    | `cartesia/sonic:3` | Proxied to Cartesia |

    Best for: real-time voice agents, expressive multilingual output.
  </Accordion>

  <Accordion title="Murf Falcon" icon="waveform">
    **Provider:** Murf | **Hosting:** Murf | **Languages:** 16 locales

    Real-time multilingual TTS over WebSocket with multiple encodings and sample rates.

    | Identifier            | Description     |
    | --------------------- | --------------- |
    | `murf/murftts:falcon` | Proxied to Murf |

    Best for: low-cost voice agents, IVR, assistants.
  </Accordion>

  <Accordion title="KugelAudio Kugel" icon="waveform">
    **Provider:** KugelAudio | **Hosting:** KugelAudio | **Languages:** 26

    87 voices with expressiveness control across 26 languages. Three variants trade off latency and quality.

    | Identifier                 | Description                    |
    | -------------------------- | ------------------------------ |
    | `kugelaudio/kugel:1-turbo` | Lowest latency                 |
    | `kugelaudio/kugel:1`       | Higher quality, higher latency |
    | `kugelaudio/kugel:2`       | Latest version, EU region      |

    Best for: multilingual voice agents, content creation.
  </Accordion>

  <Accordion title="Soniox TTS v1" icon="waveform">
    **Provider:** Soniox | **Hosting:** Soniox | **Languages:** 50+

    Streaming and one-shot synthesis across 50+ languages.

    | Identifier         | Description       |
    | ------------------ | ----------------- |
    | `soniox/tts-rt:v1` | Proxied to Soniox |

    Best for: multilingual streaming, long-form synthesis.
  </Accordion>

  <Accordion title="Sarvam Bulbul v3" icon="waveform">
    **Provider:** Sarvam AI | **Hosting:** Sarvam AI | **Languages:** 11 Indian languages

    Purpose-built for Indian languages with 30+ speaker voices.

    | Identifier         | Description          |
    | ------------------ | -------------------- |
    | `sarvam/bulbul:v3` | Proxied to Sarvam AI |

    Best for: India-focused voice apps, regional language support.
  </Accordion>
</AccordionGroup>

## Speech-to-Text

<AccordionGroup>
  <Accordion title="Deepgram Nova 3" icon="microphone">
    **Provider:** Deepgram | **Hosting:** SLNG + Deepgram | **Languages:** English, Spanish, Hindi

    Available both SLNG-hosted and proxied.

    | Identifier                   | Description                           |
    | ---------------------------- | ------------------------------------- |
    | `slng/deepgram/nova:3-en`    | SLNG-hosted (English)                 |
    | `slng/deepgram/nova:3-es`    | SLNG-hosted (Spanish)                 |
    | `slng/deepgram/nova:3-hi`    | SLNG-hosted (Hindi)                   |
    | `slng/deepgram/nova:3-multi` | SLNG-hosted (auto-detect)             |
    | `deepgram/nova:3`            | Proxied to Deepgram (17 languages)    |
    | `deepgram/nova:3-medical`    | Proxied to Deepgram (medical English) |

    Best for: low-latency streaming, voice agents.
  </Accordion>

  <Accordion title="Deepgram Nova 2" icon="microphone">
    **Provider:** Deepgram | **Hosting:** Deepgram | **Languages:** 36

    Proven model with VAD, diarization, and smart formatting.

    | Identifier        | Description         |
    | ----------------- | ------------------- |
    | `deepgram/nova:2` | Proxied to Deepgram |

    Best for: production transcription, multi-speaker audio.
  </Accordion>

  <Accordion title="Soniox Speech AI v4" icon="microphone">
    **Provider:** Soniox | **Hosting:** Soniox | **Languages:** 60+

    Real-time STT with speaker diarization, automatic language identification, and configurable endpoint detection. Returns native Soniox token frames.

    | Identifier               | Description       |
    | ------------------------ | ----------------- |
    | `soniox/speech-ai:rt-v4` | Proxied to Soniox |

    Best for: multilingual streaming, multi-speaker conversations.
  </Accordion>

  <Accordion title="Reson8 STT v1" icon="microphone">
    **Provider:** Reson8 | **Hosting:** Reson8 | **Languages:** 9 European

    Real-time STT with word-level timestamps, confidence scores, and partial results. Dutch, English, French, German, Italian, Polish, Portuguese, Spanish, Swedish.

    | Identifier            | Description       |
    | --------------------- | ----------------- |
    | `reson8/reson8stt:v1` | Proxied to Reson8 |

    Best for: European-language voice agents, low-latency transcription.
  </Accordion>

  <Accordion title="Sarvam Saaras v3" icon="microphone">
    **Provider:** Sarvam AI | **Hosting:** Sarvam AI | **Languages:** 24

    Speech recognition for 24 Indian and European languages with code-mixing support. HTTP-only; not available over WebSocket.

    | Identifier         | Description          |
    | ------------------ | -------------------- |
    | `sarvam/saaras:v3` | Proxied to Sarvam AI |

    Best for: India-focused batch transcription, code-switched audio.
  </Accordion>
</AccordionGroup>

## Choosing a model

| Use case                   | Recommended STT           | Recommended TTS         |
| -------------------------- | ------------------------- | ----------------------- |
| Voice agents (low latency) | `slng/deepgram/nova:3-en` | `slng/rime/arcana:3-en` |
| Multilingual transcription | `deepgram/nova:3`         | `cartesia/sonic:3`      |
| Indian languages           | `slng/deepgram/nova:3-hi` | `sarvam/bulbul:v3`      |
| Batch transcription        | `deepgram/nova:3`         | —                       |
| Medical transcription      | `deepgram/nova:3-medical` | —                       |

For voices, regions, and detailed model specs, see the [Model Catalog](/models).


# Parameters coverage
Source: https://docs.slng.ai/execution-layer/unified-api-parameters

Compatibility matrix for the SLNG Unified API. Which TTS and STT request parameters are supported by Deepgram, ElevenLabs, Cartesia, Sarvam, and Rime.

The SLNG Unified API accepts a common set of parameters across all providers. Some parameters are universal, others depend on the model. Provider-specific values (like voice identifiers or language codes) are passed through the same fields. The platform forwards them to the underlying provider.

## TTS parameters

| Parameter            | Type    | Required | Description                                                        |
| -------------------- | ------- | -------- | ------------------------------------------------------------------ |
| `text`               | string  | Yes      | Text to synthesize                                                 |
| `voice`              | string  | No       | Voice identifier. Accepted values depend on the provider and model |
| `config.sample_rate` | integer | No       | Output sample rate in Hz                                           |
| `config.encoding`    | string  | No       | Output encoding format                                             |
| `config.language`    | string  | No       | Language code. Accepted values depend on the provider              |
| `config.speed`       | number  | No       | Speech speed multiplier                                            |

### TTS provider support

The matrix below covers the most commonly used SLNG-hosted models. Providers not listed here (Cartesia Sonic 3, Murf Falcon, Kugel, Soniox TTS v1) accept the same `text` and `voice` fields. Check each model's [API reference](/api-reference) for the exact list of supported `config.*` fields.

| Parameter            | Rime Arcana | Deepgram Aura 2 | Sarvam Bulbul |
| -------------------- | ----------- | --------------- | ------------- |
| `voice`              | Yes         | Yes             | Yes           |
| `config.sample_rate` | Yes         | Yes             | Yes           |
| `config.encoding`    | Yes         | Yes             | Yes           |
| `config.language`    | Yes         | Yes             | Yes           |
| `config.speed`       | —           | Yes             | —             |

### Provider-specific values

The `voice` and `config.language` fields accept provider-specific values. For example:

* **Rime Arcana** voices: `luna`, `orion`, `astra`, `nova`
* **Deepgram Aura 2** voices: `aura-2-thalia-en`, `aura-2-asteria-en`, `aura-2-celeste-es` (set the `voice` field explicitly)
* **Rime Arcana** language codes: `en`, `fr`, `es`, `hi`, `ar`, `de`
* **Cartesia Sonic 3**, **Murf Falcon**, **Kugel**, **Soniox TTS v1**: see the [voice catalog](/voices) for each provider's `voice_id` values

The platform passes these values directly to the provider. If you send a voice identifier that the selected model does not support, the provider returns an error through the standard error response format.

### Supported sample rates and encodings

Sample-rate and encoding support varies by model and protocol. The Unified API uses a common request shape, but the selected model still controls which audio formats are valid.

| Model or endpoint family     | Common sample rates                | Encoding support                           | Notes                                                                                 |
| ---------------------------- | ---------------------------------- | ------------------------------------------ | ------------------------------------------------------------------------------------- |
| Unified TTS bridge           | `8000`-`48000` Hz, model-dependent | `linear16`, `mp3`, `opus`, `mulaw`, `alaw` | Accepted by the bridge schema; the selected model may still reject unsupported values |
| Deepgram Aura 2, proxied     | See endpoint reference             | `linear16`, `mp3`, `opus`                  | Use the direct Aura 2 reference for provider-specific behavior                        |
| Deepgram Aura 2, SLNG-hosted | See endpoint reference             | `linear16`, `mulaw`, `alaw`                | Optimized for real-time and telephony-style output                                    |
| Sarvam Bulbul                | See endpoint reference             | `mp3`, `linear16`, `mulaw`, `alaw`, `opus` | Indian-language TTS provider                                                          |
| Cartesia Sonic 3             | See endpoint reference             | `linear16`, `mulaw`, `alaw`                | Streaming TTS over WebSocket                                                          |

For exact allowed values, use the model-specific API reference page as the source of truth.

## STT parameters

| Parameter         | Type    | Required | Description                                           |
| ----------------- | ------- | -------- | ----------------------------------------------------- |
| `audio`           | file    | Yes      | Audio file to transcribe                              |
| `language`        | string  | No       | Language code. Accepted values depend on the provider |
| `sample_rate`     | integer | No       | Audio sample rate in Hz                               |
| `encoding`        | string  | No       | Audio encoding format                                 |
| `enable_vad`      | boolean | No       | Enable voice activity detection                       |
| `enable_partials` | boolean | No       | Enable partial transcription results                  |

### STT provider support

| Parameter         | Deepgram Nova 3 | Deepgram Nova 2 | Soniox Speech AI v4 |
| ----------------- | --------------- | --------------- | ------------------- |
| `language`        | Yes             | Yes             | Auto-detect         |
| `sample_rate`     | Yes             | Yes             | Yes                 |
| `encoding`        | Yes             | Yes             | Yes                 |
| `enable_vad`      | Yes             | Yes             | Yes                 |
| `enable_partials` | Yes             | Yes             | Yes                 |

### Supported STT encodings

`linear16`, `mp3`, `opus`.

## How provider-specific parameters work

The Unified API uses a schema-driven approach. All parameters are defined in the request schema. There is no generic passthrough or arbitrary key-value mechanism. The `voice`, `language`, and `config` fields accept provider-specific values as strings, and the platform forwards them to the underlying provider without transformation.

This means:

* You use the same field names regardless of provider
* Provider-specific values (voice names, language codes) go into the same fields
* Validation happens at the provider level. If a value is not supported, you get a standard error response with the provider's error message

## Model identifiers

Models follow the pattern `provider/model:variant` for third-party and `slng/provider/model:variant` for SLNG-hosted. For example:

* `deepgram/aura:2`: third-party, proxied to Deepgram
* `slng/deepgram/aura:2-en`: SLNG-hosted Deepgram Aura 2 (English)
* `slng/rime/arcana:3-en`: SLNG-hosted Rime Arcana v3 (English)

For the full list of model identifiers, see [Supported models](/execution-layer/unified-api-models).


# Getting started with SLNG
Source: https://docs.slng.ai/getting-started

Authenticate, send your first text-to-speech and speech-to-text requests, and stream over WebSocket with SLNG in about five minutes.

All your speech traffic routes through one platform. The quickest way to see it work is to send a text-to-speech and a speech-to-text request directly. Once you have, you can [point your existing stack at the gateway](/integrations/gateway) and keep the rest of your code.

## Prerequisites

* An SLNG account
* A SLNG key (get one at [app.slng.ai](https://app.slng.ai/api-keys))
* Basic knowledge of REST APIs or WebSockets

## Authentication

Every request needs an SLNG key in the `Authorization: Bearer SLNG_API_KEY` header. Get one from the [Dashboard](https://app.slng.ai/api-keys), and replace `SLNG_API_KEY` in the examples below with your key. For WebSocket auth, key rotation, and bringing your own provider key, see [Authentication & API Keys](/authentication).

## Your First Request

<Steps>
  <Step title="Text-to-Speech (HTTP)">
    A Text-to-Speech (TTS) request over HTTP turns text into an audio file:

    ```bash theme={null}
    curl https://api.slng.ai/v1/tts/slng/deepgram/aura:2-en \
      -H "Authorization: Bearer SLNG_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "aura-2-thalia-en",
        "text": "Hello from sunny Barcelona!"
      }' \
      --output hello.wav
    ```

    Replace `SLNG_API_KEY` with your SLNG key and run the command. Once the request completes, you have a `hello.wav` file in the current directory.

    It sounds like this:

    <AudioPlayer title="Hello from sunny Barcelona!" />
  </Step>

  <Step title="Speech-to-Text (HTTP)">
    Next, transcribe an audio file. The response is text you can process downstream.

    Download this sample file:

    <AudioPlayer title="Micro Machines sample" description="Download this file to use with the STT example below." />

    Then run:

    ```bash theme={null}
    curl https://api.slng.ai/v1/stt/slng/deepgram/nova:3-en \
      -H "Authorization: Bearer SLNG_API_KEY" \
      -F "audio=@micro-machines.wav" \
      -F "language=en"
    ```

    Response:

    ```json theme={null}
    {
      "text": "is the micro machine man presenting the most midget miniature motorcade of micro machine...",
      "transcript": "is the micro machine man presenting the most midget miniature motorcade of micro machine...",
      "confidence": 0.9749991,
      "duration": 29.888374,
      "language": "en",
      "metadata": {
          "request_id": "f5778fa4-40f9-4d60-993b-2f43f0164221",
          "model": "nova-3",
          "duration": 29.888374,
          "channels": 1
      }
    }
    ```

    The same endpoint accepts a remote URL instead of an upload:

    ```bash theme={null}
    curl https://api.slng.ai/v1/stt/slng/deepgram/nova:3-multi \
      -H "Authorization: Bearer SLNG_API_KEY" \
      -H 'Content-Type: application/json' \
      --data '{"url":"https://docs.slng.ai/audio/micro-machines.wav", "language":"en"}'
    ```

    The response is identical to the upload version.
  </Step>
</Steps>

## Go Further

<CardGroup>
  <Card title="Point your stack at SLNG" icon="plug" href="/integrations/gateway">
    Route your existing voice agent through the gateway and keep your code.
  </Card>

  <Card title="Use a framework plugin" icon="boxes" href="/integrations/overview">
    Native integrations for LiveKit, Cognigy, and Jambonz.
  </Card>

  <Card title="Explore the execution layer" icon="layers" href="/execution-layer">
    How SLNG routes and optimizes every turn between your app and the models.
  </Card>

  <Card title="Build a voice agent" icon="bot" href="/voice-agents">
    Combine streaming STT, low-latency TTS, and tool-calling to greet, route, and escalate calls.
  </Card>

  <Card title="HTTP vs. WebSocket" icon="arrow-left-right" href="/protocols">
    Understand when to use each protocol and their trade-offs.
  </Card>

  <Card title="Browse models" icon="cpu" href="/models">
    Explore all available TTS and STT models and find the right one for your use case.
  </Card>
</CardGroup>


# SLNG: the execution layer for voice
Source: https://docs.slng.ai/index

Text-to-speech, speech-to-text, and voice agents through one API. Your orchestrator stays, your models stay. Every turn is routed and optimized for lower cost and lower latency.

<div>
  <section>
    <div>
      <span>● Unmuted</span>

      <h1>
        The global execution layer for <span>real-time voice</span>
      </h1>

      <p>
        Keep your models. Keep your orchestrator. The execution layer sits between them and cuts cost and latency on every turn.
      </p>

      <div>
        <a href="/sdks/skills">Install the skills</a>
        <a href="/getting-started">Read the quickstart →</a>
      </div>

      <div><span>\$</span> npx skills add slng-ai/skills</div>
      <p>Teach your coding agent to build with SLNG, or send your first request by hand.</p>
    </div>
  </section>

  <section>
    <div>
      <div>
        <div>
          <div>39<small>%</small></div>
          <div>less turn latency, end to end</div>
        </div>

        <div>
          <div>53<small>%</small></div>
          <div>less model cost</div>
        </div>

        <div>
          <div>+16<small>%</small></div>
          <div>better call outcomes</div>
        </div>

        <div>
          <div>30<small>+</small></div>
          <div>models behind one API</div>
        </div>
      </div>
    </div>
  </section>

  <section>
    <div>
      <div>
        <div>
          <div>Drop-in</div>
          <h2>Plug in the endpoints. Nothing else changes</h2>

          <p>
            Your orchestrator, your prompts, and your tools stay exactly as they are. Repoint your speech calls at SLNG, and routing, caching, and failover happen behind the endpoint.
          </p>

          <div>
            <a href="/integrations/gateway">How integration works →</a>
          </div>
        </div>

        <div>
          <span># keep your orchestrator and prompts. repoint two calls.</span>
          <span>- stt: [https://your-current-provider/…](https://your-current-provider/…)</span>
          <span>+ stt: [https://api.slng.ai/v1/stt/](https://api.slng.ai/v1/stt/)<span><span><span>slng/deepgram/nova:3-en</span><span>slng/deepgram/nova:3-multi</span><span>soniox/soniox:latest</span><span>slng/deepgram/nova:3-en</span></span></span></span>
          <span>- tts: [https://your-current-provider/…](https://your-current-provider/…)</span>
          <span>+ tts: [https://api.slng.ai/v1/tts/](https://api.slng.ai/v1/tts/)<span><span><span>slng/deepgram/aura:2-en</span><span>slng/rime/arcana:3-en</span><span>slng/rime/arcana:3-es</span><span>slng/deepgram/aura:2-en</span></span></span></span>
        </div>
      </div>
    </div>
  </section>

  <section>
    <div>
      <div>What runs on it</div>
      <h2>Three primitives for real-time speech</h2>

      <div>
        <a href="/tts/overview">
          <span>
            <Icon icon="audio-lines" />
          </span>

          <h3>Text-to-Speech</h3>
          <p>Text in, audio out. Multiple voices and languages, over HTTP or streaming WebSocket.</p>
        </a>

        <a href="/stt/overview">
          <span>
            <Icon icon="ear" />
          </span>

          <h3>Speech-to-Text</h3>
          <p>Transcribe audio files or live streams. Single-language or auto-detect across 10+ languages.</p>
        </a>

        <a href="/voice-agents">
          <span>
            <Icon icon="bot" />
          </span>

          <h3>Voice Agents</h3>
          <p>An LLM paired with STT and TTS that takes and makes phone calls or runs in the browser.</p>
        </a>
      </div>
    </div>
  </section>

  <section>
    <div>
      <div>How it works</div>
      <h2>Every turn takes the path it actually needs</h2>

      <p>
        A 16-turn call makes 48 model calls. By default each one runs from scratch, even for a greeting you have synthesized a thousand times. The execution layer changes that across three stages.
      </p>

      <div>
        <a href="/execution-layer/stt-routing">
          <div>STAGE 01</div>
          <h3>STT routing</h3>
          <p>Route input to the right transcription model, based on language, accent, noise, and cost.</p>
        </a>

        <a href="/execution-layer/tiered-decisioning">
          <div>STAGE 02</div>
          <h3>Tiered decisioning</h3>
          <p>Decide whether a turn needs full LLM reasoning, local inference, or no inference at all.</p>
        </a>

        <a href="/execution-layer/output-assembly">
          <div>STAGE 03</div>
          <h3>Output assembly</h3>
          <p>Assemble TTS output from cache and synthesis. Don't generate what already exists.</p>
        </a>
      </div>
    </div>
  </section>

  <section>
    <div>
      <div>
        <a href="/region-override">
          <span>
            <Icon icon="globe" />
          </span>

          <h3>Select your region per request</h3>
          <p>Pin execution to any of 11 sovereign hubs with a single <code>X-Region</code> header. Data stays in-jurisdiction.</p>
        </a>

        <a href="/execution-layer/adaptive">
          <span>
            <Icon icon="trending-up" />
          </span>

          <h3>Gets faster with every call</h3>
          <p>Each call improves routing decisions and cache coverage for the next. Cost and latency fall as usage grows.</p>
        </a>
      </div>
    </div>
  </section>

  <section>
    <div>
      <div>Integrations</div>
      <h2>Drops into your orchestrator</h2>

      <p>
        Run SLNG inside the agent framework you already use. Same endpoints, native adapters.
      </p>

      <div>
        <a href="/agents/livekit-plugin">
          <span>
            <img alt="LiveKit" />
          </span>

          <h3>LiveKit</h3>
          <p>Use SLNG models inside LiveKit Agents with the <code>livekit-plugins-slng</code> adapter.</p>
        </a>

        <a href="/agents/pipecat-plugin">
          <span>
            <img alt="Pipecat" />
          </span>

          <h3>Pipecat</h3>
          <p>Use SLNG STT and TTS in a Pipecat pipeline with the <code>pipecat-slng</code> plugin.</p>
        </a>
      </div>

      <div>
        <a href="/integrations/overview">See all integrations →</a>
      </div>
    </div>
  </section>

  <section>
    <div>
      <div>Bring your own keys</div>
      <h2>Works with the models you already use</h2>

      <p>
        Bring your own provider keys and route across 30+ speech models over standard HTTP and WebSocket, without changing your integration.
      </p>

      <div>
        <a href="/api-reference/tts/deepgram-aura-2/aura-2-english-ws">
          <img alt="Deepgram" />
        </a>

        <a href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws">
          <img alt="Cartesia" />
        </a>

        <a href="/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws">
          <img alt="Rime" />
        </a>

        <a href="/api-reference/tts/murf-falcon/murf-falcon-ws">
          <img alt="Murf" />
        </a>

        <a href="/api-reference/tts/sarvam-ai-bulbul-v3/bulbul-v3-ws">
          <img alt="Sarvam" />
        </a>

        <a href="/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws">
          <img alt="Soniox" />
        </a>
      </div>

      <p>ISO 27001 certified. HIPAA and GDPR compliant. <a href="https://trust.slng.ai">trust.slng.ai</a></p>
    </div>
  </section>

  <section>
    <div>
      <div>
        <div>
          <a href="/sdks/skills">Install the skills</a>
          <a href="/getting-started">Read the quickstart</a>
          <a href="/execution-layer">Execution layer</a>
        </div>
      </div>
    </div>
  </section>
</div>


# Drop-in gateway
Source: https://docs.slng.ai/integrations/gateway

Point your existing voice stack at the SLNG platform and keep your code. Route speech-to-text and text-to-speech through one base URL to add caching, regional routing, and provider flexibility.

The fastest way to add SLNG to an existing voice agent is to route your speech traffic through the platform. You keep your application code, your agent logic, and your call flow. You change where the speech requests go.

## How it works

The SLNG platform exposes one consistent base URL for every model. The path selects the service, provider, and model:

```
https://api.slng.ai/v1/{tts|stt}/{provider}/{model}
```

Send your text-to-speech and speech-to-text requests there with your SLNG key, and you get caching, [regional routing](/region-override), and access to every supported provider behind a single integration.

<Steps>
  <Step title="Get an SLNG key">
    Create one at [app.slng.ai/api-keys](https://app.slng.ai/api-keys).
  </Step>

  <Step title="Point your requests at the gateway">
    Replace your provider's endpoint with the SLNG platform URL and send your SLNG key in the `Authorization` header.

    ```bash Text-to-speech theme={null}
    curl https://api.slng.ai/v1/tts/slng/deepgram/aura:2-en \
      -H "Authorization: Bearer SLNG_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{ "model": "aura-2-thalia-en", "text": "Hello from SLNG!" }' \
      --output hello.wav
    ```

    ```bash Speech-to-text theme={null}
    curl https://api.slng.ai/v1/stt/slng/deepgram/nova:3-en \
      -H "Authorization: Bearer SLNG_API_KEY" \
      -F "audio=@call.wav" \
      -F "language=en"
    ```
  </Step>

  <Step title="Keep your own provider key (optional)">
    Already have a provider contract? Add the `X-Slng-Provider-Key` header. Billing
    runs against your provider account, and output assembly still applies.

    BYOK applies to proxied providers, so use a provider path (not a `slng/`-hosted one). For example, Soniox:

    ```bash highlight={3} theme={null}
    curl https://api.slng.ai/v1/tts/soniox/tts-rt:v1 \
      -H "Authorization: Bearer SLNG_API_KEY" \
      -H "X-Slng-Provider-Key: YOUR_PROVIDER_KEY" \
      -H "Content-Type: application/json" \
      -d '{ "text": "I brought my own key to the party.", "voice": "Adrian", "audio_format": "wav", "sample_rate": 24000 }' \
      --output hello.wav
    ```

    See [Bring your own key](/execution-layer/byok) for supported providers, WebSocket setup, and billing.
  </Step>
</Steps>

## What you get

<CardGroup>
  <Card title="Output assembly" icon="database" href="/execution-layer/output-assembly">
    Repeated text-to-speech served from cache.
  </Card>

  <Card title="Regional execution" icon="globe-lock" href="/region-override">
    Pin traffic to a region with one header.
  </Card>

  <Card title="How it works" icon="layers" href="/execution-layer/how-it-works">
    The execution path every turn takes between your app and the models.
  </Card>

  <Card title="Unified API" icon="blend" href="/execution-layer/unified-api">
    Switch providers by changing the path.
  </Card>
</CardGroup>

## Prefer a framework plugin?

If your agent runs on LiveKit, Cognigy, or Jambonz, use the native integration instead of calling the platform directly. See [Voice platform integrations](/integrations/overview).


# Voice platform integrations
Source: https://docs.slng.ai/integrations/overview

Use SLNG STT and TTS through LiveKit Agents, Cognigy Voice Gateway, and Jambonz with no protocol rewrites. Region overrides included.

Already building on a voice framework? Use SLNG's STT and TTS models through it with a native plugin instead of calling the gateway directly. Each integration translates the platform's native protocol into SLNG calls, so you add caching, regional routing, and provider flexibility without rewriting your agent.

If you run a custom stack instead of a framework, point your requests at the [drop-in gateway](/integrations/gateway).

## Region and world-part overrides

All integrations route through the SLNG platform, which supports the `X-Region-Override` and `X-World-Part-Override` headers to pin requests to a specific region (for data residency) or to a broader geographic zone like `eu` or `na`.

The [Cognigy](/api-reference/bridges/cognigy-stt-bridge/cognigy-stt-bridge-ws) and [Jambonz](/api-reference/bridges/jambonz-stt-bridge/jambonz-stt-bridge-ws) bridges also accept `?region=` and `?world-part=` query parameters. Use these when the platform does not let you set custom HTTP headers. If you send both, the header wins.

The [LiveKit plugin](/agents/livekit-plugin#region-override) wraps this in a `region_override` parameter on the `STT` and `TTS` classes, so you set it once when you instantiate the model. The [Pipecat plugin](/agents/pipecat-plugin#region-routing) exposes the same routing through `region_override` and `world_part_override` on its STT and TTS services.

See [Region and world-part overrides](/region-override) for the full region list and header behavior.

## Available integrations

<CardGroup>
  <Card title="LiveKit" icon="https://mintcdn.com/slng/LujG4G8gXFrAV3XP/images/providers/livekit.svg?fit=max&auto=format&n=LujG4G8gXFrAV3XP&q=85&s=5ae1614bbad360d24b36276e04bbc0ea" href="/agents/livekit-plugin">
    Use SLNG models inside LiveKit Agents with the livekit-plugins-slng adapter.
  </Card>

  <Card title="Pipecat" icon="https://mintcdn.com/slng/HUXme6ATYhzzt7mD/images/providers/pipecat.svg?fit=max&auto=format&n=HUXme6ATYhzzt7mD&q=85&s=f0ff456ad8aa57cfedc6291d915bd330" href="/agents/pipecat-plugin">
    Use SLNG models inside Pipecat pipelines with the pipecat-slng STT/TTS services.
  </Card>

  <Card title="Cognigy" icon="https://mintcdn.com/slng/HUXme6ATYhzzt7mD/images/providers/cognigy.svg?fit=max&auto=format&n=HUXme6ATYhzzt7mD&q=85&s=a596bbf3873fefc5f3f85ff6f7f85452" href="/api-reference/bridges/cognigy-stt-bridge/cognigy-stt-bridge-ws">
    Connect Cognigy voice bots to SLNG STT and TTS models.
  </Card>

  <Card title="Jambonz" icon="https://mintcdn.com/slng/LujG4G8gXFrAV3XP/images/providers/jambonz.svg?fit=max&auto=format&n=LujG4G8gXFrAV3XP&q=85&s=4c6b373a760758c8e45c53674c5514ed" href="/api-reference/bridges/jambonz-stt-bridge/jambonz-stt-bridge-ws">
    Route Jambonz calls through SLNG for speech processing.
  </Card>
</CardGroup>


# Models by Language
Source: https://docs.slng.ai/models/by-language

Browse SLNG TTS and STT models grouped by supported language: English, Spanish, French, German, Hindi, Japanese, Mandarin, and 30+ Indian languages.

<Note>
  Many models support multiple languages. A model listed under one language may also appear under others. See individual model pages for the full list of supported languages and voices.
</Note>

## Arabic

<CardGroup>
  <ModelCard name="Rime Arcana v1" type="tts" href="/api-reference/tts/rime-arcana-v2/arcana-v2-english-ws" />

  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Bengali

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Bulgarian

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Chinese

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Nova 2" type="stt" href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

  <ModelCard name="Speech AI RT v4" type="stt" href="/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Czech

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Nova 2" type="stt" href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Danish

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Dutch

<CardGroup>
  <ModelCard name="Aura 2" type="tts" href="/api-reference/tts/deepgram-aura-2/aura-2-ws" />

  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Nova 2" type="stt" href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

  <ModelCard name="Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-ws" />

  <ModelCard name="Reson8 STT v1" type="stt" href="/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## English

<CardGroup>
  <ModelCard name="Rime Arcana v3" type="tts" href="/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws" />

  <ModelCard name="Rime Arcana v1" type="tts" href="/api-reference/tts/rime-arcana-v2/arcana-v2-english-ws" />

  <ModelCard name="Deepgram Aura 2" type="tts" href="/api-reference/tts/deepgram-aura-2/aura-2-english-ws" />

  <ModelCard name="Aura 2" type="tts" href="/api-reference/tts/deepgram-aura-2/aura-2-ws" />

  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Deepgram Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-multi-language-ws" />

  <ModelCard name="Nova 2" type="stt" href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

  <ModelCard name="Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-ws" />

  <ModelCard name="Nova 3 Medical" type="stt" href="/api-reference/stt/deepgram-nova-3-medical/nova-3-medical-ws" />

  <ModelCard name="Speech AI RT v4" type="stt" href="/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws" />

  <ModelCard name="Sarvam AI Saaras" type="stt" href="/api-reference/stt/sarvam-ai-saaras/saaras-v3-http" />

  <ModelCard name="Murf Falcon" type="tts" href="/api-reference/tts/murf-falcon/murf-falcon-ws" />

  <ModelCard name="Reson8 STT v1" type="stt" href="/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Soniox TTS RT v1" type="tts" href="/api-reference/tts/soniox-tts-v1/soniox-tts-v1-ws" />

  <ModelCard name="Gradium STT" type="stt" href="/api-reference/stt/gradium-stt/gradium-stt-ws" />

  <ModelCard name="Gradium TTS" type="tts" href="/api-reference/tts/gradium-tts/gradium-tts-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Finnish

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## French

<CardGroup>
  <ModelCard name="Rime Arcana v3" type="tts" href="/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws" />

  <ModelCard name="Rime Arcana v1" type="tts" href="/api-reference/tts/rime-arcana-v2/arcana-v2-english-ws" />

  <ModelCard name="Aura 2" type="tts" href="/api-reference/tts/deepgram-aura-2/aura-2-ws" />

  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Nova 2" type="stt" href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

  <ModelCard name="Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-ws" />

  <ModelCard name="Reson8 STT v1" type="stt" href="/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Gradium STT" type="stt" href="/api-reference/stt/gradium-stt/gradium-stt-ws" />

  <ModelCard name="Gradium TTS" type="tts" href="/api-reference/tts/gradium-tts/gradium-tts-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Georgian

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## German

<CardGroup>
  <ModelCard name="Rime Arcana v1" type="tts" href="/api-reference/tts/rime-arcana-v2/arcana-v2-english-ws" />

  <ModelCard name="Aura 2" type="tts" href="/api-reference/tts/deepgram-aura-2/aura-2-ws" />

  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Nova 2" type="stt" href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

  <ModelCard name="Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-ws" />

  <ModelCard name="Speech AI RT v4" type="stt" href="/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws" />

  <ModelCard name="Reson8 STT v1" type="stt" href="/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Gradium STT" type="stt" href="/api-reference/stt/gradium-stt/gradium-stt-ws" />

  <ModelCard name="Gradium TTS" type="tts" href="/api-reference/tts/gradium-tts/gradium-tts-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Greek

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Gujarati

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Hebrew

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Hindi

<CardGroup>
  <ModelCard name="Rime Arcana v3" type="tts" href="/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws" />

  <ModelCard name="Bulbul v3" type="tts" href="/api-reference/tts/sarvam-ai-bulbul-v3/bulbul-v3-ws" />

  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Deepgram Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-multi-language-ws" />

  <ModelCard name="Speech AI RT v4" type="stt" href="/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws" />

  <ModelCard name="Sarvam AI Saaras" type="stt" href="/api-reference/stt/sarvam-ai-saaras/saaras-v3-http" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Hungarian

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Indonesian

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Italian

<CardGroup>
  <ModelCard name="Aura 2" type="tts" href="/api-reference/tts/deepgram-aura-2/aura-2-ws" />

  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Nova 2" type="stt" href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

  <ModelCard name="Speech AI RT v4" type="stt" href="/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws" />

  <ModelCard name="Reson8 STT v1" type="stt" href="/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Japanese

<CardGroup>
  <ModelCard name="Aura 2" type="tts" href="/api-reference/tts/deepgram-aura-2/aura-2-ws" />

  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Nova 2" type="stt" href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

  <ModelCard name="Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-ws" />

  <ModelCard name="Speech AI RT v4" type="stt" href="/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Kannada

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Korean

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Nova 2" type="stt" href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

  <ModelCard name="Speech AI RT v4" type="stt" href="/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Malay

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Malayalam

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Marathi

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Norwegian

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Polish

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Reson8 STT v1" type="stt" href="/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Portuguese

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Nova 2" type="stt" href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

  <ModelCard name="Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-ws" />

  <ModelCard name="Speech AI RT v4" type="stt" href="/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws" />

  <ModelCard name="Reson8 STT v1" type="stt" href="/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Gradium STT" type="stt" href="/api-reference/stt/gradium-stt/gradium-stt-ws" />

  <ModelCard name="Gradium TTS" type="tts" href="/api-reference/tts/gradium-tts/gradium-tts-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Punjabi

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Romanian

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Russian

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Slovak

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Slovenian

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Spanish

<CardGroup>
  <ModelCard name="Rime Arcana v3" type="tts" href="/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws" />

  <ModelCard name="Rime Arcana v1" type="tts" href="/api-reference/tts/rime-arcana-v2/arcana-v2-english-ws" />

  <ModelCard name="Deepgram Aura 2" type="tts" href="/api-reference/tts/deepgram-aura-2/aura-2-english-ws" />

  <ModelCard name="Aura 2" type="tts" href="/api-reference/tts/deepgram-aura-2/aura-2-ws" />

  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Deepgram Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-multi-language-ws" />

  <ModelCard name="Nova 2" type="stt" href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

  <ModelCard name="Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-ws" />

  <ModelCard name="Speech AI RT v4" type="stt" href="/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws" />

  <ModelCard name="Murf Falcon" type="tts" href="/api-reference/tts/murf-falcon/murf-falcon-ws" />

  <ModelCard name="Reson8 STT v1" type="stt" href="/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Gradium STT" type="stt" href="/api-reference/stt/gradium-stt/gradium-stt-ws" />

  <ModelCard name="Gradium TTS" type="tts" href="/api-reference/tts/gradium-tts/gradium-tts-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Swedish

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Reson8 STT v1" type="stt" href="/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Tagalog

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Tamil

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Telugu

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Thai

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Turkish

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Ukrainian

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Vietnamese

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Indian Languages

Models with dedicated support for Indian languages beyond Hindi, including Bengali, Gujarati, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, and Telugu.

<CardGroup>
  <ModelCard name="Bulbul v3" type="tts" href="/api-reference/tts/sarvam-ai-bulbul-v3/bulbul-v3-ws" />

  <ModelCard name="Sarvam AI Saaras" type="stt" href="/api-reference/stt/sarvam-ai-saaras/saaras-v3-http" />
</CardGroup>


# Models by Region
Source: https://docs.slng.ai/models/by-region

See which SLNG TTS and STT models are deployed in each AWS region across North America, Europe, and Asia-Pacific for low-latency routing.

<Note>
  Models may be available in multiple regions. SLNG auto-selects the closest region by default. Use the `X-Region-Override` header to pin a specific region, or `X-World-Part-Override` to pin a broader geographic zone (`na`, `eu`, `ap`). See [Region & World-Part Overrides](/region-override) for details.
</Note>

<Tabs>
  <Tab title="North America" />

  <Tab title="Europe">
    ### Available across Europe

    <CardGroup>
      <ModelCard name="Aura 2" type="tts" href="/api-reference/tts/deepgram-aura-2/aura-2-ws" />

      <ModelCard name="Kugel 1 Turbo" type="tts" href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

      <ModelCard name="Kugel 1" type="tts" href="/api-reference/tts/kugel-1/kugel-1-ws" />

      <ModelCard name="Kugel 2" type="tts" href="/api-reference/tts/kugel-2/kugel-2-ws" />

      <ModelCard name="Nova 2" type="stt" href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

      <ModelCard name="Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-ws" />

      <ModelCard name="Nova 3 Medical" type="stt" href="/api-reference/stt/deepgram-nova-3-medical/nova-3-medical-ws" />

      <ModelCard name="Speech AI RT v4" type="stt" href="/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws" />

      <ModelCard name="Murf Falcon" type="tts" href="/api-reference/tts/murf-falcon/murf-falcon-ws" />

      <ModelCard name="Reson8 STT v1" type="stt" href="/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws" />

      <ModelCard name="Cartesia Sonic 3" type="tts" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />

      <ModelCard name="Soniox TTS RT v1" type="tts" href="/api-reference/tts/soniox-tts-v1/soniox-tts-v1-ws" />

      <ModelCard name="Gradium STT" type="stt" href="/api-reference/stt/gradium-stt/gradium-stt-ws" />

      <ModelCard name="Gradium TTS" type="tts" href="/api-reference/tts/gradium-tts/gradium-tts-ws" />

      <ModelCard name="Kugel 2 Turbo" type="tts" href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
    </CardGroup>

    ### EU North (eu-north-1)

    <CardGroup>
      <ModelCard name="Rime Arcana v3" type="tts" href="/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws" />

      <ModelCard name="Deepgram Aura 2" type="tts" href="/api-reference/tts/deepgram-aura-2/aura-2-english-ws" />

      <ModelCard name="Deepgram Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-multi-language-ws" />
    </CardGroup>
  </Tab>

  <Tab title="Asia-Pacific">
    ### AP South (ap-south-1)

    <CardGroup>
      <ModelCard name="Deepgram Nova 3 (TAMIL)" type="stt" href="/models/stt" />
    </CardGroup>

    ### AP Southeast (ap-southeast-2)

    <CardGroup>
      <ModelCard name="Rime Arcana v3" type="tts" href="/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws" />

      <ModelCard name="Rime Arcana v1" type="tts" href="/api-reference/tts/rime-arcana-v2/arcana-v2-english-ws" />

      <ModelCard name="Rime Arcana v1" type="tts" href="/models/tts" />
    </CardGroup>

    ### AP South — GCP (asia-south1)

    <CardGroup>
      <ModelCard name="Rime Arcana v3" type="tts" href="/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws" />

      <ModelCard name="Deepgram Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-multi-language-ws" />

      <ModelCard name="Deepgram Nova 3 (HI)" type="stt" href="/models/stt" />

      <ModelCard name="Deepgram Nova 3 (KANNADA)" type="stt" href="/models/stt" />

      <ModelCard name="Deepgram Nova 3 (MARATHI)" type="stt" href="/models/stt" />

      <ModelCard name="Deepgram Nova 3 (TELUGU)" type="stt" href="/models/stt" />
    </CardGroup>

    ### Sydney (australia-southeast1)

    <CardGroup>
      <ModelCard name="Deepgram Nova 3" type="stt" href="/api-reference/stt/deepgram-nova-3/nova-3-multi-language-ws" />
    </CardGroup>
  </Tab>

  <Tab title="South America">
    We don't have models deployed in South America yet. [Contact us](mailto:support@slng.ai) if you'd like us to host models in this region.
  </Tab>

  <Tab title="Middle East & Africa">
    We don't have models deployed in the Middle East or Africa yet. [Contact us](mailto:support@slng.ai) if you'd like us to host models in this region.
  </Tab>
</Tabs>


# Model Catalog
Source: https://docs.slng.ai/models/index

Browse the full catalog of TTS and STT models on SLNG. Search by provider, language, or AWS deployment region for production voice agents.

SLNG gives you access to **14 TTS models** and **8 STT models** from **10 providers**, all through a single platform. Browse by type or find which models are deployed in your region.

## At a Glance

### Text-to-Speech

| Model                                                                       | Provider   | Hosting    | Latency | Languages           |
| --------------------------------------------------------------------------- | ---------- | ---------- | ------- | ------------------- |
| [Rime Arcana v3](/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws)    | Rime       | SLNG       | Low     | 4 languages         |
| [Rime Arcana v1](/api-reference/tts/rime-arcana-v2/arcana-v2-english-ws)    | Rime       | SLNG       | Low     | 5 languages         |
| [Deepgram Aura 2](/api-reference/tts/deepgram-aura-2/aura-2-english-ws)     | Deepgram   | SLNG       | Low     | 2 languages         |
| [Aura 2 (Proxy)](/api-reference/tts/deepgram-aura-2/aura-2-ws)              | Deepgram   | Deepgram   | Medium  | 7 languages         |
| [Bulbul v3](/api-reference/tts/sarvam-ai-bulbul-v3/bulbul-v3-ws)            | Sarvam AI  | Sarvam AI  | Medium  | 11 languages        |
| [Kugel 1 Turbo](/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws)          | KugelAudio | KugelAudio | Low     | 26 languages        |
| [Kugel 1](/api-reference/tts/kugel-1/kugel-1-ws)                            | KugelAudio | KugelAudio | Medium  | 26 languages        |
| [Kugel 2](/api-reference/tts/kugel-2/kugel-2-ws)                            | KugelAudio | KugelAudio | Medium  | 26 languages        |
| [Murf Falcon](/api-reference/tts/murf-falcon/murf-falcon-ws)                | Murf       | Murf       | Low     | English and Spanish |
| [Cartesia Sonic 3](/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws) | Cartesia   | Cartesia   | Low     | 40+ languages       |
| [Soniox TTS RT v1](/api-reference/tts/soniox-tts-v1/soniox-tts-v1-ws)       | Soniox     | Soniox     | Low     | English             |
| [Gradium TTS](/api-reference/tts/gradium-tts/gradium-tts-ws)                | Gradium    | Gradium    | Low     | 5 languages         |
| [Kugel 2 Turbo](/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws)          | KugelAudio | KugelAudio | Low     | 26 languages        |
| [Inworld Max 1.5](/api-reference/tts/inworld-max/inworld-max-ws)            | Inworld    | SLNG       | Low     | 15 languages        |

### Speech-to-Text

| Model                                                                                         | Provider  | Hosting   | Latency | Languages            |
| --------------------------------------------------------------------------------------------- | --------- | --------- | ------- | -------------------- |
| [Deepgram Nova 3](/api-reference/stt/deepgram-nova-3/nova-3-multi-language-ws)                | Deepgram  | SLNG      | Low     | 4 languages          |
| [Nova 2 (Proxy)](/api-reference/stt/deepgram-nova-2/nova-2-ws)                                | Deepgram  | Deepgram  | Low     | 36 languages         |
| [Nova 3 (Proxy)](/api-reference/stt/deepgram-nova-3/nova-3-ws)                                | Deepgram  | Deepgram  | Low     | 17 languages         |
| [Nova 3 Medical](/api-reference/stt/deepgram-nova-3-medical/nova-3-medical-ws)                | Deepgram  | Deepgram  | Low     | English              |
| [Speech AI RT v4](/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws) | Soniox    | Soniox    | Low     | 60+ languages        |
| [Sarvam AI Saaras](/api-reference/stt/sarvam-ai-saaras/saaras-v3-http)                        | Sarvam AI | Sarvam AI | Medium  | 24 languages         |
| [Reson8 STT v1](/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws)                            | Reson8    | Reson8    | Low     | 9 European languages |
| [Gradium STT](/api-reference/stt/gradium-stt/gradium-stt-ws)                                  | Gradium   | Gradium   | Low     | 5 languages          |

## Browse Models

<CardGroup>
  <Card title="Text-to-Speech" icon="audio-lines" href="/models/tts">
    14 models from 9 providers.
  </Card>

  <Card title="Speech-to-Text" icon="ear" href="/models/stt">
    8 models from 5 providers.
  </Card>

  <Card title="By Region" icon="globe" href="/models/by-region">
    See which models are deployed in your region.
  </Card>

  <Card title="By Language" icon="languages" href="/models/by-language">
    Find models that support your target language.
  </Card>
</CardGroup>


# Speech-to-Text Models
Source: https://docs.slng.ai/models/stt

Browse every STT model on SLNG: Deepgram Nova, Sarvam Saaras, Soniox Speech AI, and Reson8 transcription, grouped by provider.

## SLNG-hosted

Models hosted on SLNG infrastructure for optimized latency and throughput.

<CardGroup>
  <ModelCard name="Deepgram Nova 3" type="stt" description="Deepgram Nova 3 hosted on SLNG with dedicated language endpoints (EN, ES, HI) and a multi-language auto-detect endpoint." href="/api-reference/stt/deepgram-nova-3/nova-3-multi-language-ws" />
</CardGroup>

## Deepgram

Direct proxy to Deepgram's STT API.

<CardGroup>
  <ModelCard name="Nova 2" type="stt" description="Deepgram's proven Nova 2 model with VAD, diarization, and smart formatting." href="/api-reference/stt/deepgram-nova-2/nova-2-ws" />

  <ModelCard name="Nova 3" type="stt" description="Latest Deepgram model with improved accuracy across 17 languages. Includes punctuation and smart formatting." href="/api-reference/stt/deepgram-nova-3/nova-3-ws" />

  <ModelCard name="Nova 3 Medical" type="stt" description="Specialized for medical terminology and clinical conversations." href="/api-reference/stt/deepgram-nova-3-medical/nova-3-medical-ws" />
</CardGroup>

## Gradium

<CardGroup>
  <ModelCard name="Gradium STT" type="stt" description="Real-time multilingual speech-to-text over streaming WebSocket with partial results." href="/api-reference/stt/gradium-stt/gradium-stt-ws" />
</CardGroup>

## Reson8

<CardGroup>
  <ModelCard name="Reson8 STT v1" type="stt" description="Reson8 real-time STT over WebSocket with word-level timestamps, confidence scores, and partial results." href="/api-reference/stt/reson8-stt-v1/reson8-stt-v1-ws" />
</CardGroup>

## Sarvam AI

Indian-language specialist.

<CardGroup>
  <ModelCard name="Sarvam AI Saaras" type="stt" description="Speech recognition for 24 Indian and European languages with code-mixing support." href="/api-reference/stt/sarvam-ai-saaras/saaras-v3-http" />
</CardGroup>

## Soniox

60+ language streaming speech recognition.

<CardGroup>
  <ModelCard name="Speech AI RT v4" type="stt" description="60+ language streaming STT with word-level timestamps and low latency." href="/api-reference/stt/soniox-speech-ai-real-time-v4/speech-ai-real-time-v4-ws" />
</CardGroup>


# Text-to-Speech Models
Source: https://docs.slng.ai/models/tts

Browse every TTS model on SLNG: Cartesia, Deepgram Aura, ElevenLabs, KugelAudio, Murf, Rime Arcana, Sarvam, and Soniox voices.

## SLNG-hosted

Models hosted and optimized on SLNG infrastructure for the lowest latency.

<CardGroup>
  <ModelCard name="Rime Arcana v3" type="tts" description="Rime's latest model with natural prosody across 4 languages." href="/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws" />

  <ModelCard name="Rime Arcana v1" type="tts" description="150+ voices across 5 languages including Arabic." href="/api-reference/tts/rime-arcana-v2/arcana-v2-english-ws" />

  <ModelCard name="Deepgram Aura 2" type="tts" description="Deepgram Aura 2 hosted on SLNG with English and Spanish endpoints." href="/api-reference/tts/deepgram-aura-2/aura-2-english-ws" />

  <ModelCard name="Inworld Max 1.5" type="tts" description="SLNG-hosted Inworld TTS 1.5 Max for multilingual, expressive synthesis over HTTP and bidirectional streaming WebSocket." href="/api-reference/tts/inworld-max/inworld-max-ws" />
</CardGroup>

## Cartesia

<CardGroup>
  <ModelCard name="Cartesia Sonic 3" type="tts" description="Sonic 3 delivers high-quality, natural-sounding speech with fine-grained generation controls including speed, volume, and emotion" href="/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws" />
</CardGroup>

## Deepgram

Direct proxy to Deepgram's TTS API.

<CardGroup>
  <ModelCard name="Aura 2" type="tts" description="Deepgram's flagship TTS model via direct API proxy. 68 voices across 10 languages." href="/api-reference/tts/deepgram-aura-2/aura-2-ws" />
</CardGroup>

## Gradium

<CardGroup>
  <ModelCard name="Gradium TTS" type="tts" description="Real-time multilingual text-to-speech with streaming WebSocket and one-shot HTTP synthesis." href="/api-reference/tts/gradium-tts/gradium-tts-ws" />
</CardGroup>

## KugelAudio

Multilingual TTS with expressiveness control.

<CardGroup>
  <ModelCard name="Kugel 1 Turbo" type="tts" description="87 voices with expressiveness control across 26 languages." href="/api-reference/tts/kugel-1-turbo/kugel-1-turbo-ws" />

  <ModelCard name="Kugel 1" type="tts" description="87 voices with expressiveness control across 26 languages. Higher quality, higher latency than Turbo." href="/api-reference/tts/kugel-1/kugel-1-ws" />

  <ModelCard name="Kugel 2" type="tts" description="87 voices with expressiveness control across 26 languages. Higher quality, higher latency than Turbo." href="/api-reference/tts/kugel-2/kugel-2-ws" />

  <ModelCard name="Kugel 2 Turbo" type="tts" description="87 voices with expressiveness control across 26 languages. Faster, lower-latency variant of Kugel 2." href="/api-reference/tts/kugel-2-turbo/kugel-2-turbo-ws" />
</CardGroup>

## Murf

<CardGroup>
  <ModelCard name="Murf Falcon" type="tts" description="Murf Falcon real-time TTS over WebSocket." href="/api-reference/tts/murf-falcon/murf-falcon-ws" />
</CardGroup>

## Sarvam AI

Indian-language specialist.

<CardGroup>
  <ModelCard name="Bulbul v3" type="tts" description="Purpose-built for Indian languages with 30+ speaker voices." href="/api-reference/tts/sarvam-ai-bulbul-v3/bulbul-v3-ws" />
</CardGroup>

## Soniox

<CardGroup>
  <ModelCard name="Soniox TTS RT v1" type="tts" description="Real-time text-to-speech with streaming WebSocket and one-shot HTTP synthesis." href="/api-reference/tts/soniox-tts-v1/soniox-tts-v1-ws" />
</CardGroup>


# Pronunciation dictionaries
Source: https://docs.slng.ai/pronunciation-dictionaries

Create reusable pronunciation dictionaries and attach them to any SLNG TTS request so brand names, acronyms, and domain terms are spoken the way you expect.

Pronunciation dictionaries let you control how text is spoken before it reaches the selected TTS model. Create a dictionary once, then reference it from HTTP, WebSocket, or Unified TTS requests.

Use them when a voice needs to pronounce acronyms, product names, customer names, jargon, or multilingual terms consistently across TTS models.

## Placeholders

The snippets below use these placeholders. Replace them before running the code.

| Placeholder              | Replace with                                                                |
| ------------------------ | --------------------------------------------------------------------------- |
| `SLNG_API_KEY`           | An SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys)       |
| `support-pronunciations` | The dictionary `name` you create with `POST /v1/pronunciation/dictionaries` |
| `pd_01abc...`            | A dictionary `dictionary_id` returned at creation time                      |

<Note>
  Pronunciation dictionaries currently support rewrite mode. SLNG rewrites matching words or phrases before synthesis, and the rewritten text is what the selected model receives.
</Note>

## How it works

Each dictionary belongs to the organization resolved from your SLNG key. Requests from another organization cannot read or use it.

The basic flow is:

1. Create a dictionary with rewrite rules.
2. Reference that dictionary by `name` or `dictionary_id`.
3. Send a TTS request with a `pronunciation` object.

Only one active pronunciation dictionary can apply to a request or WebSocket turn.

## Create a dictionary

Create dictionaries with the [pronunciation dictionary API reference](/api-reference/tts/pronunciation-dictionaries/create-pronunciation-dictionary-http):

```bash theme={null}
curl -X POST https://api.slng.ai/v1/pronunciation/dictionaries \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "support-pronunciations",
    "metadata": {
      "language": "en-US",
      "use_case": "support voice agent"
    },
    "modes": {
      "rewrite": {
        "rules": [
          { "match": "SLNG", "replace": "slang" },
          { "match": "QubePay", "replace": "cube pay" },
          { "match": "ACH transfer", "replace": "ay see aitch transfer" },
          { "match": "ACH", "replace": "ay see aitch" }
        ]
      }
    }
  }'
```

A successful response includes the dictionary `id`, normalized name, metadata, modes, content hash, and creation timestamp:

```json theme={null}
{
  "id": "pd_01abc...",
  "org_id": "org_123",
  "name": "support-pronunciations",
  "normalized_name": "support-pronunciations",
  "metadata": {
    "language": "en-US",
    "use_case": "support voice agent"
  },
  "modes": {
    "rewrite": {
      "rules": [
        { "match": "SLNG", "replace": "slang" },
        { "match": "QubePay", "replace": "cube pay" },
        { "match": "ACH transfer", "replace": "ay see aitch transfer" },
        { "match": "ACH", "replace": "ay see aitch" }
      ]
    }
  },
  "content_hash": "sha256:...",
  "created_at": "2026-05-15T12:00:00.000Z"
}
```

Dictionary names must be unique within your organization. Names can contain letters, numbers, `.`, `_`, and `-`, and can be up to 128 characters.

## Hear the difference

Use the same text with and without the dictionary:

```text theme={null}
Thanks for calling SLNG support. I found your QubePay ACH transfer, and the next invoice will arrive on Friday.
```

<AudioPlayer title="Without pronunciation dictionary" description="The model guesses how to pronounce acronyms and product names." />

<AudioPlayer title="With pronunciation dictionary" description="The same text after rewrite rules are applied." />

## Manage dictionaries

For request and response schemas, see the generated API reference pages for [listing dictionaries](/api-reference/tts/pronunciation-dictionaries/list-pronunciation-dictionaries-http), [reading one dictionary](/api-reference/tts/pronunciation-dictionaries/get-pronunciation-dictionary-http), and [deleting a dictionary](/api-reference/tts/pronunciation-dictionaries/delete-pronunciation-dictionary-http).

List dictionaries:

```bash theme={null}
curl -s https://api.slng.ai/v1/pronunciation/dictionaries \
  -H "Authorization: Bearer SLNG_API_KEY"
```

Get one dictionary by name:

```bash theme={null}
curl -s https://api.slng.ai/v1/pronunciation/dictionaries/support-pronunciations \
  -H "Authorization: Bearer SLNG_API_KEY"
```

Delete a dictionary:

```bash theme={null}
curl -X DELETE https://api.slng.ai/v1/pronunciation/dictionaries/support-pronunciations \
  -H "Authorization: Bearer SLNG_API_KEY"
```

## Use a dictionary with HTTP TTS

Add a `pronunciation` object to the TTS request body:

```bash theme={null}
curl -X POST https://api.slng.ai/v1/tts/slng/deepgram/aura:2-en \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "aura-2-thalia-en",
    "text": "Thanks for calling SLNG support. I found your QubePay ACH transfer, and the next invoice will arrive on Friday.",
    "pronunciation": {
      "mode": "rewrite",
      "name": "support-pronunciations"
    }
  }'
```

You can also reference the dictionary by immutable ID:

```json theme={null}
{
  "pronunciation": {
    "mode": "rewrite",
    "dictionary_id": "pd_01abc..."
  }
}
```

Rules for the request object:

* `mode` must be `"rewrite"`
* provide exactly one of `name` or `dictionary_id`
* use only one active dictionary per request

With the example dictionary above, the selected model receives this rewritten text:

```text theme={null}
Thanks for calling slang support. I found your cube pay ay see aitch transfer, and the next invoice will arrive on Friday.
```

## Use a dictionary with WebSocket TTS

Set a default dictionary when you initialize the session:

```json theme={null}
{
  "type": "init",
  "config": {
    "pronunciation": {
      "mode": "rewrite",
      "name": "support-pronunciations"
    }
  }
}
```

Then send text normally:

```json theme={null}
{
  "type": "text",
  "text": "Thanks for calling SLNG support. I found your QubePay ACH transfer, and the next invoice will arrive on Friday."
}
```

To change dictionaries for a later turn, include `pronunciation` on the `text` message:

```json theme={null}
{
  "type": "text",
  "text": "Use another dictionary for this turn",
  "pronunciation": {
    "mode": "rewrite",
    "name": "finance-pronunciations"
  }
}
```

`init.config.pronunciation` sets the session default. `text.pronunciation` replaces the active dictionary for that turn, and later text turns reuse the most recent active dictionary.

## Use a dictionary with Unified TTS

Use the same `pronunciation` shape with Unified TTS bridge requests:

```json theme={null}
{
  "type": "init",
  "model": "slng/deepgram/aura:2-en",
  "config": {
    "language": "en-US",
    "sample_rate": 24000,
    "encoding": "linear16",
    "pronunciation": {
      "mode": "rewrite",
      "name": "support-pronunciations"
    }
  }
}
```

## Rewrite matching

Rewrite mode is deterministic:

* matching is case-insensitive
* only whole words or whole phrases are matched
* longer phrases win before shorter matches
* rewriting is single-pass and non-recursive

For example, this dictionary prefers `ACH transfer` over the shorter `ACH` match:

```json theme={null}
{
  "modes": {
    "rewrite": {
      "rules": [
        { "match": "ACH", "replace": "ay see aitch" },
        { "match": "ACH transfer", "replace": "ay see aitch transfer" }
      ]
    }
  }
}
```

Input:

```text theme={null}
I found your ACH transfer
```

Rewritten result:

```text theme={null}
I found your ay see aitch transfer
```

## Limits and errors

Current limits:

| Limit                          | Value              |
| ------------------------------ | ------------------ |
| Dictionary name                | 128 characters     |
| Rewrite rules per dictionary   | 256                |
| IPA rules per dictionary       | 256                |
| `match` length                 | 128 characters     |
| `replace` length               | 256 characters     |
| `ipa` length                   | 256 characters     |
| Runtime text input for rewrite | 20,000 characters  |
| Runtime rewritten output       | 100,000 characters |

Pronunciation resolution fails closed. If the dictionary cannot be found or resolved, the request or WebSocket turn is not sent to the selected TTS model.

Common HTTP errors:

| Status and code                     | Meaning                                                                   |
| ----------------------------------- | ------------------------------------------------------------------------- |
| `400 invalid_pronunciation`         | Malformed object, invalid name, unsupported mode, or dictionary not found |
| `401 pronunciation_unauthenticated` | Missing or unresolved organization context                                |
| `409 pronunciation_conflict`        | Dictionary name already exists in the organization                        |
| `503 pronunciation_unavailable`     | Platform storage or dependency failure during dictionary resolution       |

Common WebSocket failures return an error frame:

```json theme={null}
{
  "type": "error",
  "code": "pronunciation_not_found",
  "message": "Pronunciation dictionary not found: support-pronunciations",
  "slng_request_id": "..."
}
```

## Current limitations

* Only `mode: "rewrite"` is executable today.
* `modes.ipa` can be stored but is not executed.
* There is no automatic fallback from IPA to rewrite.
* Provider-native pronunciation dictionary uploads are not supported through SLNG.

## Recommended pattern

For most applications, create a stable dictionary such as `support-pronunciations` and reuse it by name. Use `dictionary_id` only when your application needs an immutable machine reference.

Keep dictionaries scoped to a domain, product line, or voice style. For WebSocket sessions, set the default dictionary in `init`, then override individual turns only when needed.


# HTTP vs. WebSocket protocols
Source: https://docs.slng.ai/protocols

Compare HTTP and WebSocket protocols on SLNG. Latency, flow, complexity, and when to use each for text-to-speech and speech-to-text workloads.

Every TTS and STT model is reachable over both HTTP and WebSocket. The URL stays the same; only the protocol changes.

The snippets on this page use `SLNG_API_KEY` as a placeholder. Replace it with an SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys) before running the code.

## At a Glance

|                | HTTP                               | WebSocket                          |
| -------------- | ---------------------------------- | ---------------------------------- |
| **Flow**       | Request → wait → complete response | Open connection → stream both ways |
| **Latency**    | 200–500 ms                         | Sub-100 ms                         |
| **Best for**   | Batch jobs, file conversion        | Voice agents, live transcription   |
| **Complexity** | One `curl` call                    | Connection lifecycle to manage     |

## How Each Protocol Works

<Tabs>
  <Tab title="HTTP">
    You send a request and get back the full result once processing finishes.

    ```mermaid theme={null}
    sequenceDiagram
        participant Client
        participant SLNG
        Client->>SLNG: POST /v1/tts/slng/deepgram/aura:2-en<br/>{ "text": "Hello" }
        Note over SLNG: Generates full audio
        SLNG-->>Client: 200 OK – complete WAV file
    ```

    **Use HTTP when you:**

    * Generate audio files for download or storage
    * Transcribe pre-recorded audio files
    * Want the simplest possible integration
    * Don't need real-time streaming

    ```bash theme={null}
    curl https://api.slng.ai/v1/tts/slng/deepgram/aura:2-en \
      -H "Authorization: Bearer SLNG_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{ "model": "aura-2-thalia-en", "text": "Hello from HTTP!" }' \
      --output hello.wav
    ```

    See complete examples: [TTS over HTTP](/examples/tts-http) · [STT over HTTP](/examples/stt-http)
  </Tab>

  <Tab title="WebSocket">
    You open a persistent connection and stream data in both directions.

    ```mermaid theme={null}
    sequenceDiagram
        participant Client
        participant SLNG
        Client->>SLNG: Connect wss://api.slng.ai/v1/tts/slng/deepgram/aura:2-en
        SLNG-->>Client: Connection open
        Client->>SLNG: { type: "text", text: "Hello" }
        SLNG-->>Client: audio chunk 1
        SLNG-->>Client: audio chunk 2
        SLNG-->>Client: audio chunk 3
        Client->>SLNG: { type: "text", text: "More text" }
        SLNG-->>Client: audio chunk 4
        Note over Client,SLNG: Connection stays open – send more text anytime
    ```

    **Use WebSocket when you:**

    * Build voice agents (STT + LLM + TTS in a loop)
    * Need real-time transcription from a microphone
    * Want the lowest possible latency
    * Stream audio continuously

    ```javascript theme={null}
    const ws = new WebSocket("wss://api.slng.ai/v1/tts/slng/deepgram/aura:2-en");

    ws.onopen = () => {
      ws.send(JSON.stringify({ type: "text", text: "Hello from WebSocket!" }));
    };

    ws.onmessage = (event) => {
      if (event.data instanceof ArrayBuffer) {
        playAudio(event.data); // Stream audio as it arrives
      }
    };
    ```

    See complete examples: [TTS over WebSocket](/examples/tts-websocket) · [STT over WebSocket](/examples/stt-websocket)
  </Tab>
</Tabs>

## WebSocket Best Practices

WebSocket connections are stateful. You need to handle the lifecycle:

* **Reconnect with backoff.** If the connection drops, retry with exponential delay (1s, 2s, 4s... up to 30s).
* **Handle binary and text frames.** Audio arrives as binary `ArrayBuffer`; control messages come as JSON text.
* **Send a close frame** when you're done so the server releases resources.

## Which Protocol for Which Use Case?

| Use case                          | Protocol  | Why                             |
| --------------------------------- | --------- | ------------------------------- |
| Convert a script to an audio file | HTTP      | One request, one file. Simple   |
| Transcribe a batch of recordings  | HTTP      | Upload each file, get results   |
| Voice agent (phone or web)        | WebSocket | Real-time STT→LLM→TTS loop      |
| Live captioning / transcription   | WebSocket | Stream mic audio, get text back |
| Generate a voiceover for a video  | HTTP      | No real-time requirement        |

## Next Steps

<CardGroup>
  <Card title="TTS over HTTP" icon="file-audio" href="/examples/tts-http">
    Generate audio files from text with simple HTTP requests.
  </Card>

  <Card title="TTS over WebSocket" icon="bolt" href="/examples/tts-websocket">
    Stream audio in real-time with interruption support.
  </Card>

  <Card title="STT over HTTP" icon="file-lines" href="/examples/stt-http">
    Transcribe pre-recorded audio files.
  </Card>

  <Card title="STT over WebSocket" icon="microphone" href="/examples/stt-websocket">
    Transcribe live audio from a microphone.
  </Card>
</CardGroup>


# Error Codes & Troubleshooting
Source: https://docs.slng.ai/reference/errors

Authentication, WebSocket, and pronunciation-dictionary error codes for the SLNG API, plus fixes for common streaming and audio-format issues.

## Authentication errors

| Error                            | Cause                                | Fix                                                                                                                      |
| -------------------------------- | ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------ |
| HTTP 401                         | Missing or invalid SLNG key          | Check the `Authorization: Bearer SLNG_API_KEY` header. Verify the key is active in the [Dashboard](https://app.slng.ai). |
| WebSocket rejected with 401      | SLNG key not passed in the handshake | Pass the key as a header (`Authorization: Bearer SLNG_API_KEY`) or query parameter (`?token=SLNG_API_KEY`).              |
| `X-Slng-Auth-Source: client_key` | BYOK provider key rejected upstream  | Your provider key was rejected, not the SLNG key. Check the key with the provider directly.                              |

## WebSocket errors

| Error code                  | Meaning                             | What to do                                                         |
| --------------------------- | ----------------------------------- | ------------------------------------------------------------------ |
| `auth_error`                | Invalid or missing SLNG key         | Check your Authorization header.                                   |
| `config_error`              | Invalid session configuration       | Verify your `init` message parameters.                             |
| `rate_limit`                | Too many concurrent connections     | Back off and retry with exponential delay.                         |
| `provider_error`            | Upstream model returned an error    | Check model availability; consider configuring failover models.    |
| `backend_connection_failed` | Could not connect to upstream model | The model may be temporarily unavailable; retry or use a fallback. |

## Pronunciation dictionary errors

| Status | Code                            | Meaning                                                                   |
| ------ | ------------------------------- | ------------------------------------------------------------------------- |
| 400    | `invalid_pronunciation`         | Malformed object, invalid name, unsupported mode, or dictionary not found |
| 401    | `pronunciation_unauthenticated` | Missing or unresolved organization context                                |
| 409    | `pronunciation_conflict`        | Dictionary name already exists in your organization                       |
| 503    | `pronunciation_unavailable`     | Platform dependency failure during dictionary resolution                  |

WebSocket pronunciation errors return an error frame:

```json theme={null}
{
  "type": "error",
  "code": "pronunciation_not_found",
  "message": "Pronunciation dictionary not found: support-pronunciations"
}
```

## Common issues

### Connection drops

WebSocket disconnects unexpectedly.

* Implement reconnection with exponential backoff (1s, 2s, 4s, up to 30s).
* Send periodic keep-alive messages (`{"type": "keepalive"}` for STT) to prevent idle timeouts.
* If behind a corporate proxy, confirm it supports WebSocket upgrades (the `Connection: Upgrade` header).

### Choppy or distorted audio (TTS)

* Buffer at least 200ms of audio before starting playback.
* Use the WebAudio API (`AudioContext`) instead of `<audio>` elements for gapless chunk playback.
* Confirm your player's sample rate matches the `sample_rate` from your `init` config.
* 24kHz linear16 audio requires roughly 384 kbps. Verify your connection can sustain it.

### Delayed transcriptions (STT)

* Send audio in 20-100ms chunks (320-1600 bytes at 16kHz linear16).
* Confirm `encoding` and `sample_rate` in your `init` config match your actual audio format.
* For real-time use, prefer Deepgram Nova, which is optimized for streaming latency.

### Audio format mismatch

Keep your audio configuration consistent across the pipeline:

```json theme={null}
{
  "encoding": "linear16",
  "sample_rate": 16000
}
```

Your audio capture must match: 16-bit samples, 16000 Hz, single channel (mono).

## Getting help

* Email: [support@slng.ai](mailto:support@slng.ai)
* Discord: [discord.gg/slng](https://discord.gg/slng)


# Regional Execution
Source: https://docs.slng.ai/region-override

Models run where the data lives. Requests route to the lowest-latency region by default; pin a region or geographic zone with the X-Region-Override and X-World-Part-Override headers.

Models run where the data lives.

By default, each request routes to the closest available region. Two HTTP headers override that: `X-Region-Override` pins a specific region, and `X-World-Part-Override` keeps traffic within a broader geographic zone.

|                     | `X-Region-Override`             | `X-World-Part-Override`                                         |
| ------------------- | ------------------------------- | --------------------------------------------------------------- |
| **Scope**           | Exact region                    | Geographic zone                                                 |
| **Example value**   | `eu-north-1`                    | `eu`                                                            |
| **Use when**        | You need a specific data center | You want to stay in a geography without picking an exact region |
| **If both are set** | Wins                            | Ignored                                                         |

## Default behavior

When you make a request without any region headers, it routes to the closest available region. No configuration needed.

## Region pinning

Pin to a specific data center with `X-Region-Override`. Use this when you have data-residency or compliance requirements that depend on a specific location.

```bash theme={null}
curl https://api.slng.ai/v1/tts/slng/deepgram/aura:2-en \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Region-Override: eu-north-1" \
  -d '{ "voice": "aura-2-thalia-en", "text": "Hello from Europe!" }' \
  --output hello.wav
```

## World-part constraints

Keep traffic within a geographic zone with `X-World-Part-Override`. The best available region within that zone is selected. Use this when you need to stay within a geography but do not need a specific data center.

```bash theme={null}
curl https://api.slng.ai/v1/tts/slng/deepgram/aura:2-en \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-World-Part-Override: eu" \
  -d '{ "voice": "aura-2-thalia-en", "text": "Hello from somewhere in Europe!" }' \
  --output hello.wav
```

If both headers are present, `X-Region-Override` wins.

## Available regions

Not every model is deployed in every region. Check [Models by Region](/models/by-region) to see what is available where.

| World part | Region ID              | Location     |
| ---------- | ---------------------- | ------------ |
| `na`       | `us-east-1`            | US East      |
| `eu`       | `eu-north-1`           | EU North     |
| `ap`       | `ap-south-1`           | AP South     |
| `ap`       | `ap-southeast-2`       | AP Southeast |
| `ap`       | `asia-south1`          | AP South     |
| `ap`       | `asia-southeast2`      | Jakarta      |
| `ap`       | `australia-southeast1` | Sydney       |

## World parts

A world part groups several regions under one value. Requests route to the best available region within that zone, which does not guarantee a specific country.

| Value       | Zone           |
| ----------- | -------------- |
| `na`        | North America  |
| `eu`        | Europe         |
| `eu-non-eu` | Europe, non-EU |
| `ap`        | Asia-Pacific   |
| `me`        | Middle East    |

<Warning>
  If your compliance requirement depends on a specific country, use `X-Region-Override` with the exact region. A world part routes to the best region within a zone and does not guarantee a specific country.
</Warning>

## Voice agent region config

Voice agents use a separate `region` field (`us-east`, `eu-central`, `ap-south`) that determines where the agent runs. It is not interchangeable with the platform headers above: the agent region `ap-south`, for example, routes to the platform region `ap-south-1`, but you set it through a different field. See the [Voice Agents region table](/voice-agents#agent-regions) for the full mapping and the telephony country pinning each region applies.

## Compliance

Regional execution is not just about latency. In regulated industries it determines where data can exist and which models can process it. These constraints are respected per request.

If you need a particular model hosted in a region where it is not currently available, [contact us](mailto:support@slng.ai).

## Next steps

<CardGroup>
  <Card title="Models by region" icon="globe" href="/models/by-region">
    See which models are deployed in each region.
  </Card>

  <Card title="Adaptive Execution" icon="shuffle" href="/execution-layer/adaptive">
    How geography is one of four dimensions the layer adapts on.
  </Card>
</CardGroup>


# Command-line interface
Source: https://docs.slng.ai/sdks/cli

Install the voiceai CLI and run text-to-speech, speech-to-text, and streaming examples from a terminal.

`voiceai` is a single static binary that wraps the SLNG API. Use it to generate audio, transcribe files, stream over WebSocket, and pipe audio between tools.

## Install

<CodeGroup>
  ```bash curl theme={null}
  curl -fsSL https://slng.ai/install.sh | sh
  ```

  ```bash Homebrew theme={null}
  brew install slng-ai/tap/voiceai
  ```

  ```bash npm theme={null}
  npm install -g voiceai-cli
  ```
</CodeGroup>

Verify the install:

```bash theme={null}
voiceai --help
```

<Note>
  On macOS, the `curl`-installed binary is unsigned. If the first run is blocked by Gatekeeper, run `xattr -d com.apple.quarantine $(which voiceai)` or right-click → Open in Finder once.
</Note>

## Authenticate

Get an SLNG key from [app.slng.ai](https://app.slng.ai/api-keys), then export it in your shell:

```bash theme={null}
export VOICEAI_API_KEY="zpka_..."
```

Or save it to the CLI config:

```bash theme={null}
voiceai config set api-key zpka_...
```

The config lives at `~/.config/voiceai/config.json`. Environment variables take precedence.

## Text-to-speech

Synthesize audio from text. By default the CLI plays the audio and saves a copy to `$TMPDIR/voiceai-tts/`.

```bash theme={null}
voiceai tts "Hello from sunny Barcelona!" \
  --model slng/deepgram/aura:2-en \
  --voice aura-2-thalia-en \
  --out hello.mp3
```

Pipe raw audio when stdout is not a terminal:

```bash theme={null}
voiceai tts "stream me" --model slng/deepgram/aura:2-en > out.mp3
```

Stream chunks over WebSocket for long text or low-latency playback:

```bash theme={null}
voiceai tts "long passage…" --stream | ffplay -
```

## Speech-to-text

Transcribe a file:

```bash theme={null}
voiceai stt micro-machines.wav --model slng/deepgram/nova:3-en
```

Stream from the microphone:

```bash theme={null}
voiceai stt --stream
```

Pipe raw PCM from `arecord` or any source:

```bash theme={null}
arecord -f S16_LE -r 16000 -c 1 | voiceai stt --stream --source stdin
```

## Discover models and voices

```bash theme={null}
voiceai models               # list all models
voiceai voices --model slng/deepgram/aura:2-en
```

## Configuration

Defaults that the CLI reads from `~/.config/voiceai/config.json`:

| Key                 | Purpose                                       |
| ------------------- | --------------------------------------------- |
| `api-key`           | Default `VOICEAI_API_KEY`                     |
| `default-tts-model` | Model used when `--model` is omitted on `tts` |
| `default-tts-voice` | Voice used when `--voice` is omitted on `tts` |
| `default-stt-model` | Model used when `--model` is omitted on `stt` |
| `base-url`          | Override the API host (rarely needed)         |

Set any of them with `voiceai config set <key> <value>`. Override per-invocation with the matching flag.

## Source and releases

* Source: [github.com/slng-ai/sdks](https://github.com/slng-ai/sdks)
* Releases: [github.com/slng-ai/sdks/releases](https://github.com/slng-ai/sdks/releases). Tags prefixed `cli-v*` are CLI builds; everything else is for the SDKs.


# SDKs and tools
Source: https://docs.slng.ai/sdks/index

Install the voiceai CLI, the JavaScript or Python SDK, or drop the slng agent skills into your coding agent.

The SLNG API is REST and WebSocket-native, so any HTTP client works. We also ship a CLI, two SDKs, and an agent-skills pack so you don't have to write that client yourself.

<CardGroup>
  <Card title="CLI" icon="terminal" href="/sdks/cli">
    `voiceai` runs text-to-speech and speech-to-text from a terminal. Install with `curl`, Homebrew, or `npm`.
  </Card>

  <Card title="JavaScript SDK" icon="https://mintcdn.com/slng/2xZHLyyFGVnnnXpA/images/sdks/javascript.svg?fit=max&auto=format&n=2xZHLyyFGVnnnXpA&q=85&s=a0999a9caef3fe771138f3c08805a264" href="/sdks/javascript">
    `voiceai-sdk` on npm. Typed client for Node, Bun, and Deno.
  </Card>

  <Card title="Python SDK" icon="https://mintcdn.com/slng/2xZHLyyFGVnnnXpA/images/sdks/python.svg?fit=max&auto=format&n=2xZHLyyFGVnnnXpA&q=85&s=c1e3917b35ac7019c6eceef08a3a2b18" href="/sdks/python">
    `voiceai-sdk` on PyPI. Sync and async clients for Python 3.9+.
  </Card>

  <Card title="Agent skills" icon="https://mintcdn.com/slng/2xZHLyyFGVnnnXpA/images/sdks/claude.svg?fit=max&auto=format&n=2xZHLyyFGVnnnXpA&q=85&s=3952b103294f073e198c949c2532daae" href="/sdks/skills">
    `slng-ai/skills` teaches coding agents how to call the API.
  </Card>
</CardGroup>

## Which one should I use?

| If you want to…                                                          | Use                                |
| ------------------------------------------------------------------------ | ---------------------------------- |
| Try the API from a terminal, script CI jobs, or pipe audio between tools | [CLI](/sdks/cli)                   |
| Build a Node, Bun, or Deno service                                       | [JavaScript SDK](/sdks/javascript) |
| Build a Python service, backend, or notebook                             | [Python SDK](/sdks/python)         |
| Let an AI coding agent (Claude Code and similar) call the API for you    | [Agent skills](/sdks/skills)       |

All four wrap the same API, so you can mix them. Generate sample audio with the CLI, then call the Python SDK from a notebook to transcribe it.

## SLNG key

Every tool reads its key from an environment variable. Grab one from [app.slng.ai](https://app.slng.ai/api-keys) and export it before running the examples on the next pages:

```bash theme={null}
export VOICEAI_API_KEY="zpka_..."
```

<Note>
  The CLI reads `VOICEAI_API_KEY`. The JS and Python SDKs default to `SLNG_API_KEY` but accept an explicit `apiKey` option. Set both to the same value if you plan to use multiple tools side by side.
</Note>


# JavaScript SDK
Source: https://docs.slng.ai/sdks/javascript

Install voiceai-sdk on npm and call text-to-speech, speech-to-text, and streaming endpoints from Node, Bun, or Deno.

`voiceai-sdk` is the official TypeScript client for the SLNG API. It works in any runtime that supports Node 18+ (Node, Bun, Deno).

## Install

<CodeGroup>
  ```bash npm theme={null}
  npm install voiceai-sdk
  ```

  ```bash pnpm theme={null}
  pnpm add voiceai-sdk
  ```

  ```bash yarn theme={null}
  yarn add voiceai-sdk
  ```

  ```bash bun theme={null}
  bun add voiceai-sdk
  ```
</CodeGroup>

## Initialize the client

Get an SLNG key from [app.slng.ai](https://app.slng.ai/api-keys), then construct the client:

```ts theme={null}
import Slng from "voiceai-sdk";

const client = new Slng({
  apiKey: process.env.SLNG_API_KEY,
});
```

The `apiKey` option defaults to `process.env.SLNG_API_KEY`. Pass an explicit string to override.

## Text-to-speech

```ts theme={null}
import { writeFile } from "node:fs/promises";
import Slng from "voiceai-sdk";

const client = new Slng({ apiKey: process.env.SLNG_API_KEY });

const audio = await client.textToSpeech.create("slng/deepgram/aura:2-en", {
  text: "Hello from the SLNG SDK.",
  voice: "aura-2-thalia-en",
});

await writeFile("hello.wav", Buffer.from(await audio.arrayBuffer()));
```

## Speech-to-text

```ts theme={null}
import { createReadStream } from "node:fs";
import Slng from "voiceai-sdk";

const client = new Slng({ apiKey: process.env.SLNG_API_KEY });

const transcript = await client.speechToText.create("slng/deepgram/nova:3-en", {
  audio: createReadStream("meeting.wav"),
});

console.log(transcript.text);
```

## Streaming over WebSocket

For long passages of text-to-speech or live transcription, use the streaming client:

```ts theme={null}
import { StreamingClient } from "voiceai-sdk/streaming";

const streaming = new StreamingClient({ apiKey: process.env.SLNG_API_KEY });
const session = await streaming.connectStt("slng/deepgram/nova:3-en");

session.send({
  type: "init",
  config: { language: "en", sample_rate: 16000, encoding: "linear16" },
});

for await (const msg of session) {
  if (msg.type === "final_transcript") console.log(msg.text);
}
```

See [WebSockets](/websockets) for the full message schema.

## Discover models

```ts theme={null}
const models = await client.models.list();
const voices = await client.voices.list({ model: "slng/deepgram/aura:2-en" });
```

## Links

* npm: [npmjs.com/package/voiceai-sdk](https://www.npmjs.com/package/voiceai-sdk)
* Source: [github.com/slng-ai/sdks](https://github.com/slng-ai/sdks)


# Python SDK
Source: https://docs.slng.ai/sdks/python

Install voiceai-sdk on PyPI and call text-to-speech, speech-to-text, and streaming endpoints with sync or async clients.

`voiceai-sdk` is the official Python client for the SLNG API. It targets Python 3.9+ and ships both a synchronous `Slng` client and an `AsyncSlng` for asyncio code.

## Install

```bash theme={null}
pip install voiceai-sdk
```

Or with `uv`:

```bash theme={null}
uv add voiceai-sdk
```

## Initialize the client

Get an SLNG key from [app.slng.ai](https://app.slng.ai/api-keys), then construct the client:

```python theme={null}
from voiceai_sdk import Slng

client = Slng()                      # reads SLNG_API_KEY
client = Slng(api_key="zpka_...")    # or pass it explicitly
```

## Text-to-speech

```python theme={null}
from voiceai_sdk import Slng

client = Slng()

audio = client.text_to_speech.create(
    model_variant="slng/deepgram/aura:2-en",
    text="Hello from the SLNG Python SDK.",
    voice="aura-2-thalia-en",
)

audio.write_to_file("hello.wav")
```

## Speech-to-text

```python theme={null}
from pathlib import Path
from voiceai_sdk import Slng

client = Slng()

transcript = client.speech_to_text.create(
    model_variant="slng/deepgram/nova:3-en",
    audio=Path("meeting.wav"),
)

print(transcript.text)
```

## Async client

For asyncio applications, swap `Slng` for `AsyncSlng`:

```python theme={null}
import asyncio
from pathlib import Path
from voiceai_sdk import AsyncSlng

async def main():
    client = AsyncSlng()
    transcript = await client.speech_to_text.create(
        model_variant="slng/deepgram/nova:3-en",
        audio=Path("meeting.wav"),
    )
    print(transcript.text)

asyncio.run(main())
```

## Discover models

```python theme={null}
models = client.models.list()
voices = client.voices.list(model="slng/deepgram/aura:2-en")
```

## Links

* PyPI: [pypi.org/project/voiceai-sdk](https://pypi.org/project/voiceai-sdk/)
* Source: [github.com/slng-ai/sdks](https://github.com/slng-ai/sdks)


# Agent skills
Source: https://docs.slng.ai/sdks/skills

Install the slng-ai/skills pack so coding agents like Claude Code can call text-to-speech, transcription, and voice-agent APIs on your behalf.

`slng-ai/skills` is a bundle of agent skills for SLNG. After you install it, your coding agent knows how to set up an SLNG key, synthesize speech, transcribe audio, build voice-agent prompts, and dispatch outbound calls. Each skill is a short markdown brief plus example code the agent can run directly.

## Install

```bash theme={null}
npx skills add slng-ai/skills
```

That command fetches the latest version of every skill and drops them into the skills directory your agent reads from (e.g. `~/.claude/skills/` for Claude Code). Re-run it to update.

## Set up your key

The skills expect `VOICEAI_API_KEY` to be set in your shell or in a project `.env`:

```bash theme={null}
export VOICEAI_API_KEY="zpka_..."
```

Get one from [app.slng.ai](https://app.slng.ai/api-keys). The `setup-api-key` skill walks the agent through this on first use.

## What you get

| Skill            | What the agent learns to do                                                 |
| ---------------- | --------------------------------------------------------------------------- |
| `setup-api-key`  | Configure and validate `VOICEAI_API_KEY`                                    |
| `text-to-speech` | Generate speech with Deepgram Aura, Rime Arcana, Cartesia, Murf, and others |
| `speech-to-text` | Transcribe audio with Deepgram Nova, Sarvam Saaras, Soniox, or Reson8       |
| `agent-prompt`   | Build a complete voice-agent prompt ready to paste into the Agent Builder   |
| `agents`         | Create, manage, and dispatch SLNG voice agents (including outbound calls)   |

Each skill shows the same task four ways: CLI, JavaScript SDK, Python SDK, and raw HTTP. The agent picks whichever fits the project it is working in.

## Example: ask your agent to transcribe a file

After installing the pack, ask the agent something like:

> Transcribe `meeting.wav` with slng and summarize the result.

The agent picks up the `speech-to-text` skill, runs `voiceai stt meeting.wav` (or the SDK equivalent if the project is already Python or JavaScript), parses the response, and writes the summary back to you.

## Works with

Any coding agent that loads skills from a directory. The skills are plain markdown plus shell-runnable examples, so they work with Claude Code, Cursor's agent mode, and any compatible host.

## Source

* Repo: [github.com/slng-ai/skills](https://github.com/slng-ai/skills)
* File an issue or PR there to propose new skills.


# Speech-to-Text Overview
Source: https://docs.slng.ai/stt/overview

Access STT models from multiple providers through a single platform. The execution layer routes each request based on language, accent, noise, and cost.

For the full, current list, see [Speech-to-Text Models](/models/stt).

## Which approach should you use?

| I need to...                                       | Use                                            |
| -------------------------------------------------- | ---------------------------------------------- |
| Transcribe pre-recorded audio files                | [HTTP](/examples/stt-http)                     |
| Transcribe in real time from a microphone or call  | [WebSocket Streaming](/examples/stt-websocket) |
| Process large volumes of recordings asynchronously | [Batch Transcription](/batch-guide)            |

## Which model should you use?

| I need...                               | Recommended model                   | Why                                           |
| --------------------------------------- | ----------------------------------- | --------------------------------------------- |
| Lowest latency for English voice agents | Deepgram Nova 3 (SLNG-hosted)       | Deployed on SLNG infrastructure               |
| Hindi transcription                     | Deepgram Nova 3 Hindi (SLNG-hosted) | Dedicated Hindi model in AP South             |
| Broadest language coverage              | Soniox                              | Wide multi-language support                   |
| Medical terminology                     | Deepgram Nova 3 Medical             | Specialized medical vocabulary                |
| Indian languages                        | Sarvam AI Saaras                    | Domain-aware recognition for Indian languages |
| European languages                      | Reson8 STT                          | Dutch, French, German, Spanish, and more      |

## Quick example

```bash theme={null}
curl https://api.slng.ai/v1/stt/slng/deepgram/nova:3 \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -F "audio=@recording.wav" \
  -F "language=en"
```

Response:

```json theme={null}
{
  "text": "Hello, how can I help you today?",
  "confidence": 0.97,
  "duration": 2.5,
  "language": "en"
}
```

See [HTTP](/examples/stt-http) for complete examples in cURL, JavaScript, and Python, and [WebSocket Streaming](/examples/stt-websocket) for real-time transcription.


# Text-to-Speech Overview
Source: https://docs.slng.ai/tts/overview



SLNG gives you access to a range of text-to-speech models from multiple providers through a single platform. The execution layer assembles output from cache when possible, so repeated phrases return from the edge without hitting the upstream model.

For the full, current list with latency, hosting, and language details, see [Text-to-Speech Models](/models/tts). For voice samples, see [Voices](/models/index).

## Which approach should you use?

| I need to...                                        | Use                                                           |
| --------------------------------------------------- | ------------------------------------------------------------- |
| Generate audio files for download or storage        | [HTTP](/examples/tts-http)                                    |
| Stream audio in real time for a voice agent or app  | [WebSocket Streaming](/examples/tts-websocket)                |
| Control how brand names and acronyms are pronounced | Add [Pronunciation Dictionaries](/pronunciation-dictionaries) |
| Use my own provider keys with SLNG's optimization   | Enable [BYOK](/execution-layer/byok)                          |

## Which model should you use?

| I need...                                   | Recommended model                     | Why                                          |
| ------------------------------------------- | ------------------------------------- | -------------------------------------------- |
| Lowest latency English voice agent          | Deepgram Aura 2 (SLNG-hosted)         | Low-latency, deployed on SLNG infrastructure |
| Lowest latency with broad language coverage | Cartesia Sonic 3                      | Many languages, low latency                  |
| Hindi / Indian languages                    | Sarvam Bulbul                         | Indian languages, many voices                |
| Multilingual with expressiveness control    | KugelAudio Kugel                      | Broad language coverage                      |
| Spanish                                     | Deepgram Aura 2 Spanish (SLNG-hosted) | SLNG-hosted Spanish voice                    |

## Execution layer behavior

Every TTS request goes through the output assembly stage, which checks whether this text, voice, and config combination has been assembled before:

* **Cache hit**: audio returns from the edge. No upstream model call. No provider billing.
* **Cache miss**: the request routes to the model endpoint, audio is synthesized, and the result is cached.

The more calls flow through the system, the more cache coverage grows. Repeated phrases (greetings, disclosures, confirmations) become effectively free.

See [Output Assembly](/execution-layer/output-assembly) for caching, segment reuse, and cache scoping.

## Quick example

```bash theme={null}
curl https://api.slng.ai/v1/tts/slng/deepgram/aura:2 \
  -H "Authorization: Bearer SLNG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello from SLNG!"}' \
  --output hello.wav
```

See [HTTP](/examples/tts-http) for complete examples in cURL, JavaScript, and Python, and [WebSocket Streaming](/examples/tts-websocket) for real-time voice agent audio.


# Voice agents on SLNG
Source: https://docs.slng.ai/voice-agents

Voice Agents pair an LLM with SLNG's STT and TTS models. Create an agent once, then dispatch it to phone calls or web sessions, with tools, webhooks, and template variables.

Voice Agents are server-managed configurations that pair an LLM with SLNG's STT and TTS models. You create an agent once, then dispatch it to phone calls or web sessions. Agents support tools, built-in utilities like current date/time lookup, webhooks, human transfer, and dynamic prompts via template variables.

<Note>
  The Voice Agents API is served from <code>[https://api.agents.slng.ai](https://api.agents.slng.ai)</code>
  under <code>/v1/agents</code>.
</Note>

## Where to go next

This page is the orientation. The detail lives in four places:

<CardGroup>
  <Card title="Build your first agent" icon="code" href="/examples/agents-api">
    Create, update, duplicate, and delete agents in cURL, JavaScript, and Python.
  </Card>

  <Card title="Configuration & Tools" icon="sliders" href="/examples/agents-config">
    System prompts, models, tools, tool personalization, and template variables.
  </Card>

  <Card title="Calls, telephony & web sessions" icon="phone" href="/examples/agents-calls">
    Dispatch outbound calls, run batch campaigns, and test with web sessions.
  </Card>

  <Card title="Agent Infra" icon="paintbrush" href="/dashboard/agent-infra">
    Build and test agents with the visual Dashboard UI.
  </Card>
</CardGroup>

## Dashboard or API

You can build agents either way, and the two stay in sync. Start in [Agent Infra](/dashboard/agent-infra) for a UI (and to set up [Telephony](/dashboard/telephony)), or manage everything through the API. Everything in the Dashboard maps to public API endpoints.

<Tip>
  If you already have an agent configured the way you want, you can duplicate it
  from the API or from Agent Infra. Duplication preserves the stored configuration,
  but it does not copy call history or the inbound connection. After duplicating,
  reconnect inbound routing if needed, verify the outbound trunk, and test the copy
  with a web session or test call.
</Tip>

## Agent regions

Voice Agents use logical region values that correspond to the Agent Settings region menu. The selected region controls where the agent session runs and how the agent routes its model requests. For model requests, routing is constrained to the selected compliance area, and the exact deployment can vary based on model availability inside that area.

| Agent Settings label | API `region` value | LiveKit runtime location | Routing override applied to model requests |
| -------------------- | ------------------ | ------------------------ | ------------------------------------------ |
| Europe               | `eu-central`       | Frankfurt, Germany       | `X-World-Part-Override: eu`                |
| United States        | `us-east`          | Ashburn, Virginia, USA   | `X-World-Part-Override: na`                |
| Asia                 | `ap-south`         | Mumbai, India            | `X-Region-Override: ap-south-1`            |

`region` is required when you create an agent. It differs from the platform-level [region overrides](/region-override): the agent region `ap-south`, for example, routes to the platform region `ap-south-1`, but you set it through a different field.

## Example agent patterns

Common production-style tool combinations (configured in [Configuration & Tools](/examples/agents-config#tools)):

* **Scheduling assistant**: `current_datetime` + `hangup` + idle nudges. The agent needs accurate local time before offering appointment slots.
* **Support router**: contextual webhook lookup + `human_transfer`. Resolves routine cases, escalates exceptions.
* **Collections follow-up**: `voicemail_detection` + system webhook on `call_end`. Every completed call posts a summary to your CRM.
* **Restaurant host**: `current_datetime` + availability webhook. Reservation and booking lookups that depend on real-time availability.
* **After-hours clinic router**: system-injected `current_datetime` on `call_start` + `human_transfer` + `hangup`. Business-hour logic is available to the model before the first turn.

## Calls and sessions

| Endpoint                                    | Purpose                                                               |
| ------------------------------------------- | --------------------------------------------------------------------- |
| `POST /v1/agents/{agent_id}/calls`          | Dispatch an outbound call (requires telephony)                        |
| `POST /v1/agents/{agent_id}/web-sessions`   | Create a web (non-telephony) session                                  |
| `POST /v1/agents/{agent_id}/duplicate`      | Server-side copy (inbound connection and call history are not copied) |
| `GET /v1/agents/{agent_id}/calls`           | List calls (paginated)                                                |
| `GET /v1/agents/{agent_id}/calls/{call_id}` | Fetch a call record                                                   |

For code, see [dispatching calls](/examples/agents-calls) and the [agent lifecycle examples](/examples/agents-api). For a friendly transcript view, use the Dashboard [calls page](/dashboard/agent-infra#calls).

### Tool execution tracking

Record webhook, template, human-transfer, and built-in tool activity against a call by posting to the [tool executions endpoint](/api-reference/calls/submit-tool-execution). Each record carries the outcome, duration, and HTTP status, and surfaces on the [call detail response](/api-reference/calls/get-call) for debugging or analytics.

## API reference

See the **Voice Agents API** group in the [API Reference](/api-reference) for the complete OpenAPI spec.


# Cartesia Sonic 3
Source: https://docs.slng.ai/voices/cartesia-sonic-3

Browse Cartesia Sonic 3 voices on SLNG with audio samples — low-latency multilingual TTS across 40+ languages including English, Spanish, French, and Hindi.

Cartesia Sonic 3 is a low-latency multilingual text-to-speech model with a large catalog of voices across 40+ languages. Voices are referenced by UUID. Pass the `voice_id` from the tables below as the `voice` field in your init message.

```json theme={null}
{
  "type": "init",
  "model_id": "sonic-3",
  "voice": "f786b574-daa5-4673-aa0c-cbe3e8534c02",
  "encoding": "linear16",
  "sample_rate": 24000
}
```

Many voices support multiple languages. To override the default language for a multilingual voice, set the optional `language` field to a supported ISO code (for example `"language": "es"`).

## Supported languages

| Language                  | Code | Voices |
| ------------------------- | ---- | ------ |
| [English](#english)       | `en` | 373    |
| [Spanish](#spanish)       | `es` | 47     |
| [French](#french)         | `fr` | 35     |
| [German](#german)         | `de` | 32     |
| [Hindi](#hindi)           | `hi` | 29     |
| [Japanese](#japanese)     | `ja` | 22     |
| [Korean](#korean)         | `ko` | 17     |
| [Portuguese](#portuguese) | `pt` | 16     |
| [Arabic](#arabic)         | `ar` | 14     |
| [Chinese](#chinese)       | `zh` | 12     |
| [Dutch](#dutch)           | `nl` | 12     |
| [Italian](#italian)       | `it` | 12     |
| [Polish](#polish)         | `pl` | 12     |
| [Russian](#russian)       | `ru` | 9      |
| [Swedish](#swedish)       | `sv` | 9      |
| [Tagalog](#tagalog)       | `tl` | 8      |
| [Telugu](#telugu)         | `te` | 8      |
| [Turkish](#turkish)       | `tr` | 8      |
| [Tamil](#tamil)           | `ta` | 7      |
| [Czech](#czech)           | `cs` | 6      |
| [Hebrew](#hebrew)         | `he` | 6      |
| [Finnish](#finnish)       | `fi` | 5      |
| [Thai](#thai)             | `th` | 5      |
| [Danish](#danish)         | `da` | 4      |
| [Hungarian](#hungarian)   | `hu` | 3      |
| [Vietnamese](#vietnamese) | `vi` | 3      |
| [Bengali](#bengali)       | `bn` | 2      |
| [Bulgarian](#bulgarian)   | `bg` | 2      |
| [Croatian](#croatian)     | `hr` | 2      |
| [Georgian](#georgian)     | `ka` | 2      |
| [Greek](#greek)           | `el` | 2      |
| [Gujarati](#gujarati)     | `gu` | 2      |
| [Indonesian](#indonesian) | `id` | 2      |
| [Kannada](#kannada)       | `kn` | 2      |
| [Malay](#malay)           | `ms` | 2      |
| [Malayalam](#malayalam)   | `ml` | 2      |
| [Marathi](#marathi)       | `mr` | 2      |
| [Norwegian](#norwegian)   | `no` | 2      |
| [Punjabi](#punjabi)       | `pa` | 2      |
| [Romanian](#romanian)     | `ro` | 2      |
| [Slovak](#slovak)         | `sk` | 2      |
| [Ukrainian](#ukrainian)   | `uk` | 1      |

## English

| Voice ID                               | Name                                | Sample                                                      | Gender    | Age   | Tone                                                                                                 | Use Case                       |
| -------------------------------------- | ----------------------------------- | ----------------------------------------------------------- | --------- | ----- | ---------------------------------------------------------------------------------------------------- | ------------------------------ |
| `39d518b7-fd0b-4676-9b8b-29d64ff31e12` | Aarav - Old Time Storyteller        | <AudioPlayer title="Aarav - Old Time Storyteller" />        | masculine | Adult | Warm adult male voice with a slight Indian accent and a vintage tone for nostalgic storytelling,…    | Voice Agents, Customer Support |
| `e2d48e7b-cd73-4c4c-bc1e-f232580e8709` | Adrian - Explorer                   | <AudioPlayer title="Adrian - Explorer" />                   | masculine | Adult | Deep American adult male voice with a curious and engaging tone for explorations, documentaries,…    | Voice Agents, Customer Support |
| `3ccc4544-84f7-45e3-ae57-5c52b5a1fac6` | Aiden - Yogi                        | <AudioPlayer title="Aiden - Yogi" />                        | masculine | Adult | Soothing voice with calm depth and gentle pacing, perfect for peaceful narrations and relaxation…    | Voice Agents, Customer Support |
| `80c81aee-b6ad-4d12-9af8-a9c79c2e141d` | Aina - Meditation Guru              | <AudioPlayer title="Aina - Meditation Guru" />              | feminine  | Adult | Calm voice with soothing balance and gentle rhythm, ideal for meditation, mindfulness, and…          | Voice Agents, Customer Support |
| `87748186-23bb-4158-a1eb-332911b0b708` | Alaric - Wizard                     | <AudioPlayer title="Alaric - Wizard" />                     | masculine | Adult | Wistful, wise, elderly male for entertainment and fun characters                                     | Voice Agents, Customer Support |
| `9a0894a9-28f0-436e-9a1d-e92bccbce4dd` | Albert - Firm Guide                 | <AudioPlayer title="Albert - Firm Guide" />                 | masculine | Adult | English male adult voice with a firm and authoritative tone for providing clear instructions and…    | Voice Agents, Customer Support |
| `50d6beb4-80ea-4802-8387-6c948fe84208` | Alfred - Cheeky Person              | <AudioPlayer title="Alfred - Cheeky Person" />              | masculine | Adult | Playful, elderly male for media and entertainment                                                    | Voice Agents, Customer Support |
| `c8f7835e-28a3-4f0c-80d7-c1302ac62aae` | Alistair - Composed Consultant      | <AudioPlayer title="Alistair - Composed Consultant" />      | masculine | Adult | Sophisticated, steady British male for customer interactions.                                        | Voice Agents, Customer Support |
| `9287676d-f0cc-423f-ac03-3b3c7242f091` | Allen - Modern Voice                | <AudioPlayer title="Allen - Modern Voice" />                | masculine | Adult | Confident young adult male voice with a neutral American accent for presentations, ads, and…         | Voice Agents, Customer Support |
| `2747b6cf-fa34-460c-97db-267566918881` | Allie - Natural Conversationalist   | <AudioPlayer title="Allie - Natural Conversationalist" />   | feminine  | Adult | Confident, approachable young adult woman for natural conversational support                         | Voice Agents, Customer Support |
| `b60048c2-abb5-43fa-b403-90dce232e55e` | Amanda - Warm Guide                 | <AudioPlayer title="Amanda - Warm Guide" />                 | feminine  | Adult | Inviting and approachable tone perfect for providing friendly guidance.                              | Voice Agents, Customer Support |
| `a7a59115-2425-4192-844c-1e98ec7d6877` | Amber - Warm Support Agent          | <AudioPlayer title="Amber - Warm Support Agent" />          | feminine  | Adult | English female adult voice with a cheerful yet deeper tone, striking a balance of warmth and…        | Voice Agents, Customer Support |
| `043cfc81-d69f-4bee-ae1e-7862cb358650` | Amelia - Instructor                 | <AudioPlayer title="Amelia - Instructor" />                 | feminine  | Adult | Strong, composed female voice suited for giving instructions with clarity and authority              | Voice Agents, Customer Support |
| `072d954b-8379-4b6b-816a-bb0cd38725f8` | Anele - Bright Presenter            | <AudioPlayer title="Anele - Bright Presenter" />            | feminine  | Adult | Clear South African female for customer service.                                                     | Voice Agents, Customer Support |
| `ec1e269e-9ca0-402f-8a18-58e0e022355a` | Ariana - Kind Friend                | <AudioPlayer title="Ariana - Kind Friend" />                | feminine  | Adult | Friendly and approachable female voice with a warm, welcoming tone that builds instant connection    | Voice Agents, Customer Support |
| `1f575487-6f3d-40e0-862a-814f55b5fb15` | Ariane - Captivating Tone           | <AudioPlayer title="Ariane - Captivating Tone" />           | feminine  | Adult | Engaging voice with expressive warmth and clarity, perfect for drawing listeners into any…           | Voice Agents, Customer Support |
| `3f04e815-3260-4f50-8fd9-af9c657be4c2` | Arvin - Reliable Guide              | <AudioPlayer title="Arvin - Reliable Guide" />              | masculine | Adult | Clear, steady male voice that communicates instructions and troubleshooting steps with…              | Voice Agents, Customer Support |
| `00967b2f-88a6-4a31-8153-110a92134b9f` | Asher - Podcaster                   | <AudioPlayer title="Asher - Podcaster" />                   | masculine | Adult | Firm adult male for audiobooks and clear communication                                               | Voice Agents, Customer Support |
| `87041166-c212-4838-9028-05d7437df750` | Aubrey - Easygoing Pal              | <AudioPlayer title="Aubrey - Easygoing Pal" />              | feminine  | Adult | Warm voice with a relaxed, natural tone that feels friendly and effortlessly relatable               | Voice Agents, Customer Support |
| `8f091740-3df1-4795-8bd9-dc62d88e5131` | Aurora - Fairy Princess             | <AudioPlayer title="Aurora - Fairy Princess" />             | feminine  | Adult | Fairy like female for character use cases in entertainment                                           | Voice Agents, Customer Support |
| `cccc21e8-5bcf-4ff0-bc7f-be4e40afc544` | Avery - Gaming Girl                 | <AudioPlayer title="Avery - Gaming Girl" />                 | feminine  | Adult | High pitched, energetic young female for animated characters and gaming and entertainment use cases  | Voice Agents, Customer Support |
| `13524ffb-a918-499a-ae97-c98c7c4408c4` | Barry - Helper                      | <AudioPlayer title="Barry - Helper" />                      | masculine | Adult | Inviting, friendly male for customer support and product videos                                      | Voice Agents, Customer Support |
| `4fb26a05-57de-4d21-855a-f51adae44f38` | Barry 2.0 - Helper                  | <AudioPlayer title="Barry 2.0 - Helper" />                  | masculine | Adult | Inviting, friendly male for customer support and product videos                                      | Voice Agents, Customer Support |
| `bbee10a8-4f08-4c5c-8282-e69299115055` | Ben - Helpful Man                   | <AudioPlayer title="Ben - Helpful Man" />                   | masculine | Adult | slightly raspy voiced middle aged man for friendly and natural conversational support                | Voice Agents, Customer Support |
| `3c0f09d6-e0d7-499c-a594-70c5b7b93048` | Benedict - Measured Mediator        | <AudioPlayer title="Benedict - Measured Mediator" />        | masculine | Adult | Polished, and formal British male.                                                                   | Voice Agents, Customer Support |
| `7cf0e2b1-8daf-4fe4-89ad-f6039398f359` | Benedict - Royal Narrator           | <AudioPlayer title="Benedict - Royal Narrator" />           | masculine | Adult | Confident, firm male for narrations                                                                  | Voice Agents, Customer Support |
| `2d5b8c3a-116c-4741-acaf-ba4fa289eba2` | Benji - Joyful Spirit               | <AudioPlayer title="Benji - Joyful Spirit" />               | masculine | Adult | Excited and cheerful voice with bright energy and lively tone, perfect for upbeat chats and…         | Voice Agents, Customer Support |
| `a167e0f3-df7e-4d52-a9c3-f949145efdab` | Blake - Helpful Agent               | <AudioPlayer title="Blake - Helpful Agent" />               | masculine | Adult | Energetic adult male for engaging customer support                                                   | Voice Agents, Customer Support |
| `5cad89c9-d88a-4832-89fb-55f2f16d13d3` | Brandon - Confident Guy             | <AudioPlayer title="Brandon - Confident Guy" />             | masculine | Adult | Confident voice with strong clarity and composed tone, perfect for persuasive and professional…      | Voice Agents, Customer Support |
| `607167f6-9bf2-473c-accc-ac7b3b66b30b` | Brenda - Host                       | <AudioPlayer title="Brenda - Host" />                       | feminine  | Adult | Cheerful, friendly female voice that creates a positive, helpful experience for customer…            | Voice Agents, Customer Support |
| `3d808d23-cb09-4c39-8afd-528e209cba4f` | Brent - Steady Conversationalist    | <AudioPlayer title="Brent - Steady Conversationalist" />    | masculine | Adult | English male adult voice with a calm, steady, and composed delivery                                  | Voice Agents, Customer Support |
| `46788d8e-cdf9-4d5c-9125-094eb2e4d44c` | Brittany - Intense Performer        | <AudioPlayer title="Brittany - Intense Performer" />        | feminine  | Adult | Strong and aggressive American-accented female voice for intense dialogue, dramatic roles, or…       | Voice Agents, Customer Support |
| `e07c00bc-4134-4eae-9ea4-1a55fb45746b` | Brooke - Big Sister                 | <AudioPlayer title="Brooke - Big Sister" />                 | feminine  | Adult | Confident adult female for conversational use cases                                                  | Voice Agents, Customer Support |
| `2948c301-9211-4112-8f36-4c3fc836ef12` | Bryce - Clear Explainer             | <AudioPlayer title="Bryce - Clear Explainer" />             | masculine | Adult | Confident voice with clear enunciation and strong delivery, ideal for professional and…              | Voice Agents, Customer Support |
| `b9cf5ec3-eaa4-46a5-a5b2-b0d0f22395a2` | Caleb - Seasoned Pro                | <AudioPlayer title="Caleb - Seasoned Pro" />                | masculine | Adult | Confident male voice with authoritative clarity, perfect for delivering expert insights and…         | Voice Agents, Customer Support |
| `da4a4eff-3b7e-4846-8f70-f075ff61222c` | Callum - Brand Spokesperson         | <AudioPlayer title="Callum - Brand Spokesperson" />         | masculine | Adult | Neutral, confident young adult male fit for voiceovers and customer interactions                     | Voice Agents, Customer Support |
| `03496517-369a-4db1-8236-3d3ae459ddf7` | Calypso - ASMR Lady                 | <AudioPlayer title="Calypso - ASMR Lady" />                 | feminine  | Adult | Soothing female for meditations and other calming use cases                                          | Voice Agents, Customer Support |
| `df872fcd-da17-4b01-a49f-a80d7aaee95e` | Cameron - Chill Companion           | <AudioPlayer title="Cameron - Chill Companion" />           | masculine | Adult | Laidback voice with a natural, conversational tone that feels friendly and easy to engage with       | Voice Agents, Customer Support |
| `55deba52-bc73-4481-ab69-9c8831c8a7c3` | Camille - Friendly Expert           | <AudioPlayer title="Camille - Friendly Expert" />           | feminine  | Adult | Calm, neutral female for customer support and instructional videos                                   | Voice Agents, Customer Support |
| `ed82c17b-4704-4d34-be43-5d19065acdf1` | Carl - Steady Storyteller           | <AudioPlayer title="Carl - Steady Storyteller" />           | masculine | Adult | Matured male voice with calm depth and measured pacing, perfect for narrations and documentaries     | Voice Agents, Customer Support |
| `1fc31370-81b1-4588-9c1a-f93793c6e01d` | Carlo - Roman Guide                 | <AudioPlayer title="Carlo - Roman Guide" />                 | masculine | Adult | Inviting, young accented male for tourism use cases                                                  | Voice Agents, Customer Support |
| `bf991597-6c13-47e4-8411-91ec2de5c466` | Carol - Task Coach                  | <AudioPlayer title="Carol - Task Coach" />                  | feminine  | Adult | Authortative, mature female for giving instructions                                                  | Voice Agents, Customer Support |
| `f9836c6e-a0bd-460e-9d3c-f7299fa60f94` | Caroline - Southern Guide           | <AudioPlayer title="Caroline - Southern Guide" />           | feminine  | Adult | Friendly, inviting, slow young adult female for conversation support                                 | Voice Agents, Customer Support |
| `0b32066b-2bcc-44b9-89ab-0223a09d1606` | Carson - Angry Friendly Support     | <AudioPlayer title="Carson - Angry Friendly Support" />     | masculine | Adult | Friendly young adult male for customer support conversations                                         | Voice Agents, Customer Support |
| `86e30c1d-714b-4074-a1f2-1cb6b552fb49` | Carson - Curious Conversationalist  | <AudioPlayer title="Carson - Curious Conversationalist" />  | masculine | Adult | Friendly young adult male for customer support conversations                                         | Voice Agents, Customer Support |
| `ee8b13e7-98af-4b15-89d1-8d402be10c94` | Carson - Disgusted Friendly Support | <AudioPlayer title="Carson - Disgusted Friendly Support" /> | masculine | Adult | Friendly young adult male for customer support conversations                                         | Voice Agents, Customer Support |
| `4df027cb-2920-4a1f-8c34-f21529d5c3fe` | Carson - Friendly Support           | <AudioPlayer title="Carson - Friendly Support" />           | masculine | Adult | Friendly, young adult male for customer support conversations                                        | Voice Agents, Customer Support |
| `96c64eb5-a945-448f-9710-980abe7a514c` | Carson - Friendly Support           | <AudioPlayer title="Carson - Friendly Support" />           | masculine | Adult | Friendly, young adult male for customer support conversations                                        | Voice Agents, Customer Support |
| `3246e36c-ac8c-418d-83cd-4eaad5a3b887` | Carson - Sad Friendly Support       | <AudioPlayer title="Carson - Sad Friendly Support" />       | masculine | Adult | Friendly young adult male for customer support conversations                                         | Voice Agents, Customer Support |
| `5c43e078-5ba4-4e1f-9639-8d85a403f76a` | Carson - Scared Friendly Support    | <AudioPlayer title="Carson - Scared Friendly Support" />    | masculine | Adult | Friendly young adult male for customer support conversations                                         | Voice Agents, Customer Support |
| `66f5935b-af2e-4ec9-bb3e-59112e9ddc93` | Carson - Surprised Friendly Support | <AudioPlayer title="Carson - Surprised Friendly Support" /> | masculine | Adult | Friendly young adult male for customer support conversations                                         | Voice Agents, Customer Support |
| `4f7f1324-1853-48a6-b294-4e78e8036a83` | Casper - Gentle Narrator            | <AudioPlayer title="Casper - Gentle Narrator" />            | masculine | Adult | Wistful, young male for emotional narrations                                                         | Voice Agents, Customer Support |
| `d7862948-75c3-4c7c-ae28-2959fe166f49` | Caspian - Oracle                    | <AudioPlayer title="Caspian - Oracle" />                    | masculine | Adult | Echo-y, mystical male for characters with gravitas                                                   | Voice Agents, Customer Support |
| `e8e5fffb-252c-436d-b842-8879b84445b6` | Cathy - Coworker                    | <AudioPlayer title="Cathy - Coworker" />                    | feminine  | Adult | Nice, young adult female for casual conversations                                                    | Voice Agents, Customer Support |
| `ca566b43-944e-4474-b494-7d9f0695f307` | Celine - Soothing Presence          | <AudioPlayer title="Celine - Soothing Presence" />          | feminine  | Adult | Relaxed voice with smooth tone and gentle warmth, ideal for calm conversations and easy listening    | Voice Agents, Customer Support |
| `3af40927-948e-429b-b92d-e2158f79fb9f` | Cera - Lighthearted Muse            | <AudioPlayer title="Cera - Lighthearted Muse" />            | feminine  | Adult | Casual female voice with an easy, conversational flow that feels natural and friendly                | Voice Agents, Customer Support |
| `356f4a89-d056-4e2e-8c73-865fa4d3af0a` | Chandler - Easygoing Pal            | <AudioPlayer title="Chandler - Easygoing Pal" />            | masculine | Adult | Casual male voice with a warm, natural tone that feels friendly and effortlessly relatable           | Voice Agents, Customer Support |
| `ec58877e-44ae-4581-9078-a04225d42bd4` | Charles - Heroic Man                | <AudioPlayer title="Charles - Heroic Man" />                | masculine | Adult | Very deep, adult male for characters that embody strength and determination                          | Voice Agents, Customer Support |
| `71a7ad14-091c-4e8e-a314-022ece01c121` | Charlotte - Heiress                 | <AudioPlayer title="Charlotte - Heiress" />                 | feminine  | Adult | Elegant, young adult female for narrations                                                           | Voice Agents, Customer Support |
| `f762e181-ddc7-486e-9a48-636bd7e229d4` | Chloe - Persuasive Lady             | <AudioPlayer title="Chloe - Persuasive Lady" />             | feminine  | Adult | English female adult voice with a confident and persuasive tone, able to influence and engage…       | Voice Agents, Customer Support |
| `1242fb95-7ddd-44ac-8a05-9e8a22a6137d` | Cindy - Receptionist                | <AudioPlayer title="Cindy - Receptionist" />                | feminine  | Adult | Smooth, welcoming adult female for frontline customer interactions                                   | Voice Agents, Customer Support |
| `f039066f-cdb7-45ed-b51d-1034ae2f04a0` | Cindy Baker - Receptionist          | <AudioPlayer title="Cindy Baker - Receptionist" />          | feminine  | Adult | Smooth, welcoming adult female for frontline customer interactions                                   | Voice Agents, Customer Support |
| `15a9cd88-84b0-4a8b-95f2-5d583b54c72e` | Claire - Storyteller                | <AudioPlayer title="Claire - Storyteller" />                | feminine  | Adult | Soothing, neutral female for narrations                                                              | Voice Agents, Customer Support |
| `01eaafa9-308a-4276-a017-6ab0cf061b1f` | Clara - Instructor                  | <AudioPlayer title="Clara - Instructor" />                  | feminine  | Adult | Middle-aged American female voice with a clear tone and precise enunciation for instructions,…       | Voice Agents, Customer Support |
| `41534e16-2966-4c6b-9670-111411def906` | Clarence - Newsman                  | <AudioPlayer title="Clarence - Newsman" />                  | masculine | Adult | Firm, deep male with old time radio like acoustics for 20th century historical reenactments          | Voice Agents, Customer Support |
| `c78dd7ae-6692-4c44-a2a2-834e365afe60` | Clark - Trustworthy Expert          | <AudioPlayer title="Clark - Trustworthy Expert" />          | masculine | Adult | Approachable male voice with a confident, knowledgeable tone ideal for customer service and support  | Voice Agents, Customer Support |
| `c0f43c66-9f21-4034-b485-8f1d3340d759` | Clarkson - Executive Tone           | <AudioPlayer title="Clarkson - Executive Tone" />           | masculine | Adult | Businesslike voice with confident tone and professional delivery, perfect for corporate and…         | Voice Agents, Customer Support |
| `f80e7298-93f5-46d0-86f2-b8f29cfc88bd` | Claudia - Welcoming Lady            | <AudioPlayer title="Claudia - Welcoming Lady" />            | feminine  | Adult | Friendly, calm young adult female for casual conversations                                           | Voice Agents, Customer Support |
| `db69127a-dbaf-4fa9-b425-2fe67680c348` | Clint - Rugged Actor                | <AudioPlayer title="Clint - Rugged Actor" />                | masculine | Adult | Raspy voice with rugged tone, perfect for voice acting and dramatic narration                        | Voice Agents, Customer Support |
| `98a34ef2-2140-4c28-9c71-663dc4dd7022` | Clyde - Calm Narrator               | <AudioPlayer title="Clyde - Calm Narrator" />               | masculine | Adult | Gentle, measured male voice with warmth and clarity for storytelling and informative reads           | Voice Agents, Customer Support |
| `18f8d87b-0da9-4efa-b504-4580e303f7db` | Colby - Lively Guy                  | <AudioPlayer title="Colby - Lively Guy" />                  | masculine | Adult | Casual voice with an engaging, upbeat tone that brings energy and friendliness to any conversation   | Voice Agents, Customer Support |
| `3e39e9a5-585c-4f5f-bac6-5e4905c51095` | Cole - Clear Communicator           | <AudioPlayer title="Cole - Clear Communicator" />           | masculine | Adult | Articulate, approachable male designed for friendly communication.                                   | Voice Agents, Customer Support |
| `e39b9fc0-23f5-4616-962a-da99c8ccb1dc` | Colin - Assured Guide               | <AudioPlayer title="Colin - Assured Guide" />               | masculine | Adult | Confident voice with clear articulation and reassuring tone, ideal for professional and customer…    | Voice Agents, Customer Support |
| `8d8ce8c9-44a4-46c4-b10f-9a927b99a853` | Connie - Candid Conversationalist   | <AudioPlayer title="Connie - Candid Conversationalist" />   | feminine  | Adult | Natural, cheery young adult female for authentic conversations                                       | Voice Agents, Customer Support |
| `92c41dd4-04aa-45de-8504-a92b40cb8818` | Connor - Grateful Person            | <AudioPlayer title="Connor - Grateful Person" />            | masculine | Adult | Expressive American adult male voice with a grateful yet firm tone for speeches, storytelling,…      | Voice Agents, Customer Support |
| `1ec736fa-db96-4eea-9299-235ce2cb7a0e` | Conor - Decisive Agent              | <AudioPlayer title="Conor - Decisive Agent" />              | masculine | Adult | Decisive Irish male for straightforward customer communication.                                      | Voice Agents, Customer Support |
| `9c8880b2-ccf9-4730-b805-cea23df247d7` | Conrad - Seasoned Support           | <AudioPlayer title="Conrad - Seasoned Support" />           | masculine | Adult | Mature, confident voice with composed authority and clear tone, perfect for professional or…         | Voice Agents, Customer Support |
| `49743b08-0f5d-4741-839c-b12933853780` | Cooper - Friendly Mate              | <AudioPlayer title="Cooper - Friendly Mate" />              | masculine | Adult | Warm and highly relatable, excellent for customer service.                                           | Voice Agents, Customer Support |
| `41468051-3a85-4b68-92ad-64add250d369` | Cory - Relaxed Voice                | <AudioPlayer title="Cory - Relaxed Voice" />                | masculine | Adult | Casual male voice with a friendly, easygoing tone that feels natural and approachable                | Voice Agents, Customer Support |
| `32b3f3c5-7171-46aa-abe7-b598964aa793` | Daisy - Reading Girl                | <AudioPlayer title="Daisy - Reading Girl" />                | feminine  | Adult | Very young female for children's book narrations and young animated personas                         | Voice Agents, Customer Support |
| `23e9e50a-4ea2-447b-b589-df90dbb848a2` | Dallas - Fireside Friend            | <AudioPlayer title="Dallas - Fireside Friend" />            | masculine | Adult | Kind male for inviting and authentic conversations                                                   | Voice Agents, Customer Support |
| `dbfa416f-d5c3-4006-854b-235ef6bdf4fd` | Damon - Commanding Narrator         | <AudioPlayer title="Damon - Commanding Narrator" />         | masculine | Adult | Deep and serious male voice with steady gravitas, ideal for documentaries and impactful storytelling | Voice Agents, Customer Support |
| `cc00e582-ed66-4004-8336-0175b85c85f6` | Dana - Balanced Spirit              | <AudioPlayer title="Dana - Balanced Spirit" />              | feminine  | Adult | Neutral female voice with clear articulation and calm tone, ideal for versatile conversational…      | Voice Agents, Customer Support |
| `47c38ca4-5f35-497b-b1a3-415245fb35e1` | Daniel - Modern Assistant           | <AudioPlayer title="Daniel - Modern Assistant" />           | masculine | Adult | Clear, crisp male voice for digital assistants and system interactions                               | Voice Agents, Customer Support |
| `09ed0318-2f4a-41b1-abe5-d11da7537c31` | Daphne - Excited Woman              | <AudioPlayer title="Daphne - Excited Woman" />              | feminine  | Adult | Expressive and upbeat American-accented female voice with an exciting tone for ads,…                 | Voice Agents, Customer Support |
| `23112795-d54e-4560-9568-791a87c30201` | Darius - Engaging Narrator          | <AudioPlayer title="Darius - Engaging Narrator" />          | masculine | Adult | Husky matured male voice with rich texture and commanding tone, ideal for engaging story telling…    | Voice Agents, Customer Support |
| `996a8b96-4804-46f0-8e05-3fd4ef1a87cd` | Darla - Resolution Agent            | <AudioPlayer title="Darla - Resolution Agent" />            | feminine  | Adult | Firm and confident female voice with a calm, supportive tone - ideal for customer support roles      | Voice Agents, Customer Support |
| `8d110413-2f14-44a2-8203-2104db4340e9` | Darren - Friendly Barritone         | <AudioPlayer title="Darren - Friendly Barritone" />         | masculine | Adult | Deep, friendly adult male for happy voiceovers                                                       | Voice Agents, Customer Support |
| `fd098a10-ba9e-445e-b144-be2a9f3dac02` | David - Angry Greeter               | <AudioPlayer title="David - Angry Greeter" />               | masculine | Adult | Engaging adult male for advertising and upbeat conversations                                         | Voice Agents, Customer Support |
| `b08c966e-2146-4592-99eb-3171a714a43c` | David - Curious Greeter             | <AudioPlayer title="David - Curious Greeter" />             | masculine | Adult | Engaging adult male for advertising and upbeat conversations                                         | Voice Agents, Customer Support |
| `9d2b4a7f-7ced-4fb8-b570-9ce21fb931c8` | David - Disgusted Greeter           | <AudioPlayer title="David - Disgusted Greeter" />           | masculine | Adult | Engaging adult male for advertising and upbeat conversations                                         | Voice Agents, Customer Support |
| `da69d796-4603-4419-8a95-293bfc5679eb` | David - Greeter                     | <AudioPlayer title="David - Greeter" />                     | masculine | Adult | Engaging adult male for advertising and upbeat conversations                                         | Voice Agents, Customer Support |
| `6b622a1d-906f-44af-b60c-7bef365bf124` | David - Happy Greeter               | <AudioPlayer title="David - Happy Greeter" />               | masculine | Adult | Engaging adult male for advertising and upbeat conversations                                         | Voice Agents, Customer Support |
| `c4e848dc-d4fd-4bc8-90ea-8525563ec0e5` | David - Sad Greeter                 | <AudioPlayer title="David - Sad Greeter" />                 | masculine | Adult | Engaging adult male for advertising and upbeat conversations                                         | Voice Agents, Customer Support |
| `a3a4fe2a-d402-41d1-be7d-28f71eda755f` | David - Scared Greeter              | <AudioPlayer title="David - Scared Greeter" />              | masculine | Adult | Engaging adult male for advertising and upbeat conversations                                         | Voice Agents, Customer Support |
| `10d17ae0-8f64-472a-be00-f00a98c729e0` | David - Surprised Greeter           | <AudioPlayer title="David - Surprised Greeter" />           | masculine | Adult | Engaging adult male for advertising and upbeat conversations                                         | Voice Agents, Customer Support |
| `90c896fa-aaa1-41af-a612-5267636440a3` | Dean - Laidback Pal                 | <AudioPlayer title="Dean - Laidback Pal" />                 | masculine | Adult | Casual male voice with a relaxed, natural tone that feels easy to listen to and effortlessly genuine | Voice Agents, Customer Support |
| `8a1b8af0-c4f6-423f-a268-5507fd4aefdf` | Denise - Professional Woman         | <AudioPlayer title="Denise - Professional Woman" />         | feminine  | Adult | Professional female voice with confident clarity and polished tone, ideal for corporate and…         | Voice Agents, Customer Support |
| `5cf0e4d9-ca2b-4fd5-81fa-89db3b645539` | Derrick - Professional Man          | <AudioPlayer title="Derrick - Professional Man" />          | masculine | Adult | No-nonsense voice with steady confidence and clear tone, ideal for customer service and tech support | Voice Agents, Customer Support |
| `1259b7e3-cb8a-43df-9446-30971a46b8b0` | Devansh - Warm Support Agent        | <AudioPlayer title="Devansh - Warm Support Agent" />        | masculine | Adult | Warm, conversational Indian male adult voice for casual chats, everyday interactions, and…           | Voice Agents, Customer Support |
| `87a983d8-3471-4c4b-9ade-f1d10a4110ac` | Devin - Relaxed Spirit              | <AudioPlayer title="Devin - Relaxed Spirit" />              | masculine | Adult | Laidback male voice with a smooth, easygoing tone that feels relaxed and effortlessly cool.          | Voice Agents, Customer Support |
| `083de431-6b5c-4b18-a2dc-264eafa205f2` | Diana - Animated Narrator           | <AudioPlayer title="Diana - Animated Narrator" />           | feminine  | Adult | Chirpy matured female voice with expressive warmth and lively cadence, perfect for engaging…         | Voice Agents, Customer Support |
| `ea93f57f-7c71-4d79-aeaa-0a39b150f6ca` | Diana - Gentle Mom                  | <AudioPlayer title="Diana - Gentle Mom" />                  | feminine  | Adult | Matured voice with a casual, friendly tone that feels warm, relatable, and easy to connect with      | Voice Agents, Customer Support |
| `a8136a0c-9642-497a-882d-8d591bdcb2fa` | Diane - Service Assistant           | <AudioPlayer title="Diane - Service Assistant" />           | feminine  | Adult | Firm, mature adult female for customer support use cases                                             | Voice Agents, Customer Support |
| `59697755-8cfb-4ccf-9da4-f2201d06b067` | Dominic - Sportscaster              | <AudioPlayer title="Dominic - Sportscaster" />              | masculine | Adult | Strong voice with commanding projection and energetic tone, perfect for sports commentary and…       | Voice Agents, Customer Support |
| `d709a7e8-9495-4247-aef0-01b3207d11bf` | Donny - Steady Presence             | <AudioPlayer title="Donny - Steady Presence" />             | masculine | Adult | Neutral male voice with balanced tone and clarity, adaptable for a wide range of casual speaking…    | Voice Agents, Customer Support |
| `586b6832-1ca1-43ad-b974-527dc13c2532` | Dorian - Director                   | <AudioPlayer title="Dorian - Director" />                   | masculine | Adult | Welcoming male for providing instructions and guidance                                               | Voice Agents, Customer Support |
| `0c8ed86e-6c64-40f0-b252-b773911de6bb` | Doris - Friend                      | <AudioPlayer title="Doris - Friend" />                      | feminine  | Adult | Warm and relatable female voice suited for casual, natural conversations                             | Voice Agents, Customer Support |
| `66c6b81c-ddb7-4892-bdd5-19b5a7be38e7` | Dorothy - Easy Charm                | <AudioPlayer title="Dorothy - Easy Charm" />                | feminine  | Adult | Casual female voice with a relaxed and natural tone, perfect for everyday conversations and…         | Voice Agents, Customer Support |
| `e3827ec5-697a-4b7c-9704-1a23041bbc51` | Dottie - Sweet Gal                  | <AudioPlayer title="Dottie - Sweet Gal" />                  | feminine  | Adult | High pitched, earnest, very young female for character narrations for children                       | Voice Agents, Customer Support |
| `b2222537-1561-4425-8c3c-e1aca96ad853` | Dylan - Chill Companion             | <AudioPlayer title="Dylan - Chill Companion" />             | masculine | Adult | Casual male voice with an easy, conversational tone that feels friendly and down-to-earth            | Voice Agents, Customer Support |
| `c8605446-247c-4d39-acd4-8f4c28aa363c` | Edith - Matriarch                   | <AudioPlayer title="Edith - Matriarch" />                   | feminine  | Adult | Elderly, confident female for narrations and wise characters                                         | Voice Agents, Customer Support |
| `19e399df-5b30-4fba-9d1d-99434f993614` | Edna - Graceful Veteran             | <AudioPlayer title="Edna - Graceful Veteran" />             | feminine  | Adult | Matured female voice with gentle wisdom and poise, perfect for thoughtful narration and…             | Voice Agents, Customer Support |
| `921034a2-aace-4ef7-87b1-b9bc455c9a15` | Edric - Refined Mentor              | <AudioPlayer title="Edric - Refined Mentor" />              | masculine | Adult | Matured male voice with steady pacing and clear intonation, delivering messages with poise and…      | Voice Agents, Customer Support |
| `5fb68a42-0ed7-46fa-8a8f-ad4b332fbf6f` | Edward - Persuasive Promoter        | <AudioPlayer title="Edward - Persuasive Promoter" />        | masculine | Adult | Confident voice with clarity and persuasive tone, perfect for advertisements and promotional content | Voice Agents, Customer Support |
| `f0377496-2708-4cc9-b2f8-1b7fdb5e1a2a` | Elaine - Confident Guide            | <AudioPlayer title="Elaine - Confident Guide" />            | feminine  | Adult | Assured voice with calm confidence and clear tone, ideal for professional, informative, or…          | Voice Agents, Customer Support |
| `7d7d769c-5ab1-4dd5-bb17-ec8d4b69d03d` | Eleanor - Composed Clarifier        | <AudioPlayer title="Eleanor - Composed Clarifier" />        | feminine  | Adult | Clear, professional adult female for customer communication                                          | Voice Agents, Customer Support |
| `6a176356-ada1-4b48-b2ae-3a3fdd485680` | Elias - Night Warden                | <AudioPlayer title="Elias - Night Warden" />                | masculine | Adult | Deep male for entertainment and gaming characters                                                    | Voice Agents, Customer Support |
| `7a8ae0b6-504a-49af-92d3-4e7e2eb84ca1` | Eliott - Positive Spirit            | <AudioPlayer title="Eliott - Positive Spirit" />            | masculine | Adult | Approachable and cheerful voice with bright warmth that instantly connects and uplifts listeners     | Voice Agents, Customer Support |
| `64b2a604-f0de-449f-9d90-255602357c05` | Elise - Helpful Voice               | <AudioPlayer title="Elise - Helpful Voice" />               | feminine  | Adult | Casual female voice with a smooth, approachable tone that feels effortless and natural in…           | Voice Agents, Customer Support |
| `248be419-c632-4f23-adf1-5324ed7dbf1d` | Elizabeth - Manager                 | <AudioPlayer title="Elizabeth - Manager" />                 | feminine  | Adult | Enunicating young female for providing guidance and instructions                                     | Voice Agents, Customer Support |
| `5c9e800f-2a92-4720-969b-99c4ab8fbc87` | Ellen - Welcome Agent               | <AudioPlayer title="Ellen - Welcome Agent" />               | feminine  | Adult | Authentic female voice with balanced warmth and clarity for both casual and support-driven contexts  | Voice Agents, Customer Support |
| `8d2c9eda-31df-477a-9eb6-df6f00b82845` | Ellie Mae - Friendly Companion      | <AudioPlayer title="Ellie Mae - Friendly Companion" />      | feminine  | Adult | Bright, approachable Southern female that feels like a trusted neighbor.                             | Voice Agents, Customer Support |
| `7edf9efb-58fc-46ba-a648-3a00a86b111b` | Elliott - Reflective Storyteller    | <AudioPlayer title="Elliott - Reflective Storyteller" />    | masculine | Adult | English male adult voice with a soft, melancholic tone and a questioning inflection for…             | Voice Agents, Customer Support |
| `f6ce3444-478b-4ce4-982e-bcb72dffe7aa` | Emily - Easygoing Pal               | <AudioPlayer title="Emily - Easygoing Pal" />               | feminine  | Adult | Cheerful voice with warm and welcoming tone that feels natural and easy to connect with              | Voice Agents, Customer Support |
| `f6ff7c0c-e396-40a9-a70b-f7607edb6937` | Emma - Customer Care Line           | <AudioPlayer title="Emma - Customer Care Line" />           | feminine  | Adult | Casual adult female for natural conversations and customer support                                   | Voice Agents, Customer Support |
| `8918ddfe-2ad4-4cc8-a573-e020ca13f3f5` | Erin - Joyful Guide                 | <AudioPlayer title="Erin - Joyful Guide" />                 | feminine  | Adult | Cheerful and optimistic adult female voice for upbeat conversations, advertisements, and…            | Voice Agents, Customer Support |
| `3c7dfd17-3fa8-47aa-aacc-6313fe025442` | Evelyn - Digital Assistante         | <AudioPlayer title="Evelyn - Digital Assistante" />         | feminine  | Adult | A clear, neutral, and precise female voice with a smooth digital polish - perfect for…               | Voice Agents, Customer Support |
| `320f7211-3dc3-4292-89b1-3661e8cac27c` | Evelyn - Peaceful Whisper           | <AudioPlayer title="Evelyn - Peaceful Whisper" />           | feminine  | Adult | Calm voice with soft warmth and gentle pacing, ideal for soothing narrations and ASMR                | Voice Agents, Customer Support |
| `e5d4c33a-d8f6-46e8-a10f-b5afecc35648` | Evie - Engaging Expert              | <AudioPlayer title="Evie - Engaging Expert" />              | feminine  | Adult | Formal British female for high-level corporate interactions.                                         | Voice Agents, Customer Support |
| `a01c369f-6d2d-4185-bc20-b32c225eab70` | Fiona - Witty Woman                 | <AudioPlayer title="Fiona - Witty Woman" />                 | feminine  | Adult | Chirpy and energetic British female voice with a bright tone, great for lively and engaging…         | Voice Agents, Customer Support |
| `236bb1fb-dc41-4a2b-84d6-d22d2a2aaae1` | Franklin - Old Time Radio Host      | <AudioPlayer title="Franklin - Old Time Radio Host" />      | masculine | Adult | Elderly man speaking over a crackling 20th century radio for historical reenactments                 | Voice Agents, Customer Support |
| `c58bda25-abd5-4c72-97a2-4dbe049b368d` | Garrett - Enthusiastic Pal          | <AudioPlayer title="Garrett - Enthusiastic Pal" />          | masculine | Adult | Upbeat voice with bright energy and confident tone, perfect for lively conversations and…            | Voice Agents, Customer Support |
| `f4a3a8e4-694c-4c45-9ca0-27caf97901b5` | Gavin - Friendly Vibe               | <AudioPlayer title="Gavin - Friendly Vibe" />               | masculine | Adult | Casual male voice with a relaxed, conversational tone that feels approachable and genuine            | Voice Agents, Customer Support |
| `62ae83ad-4f6a-430b-af41-a9bede9286ca` | Gemma - Decisive Agent              | <AudioPlayer title="Gemma - Decisive Agent" />              | feminine  | Adult | Confident, emotive British female for professional assistance                                        | Voice Agents, Customer Support |
| `4bc3cb8c-adb9-4bb8-b5d5-cbbef950b991` | George - Composed Consultant        | <AudioPlayer title="George - Composed Consultant" />        | masculine | Adult | Steady, British male voice for capable assistance.                                                   | Voice Agents, Customer Support |
| `36b42fcb-60c5-4bec-b077-cb1a00a92ec6` | Gordon - Pilot                      | <AudioPlayer title="Gordon - Pilot" />                      | masculine | Adult | Male, simulating the acoustics over an intercom, for entertainment use cases                         | Voice Agents, Customer Support |
| `a4a16c5e-5902-4732-b9b6-2a48efd2e11b` | Grace - Helpful Hand                | <AudioPlayer title="Grace - Helpful Hand" />                | feminine  | Adult | Polished, bright Australian female for friendly professional assistance.                             | Voice Agents, Customer Support |
| `1628cfcd-a161-4e47-98ff-46bffa4ab290` | Graham - Assured Helper             | <AudioPlayer title="Graham - Assured Helper" />             | masculine | Adult | Confident male voice with a clear, reassuring tone, perfect for professional and customer…           | Voice Agents, Customer Support |
| `d46abd1d-2d02-43e8-819f-51fb652c1c61` | Grant - Friendly Support            | <AudioPlayer title="Grant - Friendly Support" />            | masculine | Adult | Reliable, clear male voice with neutral American accent for customer support interactions            | Voice Agents, Customer Support |
| `a0e99841-438c-4a64-b679-ae501e7d6091` | Greg - Supporter                    | <AudioPlayer title="Greg - Supporter" />                    | masculine | Adult | Neutral, deep male for conversational support                                                        | Voice Agents, Customer Support |
| `34d923aa-c3b5-4f21-aac7-2c1f12730d4b` | Griffin - Excited Narrator          | <AudioPlayer title="Griffin - Excited Narrator" />          | masculine | Adult | Elderly male for narrations                                                                          | Voice Agents, Customer Support |
| `c99d36f3-5ffd-4253-803a-535c1bc9c306` | Griffin - Narrator                  | <AudioPlayer title="Griffin - Narrator" />                  | masculine | Adult | Elderly male for narrations                                                                          | Voice Agents, Customer Support |
| `cec7cae1-ac8b-4a59-9eac-ec48366f37ae` | Haley - Engaging Friend             | <AudioPlayer title="Haley - Engaging Friend" />             | feminine  | Adult | Casual female voice with a relaxed, friendly tone that feels natural and easy to engage with         | Voice Agents, Customer Support |
| `a892d232-f705-40d7-bc8d-e368b295ec2a` | Harlan - Vintage Tone               | <AudioPlayer title="Harlan - Vintage Tone" />               | masculine | Adult | Deep male voice with classic resonance and smooth authority, reminiscent of an old radio announcer   | Voice Agents, Customer Support |
| `fdf6303b-4cfa-4f8e-b7ae-acb398984cf9` | Harley - Comforting Voice           | <AudioPlayer title="Harley - Comforting Voice" />           | masculine | Adult | Casual voice with a relaxed, natural tone that feels approachable and genuine                        | Voice Agents, Customer Support |
| `c5d00dfb-501f-43f3-8e79-c810d24f5acd` | Harper - Conversationalist          | <AudioPlayer title="Harper - Conversationalist" />          | feminine  | Adult | Adult female for highly structured communication.                                                    | Voice Agents, Customer Support |
| `df89f42f-f285-4613-adbf-14eedcec4c9e` | Harrison - Diligent Detailer        | <AudioPlayer title="Harrison - Diligent Detailer" />        | masculine | Adult | Crisp, professional British male for efficient customer interactions.                                | Voice Agents, Customer Support |
| `3dcaa773-fb1a-47f7-82a4-1bf756c4e1fb` | Harry - Service Advisor             | <AudioPlayer title="Harry - Service Advisor" />             | masculine | Adult | Seasoned male for friendly conversation and customer support                                         | Voice Agents, Customer Support |
| `87286a8d-7ea7-4235-a41a-dd9fa6630feb` | Henry - Plainspoken Guy             | <AudioPlayer title="Henry - Plainspoken Guy" />             | masculine | Adult | A relaxed, youthful male voice with a monotone, matter-of-fact attitude - ideal for casual,…         | Voice Agents, Customer Support |
| `aef96ff9-4578-4b5d-9744-7fb347cbe4d4` | Holly - Joyful Presence             | <AudioPlayer title="Holly - Joyful Presence" />             | feminine  | Adult | Cheerful voice with bright warmth and friendly energy, perfect for engaging conversations and…       | Voice Agents, Customer Support |
| `0d42f0f6-c019-4082-b250-1c16133d1c82` | Howard - Approachable Man           | <AudioPlayer title="Howard - Approachable Man" />           | masculine | Adult | Male adult voice with a clear, approachable tone and steady delivery                                 | Voice Agents, Customer Support |
| `4cf80313-54dc-4ca9-a17c-3e5b8f68a78c` | Hugh - Confident Veteran            | <AudioPlayer title="Hugh - Confident Veteran" />            | masculine | Adult | Seasoned male voice with rich character and charisma, great for lively ads and engaging…             | Voice Agents, Customer Support |
| `1463a4e1-56a1-4b41-b257-728d56e93605` | Hugo - Teatime Friend               | <AudioPlayer title="Hugo - Teatime Friend" />               | masculine | Adult | Expressive, young adult male for characters and natural conversation                                 | Voice Agents, Customer Support |
| `eef47c0d-cb49-4160-a4a0-6b97ed4c81e6` | Isla - Serene Flow                  | <AudioPlayer title="Isla - Serene Flow" />                  | feminine  | Adult | Calm voice with gentle warmth and steady rhythm, perfect for yoga, meditation, and relaxation        | Voice Agents, Customer Support |
| `6776173b-fd72-460d-89b3-d85812ee518d` | Jace - Cool Conversationalist       | <AudioPlayer title="Jace - Cool Conversationalist" />       | masculine | Adult | Friendly and chill male voice with an easygoing tone that feels relaxed and natural                  | Voice Agents, Customer Support |
| `9626c31c-bec5-4cca-baa8-f8ba9e84c8bc` | Jacqueline - Reassuring Agent       | <AudioPlayer title="Jacqueline - Reassuring Agent" />       | feminine  | Adult | Confident, young adult female for empathic customer support                                          | Voice Agents, Customer Support |
| `729651dc-c6c3-4ee5-97fa-350da1f88600` | Jake - Sidekick                     | <AudioPlayer title="Jake - Sidekick" />                     | masculine | Adult | Friendly, young adult male for welcoming and engaging conversations                                  | Voice Agents, Customer Support |
| `42b39f37-515f-4eee-8546-73e841679c1d` | James - Navigator                   | <AudioPlayer title="James - Navigator" />                   | masculine | Adult | Very deep, authoritative male for providing guidance and instruction                                 | Voice Agents, Customer Support |
| `a5136bf9-224c-4d76-b823-52bd5efcffcc` | Jameson - Easygoing Support         | <AudioPlayer title="Jameson - Easygoing Support" />         | masculine | Adult | Friendly, laid-back male voice for customer support and onboarding                                   | Voice Agents, Customer Support |
| `b5c1bab5-f036-481f-9295-4db6f06f6443` | Jamie - Comforting Presence         | <AudioPlayer title="Jamie - Comforting Presence" />         | feminine  | Adult | Casual voice with a warm, friendly tone that feels like chatting with a close friend                 | Voice Agents, Customer Support |
| `2a17e905-8f14-4db7-9b9d-9223a8e3f278` | Jane - Digital Guide                | <AudioPlayer title="Jane - Digital Guide" />                | feminine  | Adult | A crisp, modern voice with a friendly, intelligent tone — great for virtual-assistant tasks,…        | Voice Agents, Customer Support |
| `58fbaf73-d7de-4e82-a6b3-118180e7057c` | Janet - Sunny Speaker               | <AudioPlayer title="Janet - Sunny Speaker" />               | feminine  | Adult | Bright, warm female voice for guidance, narration, and supportive interactions                       | Voice Agents, Customer Support |
| `69092565-1c93-4a88-9f2c-ac8cddaf9f65` | Janice - Engaging Tone              | <AudioPlayer title="Janice - Engaging Tone" />              | feminine  | Adult | Engaging voice with a casual, friendly tone that draws listeners in and keeps conversations lively   | Voice Agents, Customer Support |
| `7ea5e9c2-b719-4dc3-b870-5ba5f14d31d8` | Janvi - Steady Agent                | <AudioPlayer title="Janvi - Steady Agent" />                | feminine  | Adult | Calm and neutral female voice with a slow, steady delivery, ideal for customer support scenarios     | Voice Agents, Customer Support |
| `3faa81ae-d3d8-4ab1-9e44-e50e46d33c30` | Jasper - Service Specialist         | <AudioPlayer title="Jasper - Service Specialist" />         | masculine | Adult | Warm, expressive voice for customer support and sales conversations                                  | Voice Agents, Customer Support |
| `6cb8801d-259a-4bdc-978f-b45808d58cd3` | Jeremy - Energetic Promoter         | <AudioPlayer title="Jeremy - Energetic Promoter" />         | masculine | Adult | High energy voice with clear and engaging tone, perfect for advertisements and promotions            | Voice Agents, Customer Support |
| `25d7abcb-4d6d-4aca-adce-8a1c85620c8b` | Jessica - Clear Communicator        | <AudioPlayer title="Jessica - Clear Communicator" />        | feminine  | Adult | Crisp and articulate delivery designed for seamless information sharing.                             | Voice Agents, Customer Support |
| `bbc5d060-50e1-45a3-87ff-191b8cea3092` | Jett - Helpful Pal                  | <AudioPlayer title="Jett - Helpful Pal" />                  | masculine | Adult | Casual male voice with an easygoing rhythm and friendly tone that feels natural and relatable        | Voice Agents, Customer Support |
| `f39d8500-0d9b-4b8b-a080-38f5188f5892` | Jewel - Commercial Announcer        | <AudioPlayer title="Jewel - Commercial Announcer" />        | feminine  | Adult | Smooth, confident, and engaging female voice for advertising, promos, and high-impact brand…         | Voice Agents, Customer Support |
| `e4d5f4c4-6601-4779-bee1-b3c14d629dc6` | Jillian - Happy Spirit              | <AudioPlayer title="Jillian - Happy Spirit" />              | feminine  | Adult | Cheerful voice with lively warmth and friendly tone, perfect for upbeat conversations                | Voice Agents, Customer Support |
| `5abd2130-146a-41b1-bcdb-974ea8e19f56` | Jo - Go to Gal                      | <AudioPlayer title="Jo - Go to Gal" />                      | feminine  | Adult | Young adult female for casual conversations                                                          | Voice Agents, Customer Support |
| `c9440d34-5641-427b-bbb7-80ef7462576d` | Joan - Messenger                    | <AudioPlayer title="Joan - Messenger" />                    | feminine  | Adult | Young adult female for casual conversations                                                          | Voice Agents, Customer Support |
| `a7b8d8fa-f6e5-4908-900e-0c11d1d82519` | Joanie - Vibrant Speaker            | <AudioPlayer title="Joanie - Vibrant Speaker" />            | feminine  | Adult | Upbeat matured female voice with lively warmth and confidence, perfect for natural and engaging…     | Voice Agents, Customer Support |
| `34575e71-908f-4ab6-ab54-b08c95d6597d` | Joey - Neighborhood Guy             | <AudioPlayer title="Joey - Neighborhood Guy" />             | masculine | Adult | Casual, friendly male for natural conversations                                                      | Voice Agents, Customer Support |
| `d1d9c946-7cfc-4378-85a4-07d09827cb7e` | Jolene - Warm Storyteller           | <AudioPlayer title="Jolene - Warm Storyteller" />           | feminine  | Adult | Rich, honeyed Southern female perfect for narration.                                                 | Voice Agents, Customer Support |
| `7d444628-dd13-442b-b687-71a6baf0c07e` | Joseph - Empathetic Voice           | <AudioPlayer title="Joseph - Empathetic Voice" />           | masculine | Adult | Gentle and reassuring tone designed to offer comfort and build trust.                                | Voice Agents, Customer Support |
| `4d3d2e9c-14e4-4802-a8d8-bd5268a73fde` | Judith - Poised Strength            | <AudioPlayer title="Judith - Poised Strength" />            | feminine  | Adult | Confident voice with clear articulation and composed tone, perfect for presentations and…            | Voice Agents, Customer Support |
| `5319c0b1-3dd1-4c00-b721-bfd2ec88ef56` | Julian - Vibrant Voice              | <AudioPlayer title="Julian - Vibrant Voice" />              | masculine | Adult | Friendly and cheerful male voice with uplifting warmth, great for feel-good narrations and…          | Voice Agents, Customer Support |
| `489b647b-5662-408f-8c95-82e26ef8d29e` | Kate - Practical Voice              | <AudioPlayer title="Kate - Practical Voice" />              | feminine  | Adult | Direct, no-nonsense female voice for instructions and clear explanations                             | Voice Agents, Customer Support |
| `f786b574-daa5-4673-aa0c-cbe3e8534c02` | Katie - Friendly Fixer              | <AudioPlayer title="Katie - Friendly Fixer" />              | feminine  | Adult | Enunciating young adult female for conversational support use cases                                  | Voice Agents, Customer Support |
| `1ac31ebd-9113-405b-9d80-4a4bbbeea91c` | Kayla - Easygoing Pal               | <AudioPlayer title="Kayla - Easygoing Pal" />               | feminine  | Adult | Casual female voice with a friendly, natural tone that feels effortless and engaging in conversation | Voice Agents, Customer Support |
| `9fa83ce3-c3a8-4523-accc-173904582ced` | Keith - Easygoing Friend            | <AudioPlayer title="Keith - Easygoing Friend" />            | masculine | Adult | Chill, young adult male for casual conversations                                                     | Voice Agents, Customer Support |
| `4b1e0bf9-53a0-4e9e-8664-ba1314dbcb38` | Kelly - Friendly Spirit             | <AudioPlayer title="Kelly - Friendly Spirit" />             | feminine  | Adult | Casual voice with a friendly, natural tone that feels easygoing and approachable                     | Voice Agents, Customer Support |
| `050f5a7a-9d2b-4b76-84e3-2d056a0a3eb0` | Kelsey - Ball of energy             | <AudioPlayer title="Kelsey - Ball of energy" />             | feminine  | Adult | Upbeat voice with lively energy and friendly warmth, perfect for energetic and engaging…             | Voice Agents, Customer Support |
| `911b8b22-887f-4caf-bf87-85d834c08708` | Kenneth - Friendly Rep              | <AudioPlayer title="Kenneth - Friendly Rep" />              | masculine | Adult | Well-paced male voice with clear enunciation, great for approachable and informative conversations   | Voice Agents, Customer Support |
| `f8f5f1b2-f02d-4d8e-a40d-fd850a487b3d` | Kiara - Joyful Woman                | <AudioPlayer title="Kiara - Joyful Woman" />                | feminine  | Adult | Upbeat, enunciating Indian accented mature adult female for happy conversations                      | Voice Agents, Customer Support |
| `228fca29-3a0a-435c-8728-5cb483251068` | Kiefer - Assured Tone               | <AudioPlayer title="Kiefer - Assured Tone" />               | masculine | Adult | Confident voice with strong clarity and composed delivery, ideal for presentations and customer…     | Voice Agents, Customer Support |
| `eb649460-7e23-43bc-ad20-0a7a2749b938` | Kim - Cheerful Pal                  | <AudioPlayer title="Kim - Cheerful Pal" />                  | feminine  | Adult | Friendly voice with a smooth, easygoing tone                                                         | Voice Agents, Customer Support |
| `57dcab65-68ac-45a6-8480-6c4c52ec1cd1` | Kira - Trusted Confidant            | <AudioPlayer title="Kira - Trusted Confidant" />            | feminine  | Adult | Emotive, young adult female for empathetic conversations                                             | Voice Agents, Customer Support |
| `c63361f8-d142-4c62-8da7-8f8149d973d6` | Krishna - Friendly Pal              | <AudioPlayer title="Krishna - Friendly Pal" />              | masculine | Adult | Easygoing adult male voice with a slight Indian accent for casual conversations, approachable…       | Voice Agents, Customer Support |
| `efa653e5-314d-46ca-9f90-70ac7d6ca71e` | Kurt - Phone Support                | <AudioPlayer title="Kurt - Phone Support" />                | masculine | Adult | Engaging male voice with expressive tone and natural warmth, ideal for customer service              | Voice Agents, Customer Support |
| `c961b81c-a935-4c17-bfb3-ba2239de8c2f` | Kyle - Approachable Friend          | <AudioPlayer title="Kyle - Approachable Friend" />          | masculine | Adult | Friendly male voice with a warm, conversational tone that builds instant connection and trust        | Voice Agents, Customer Support |
| `efc5488b-5429-4e72-aaa2-570981cf47d9` | Lacey - Sunny Soul                  | <AudioPlayer title="Lacey - Sunny Soul" />                  | feminine  | Adult | Cheerful and friendly female voice with bright energy that uplifts and engages listeners instantly   | Voice Agents, Customer Support |
| `cb6a8744-41b0-4cdc-b643-fabeb545c6a9` | Laurel - Caring Sister              | <AudioPlayer title="Laurel - Caring Sister" />              | feminine  | Adult | Warm voice with gentle empathy and clarity, perfect for heartfelt conversations and customer support | Voice Agents, Customer Support |
| `a33f7a4c-100f-41cf-a1fd-5822e8fc253f` | Lauren - Lively Narrator            | <AudioPlayer title="Lauren - Lively Narrator" />            | feminine  | Adult | Expressive female voice for narration, storytelling, and creative content                            | Voice Agents, Customer Support |
| `d2c66146-c1c8-4c3a-9870-38e5a6b72442` | Lawson - Suave Storyteller          | <AudioPlayer title="Lawson - Suave Storyteller" />          | masculine | Adult | Charming matured male voice with smooth delivery and refined tone, perfect for narrations and…       | Voice Agents, Customer Support |
| `999df508-4de5-40a7-8bd3-8c12f678c284` | Layla - Casual Friend               | <AudioPlayer title="Layla - Casual Friend" />               | feminine  | Adult | Chill voice with a smooth, easygoing tone that feels relaxed and effortlessly cool                   | Voice Agents, Customer Support |
| `0834f3df-e650-4766-a20c-5a93a43aa6e3` | Leo - Genuine Companion             | <AudioPlayer title="Leo - Genuine Companion" />             | masculine | Adult | Friendly and approachable male voice that brings warmth and ease to any interaction                  | Voice Agents, Customer Support |
| `4703c250-66e4-4682-a223-0a60acafcfc0` | Levi - Steady Spokesman             | <AudioPlayer title="Levi - Steady Spokesman" />             | masculine | Adult | Strong, confident voice for customer service, newscasting, and reliable narration                    | Voice Agents, Customer Support |
| `56b87df1-594d-4135-992c-1112bb504c59` | Lexi - Fun Friend                   | <AudioPlayer title="Lexi - Fun Friend" />                   | feminine  | Adult | Cheery, young female for entertainment, media, and gaming use cases                                  | Voice Agents, Customer Support |
| `41f3c367-e0a8-4a85-89e0-c27bae9c9b6d` | Liam - Guy Next Door                | <AudioPlayer title="Liam - Guy Next Door" />                | masculine | Adult | Casual, friendly young male for authentic and engaging conversations                                 | Voice Agents, Customer Support |
| `4af7c703-f2a9-45dd-a7fd-724cf7efc371` | Lila - Meditation Guide             | <AudioPlayer title="Lila - Meditation Guide" />             | feminine  | Adult | Melodic female for gentle and empathetic conversations                                               | Voice Agents, Customer Support |
| `dda51133-5d43-4a3b-84e6-e68c13f60cba` | Lily - Casual Pal                   | <AudioPlayer title="Lily - Casual Pal" />                   | feminine  | Adult | Relaxed, casual voice for friendly, everyday conversations                                           | Voice Agents, Customer Support |
| `829ccd10-f8b3-43cd-b8a0-4aeaa81f3b30` | Linda - Conversational Guide        | <AudioPlayer title="Linda - Conversational Guide" />        | feminine  | Adult | Clear, confident mature female for conversational use cases                                          | Voice Agents, Customer Support |
| `a38e4e85-e815-43ab-acf1-907c4688dd6c` | Lindsey - Relaxed Rep               | <AudioPlayer title="Lindsey - Relaxed Rep" />               | feminine  | Adult | Happy adult female with a laidback affect for casual conversations and customer support              | Voice Agents, Customer Support |
| `c1b9a03e-747f-40ad-8e7b-18caf8aaac0b` | Lira - Tranquil Voice               | <AudioPlayer title="Lira - Tranquil Voice" />               | feminine  | Adult | Soothing female voice with gentle warmth, ideal for calm narrations and ASMR                         | Voice Agents, Customer Support |
| `ea7c252f-6cb1-45f5-8be9-b4f6ac282242` | Logan - Approachable Friend         | <AudioPlayer title="Logan - Approachable Friend" />         | masculine | Adult | Casual voice with an easy, conversational tone that feels natural and approachable                   | Voice Agents, Customer Support |
| `57c63422-d911-4666-815b-0c332e4d7d6a` | Lori - Cheerleader                  | <AudioPlayer title="Lori - Cheerleader" />                  | feminine  | Adult | Female with clear enunciation for upbeat, emotive conversations                                      | Voice Agents, Customer Support |
| `5cc54223-ec0c-4c50-87e9-b9947264e1f4` | Lori - Cheerleader                  | <AudioPlayer title="Lori - Cheerleader" />                  | feminine  | Adult | Female with clear enunciation for upbeat, emotive conversations                                      | Voice Agents, Customer Support |
| `ba0add52-783c-4ec0-8b9c-7a6b60f99d1c` | Lori - Curious Cheerleader          | <AudioPlayer title="Lori - Curious Cheerleader" />          | feminine  | Adult | Female with clear enunciation for upbeat, emotive conversations                                      | Voice Agents, Customer Support |
| `414da90b-16b3-4e88-86f5-3c3945e8fa4b` | Lori - Disgusted Cheerleader        | <AudioPlayer title="Lori - Disgusted Cheerleader" />        | feminine  | Adult | Female with clear enunciation for upbeat, emotive conversations                                      | Voice Agents, Customer Support |
| `8843adfb-77d3-455a-86f9-de0651555ec6` | Lori - Happy Cheerleader            | <AudioPlayer title="Lori - Happy Cheerleader" />            | feminine  | Adult | Female with clear enunciation for upbeat, emotive conversations                                      | Voice Agents, Customer Support |
| `2d01710c-7c77-4cf1-b0d0-5902a25f6e17` | Lori - Sad Cheerleader              | <AudioPlayer title="Lori - Sad Cheerleader" />              | feminine  | Adult | Female with clear enunciation for upbeat, emotive conversations                                      | Voice Agents, Customer Support |
| `fb78f09f-f998-4061-ad51-d71f90388f0e` | Lori - Scared Cheerleader           | <AudioPlayer title="Lori - Scared Cheerleader" />           | feminine  | Adult | Female with clear enunciation for upbeat, emotive conversations                                      | Voice Agents, Customer Support |
| `c2da2a3e-b0d6-46bf-a09a-68562617a50a` | Lori - Surprised Cheerleader        | <AudioPlayer title="Lori - Surprised Cheerleader" />        | feminine  | Adult | Female with clear enunciation for upbeat, emotive conversations                                      | Voice Agents, Customer Support |
| `2f251ac3-89a9-4a77-a452-704b474ccd01` | Lucy - Capable Coordinator          | <AudioPlayer title="Lucy - Capable Coordinator" />          | feminine  | Adult | Reassuring British female for customer assistance.                                                   | Voice Agents, Customer Support |
| `61001bc6-9064-40a4-b8b2-29178e0fa558` | Luke - Angry Broadway Voice         | <AudioPlayer title="Luke - Angry Broadway Voice" />         | masculine | Adult | Seasoned male voice for casual, authentic conversations                                              | Voice Agents, Customer Support |
| `7b2c0a2e-3dd3-4a44-b16b-26ecd8134279` | Luke - Broadway Voice               | <AudioPlayer title="Luke - Broadway Voice" />               | masculine | Adult | Seasoned male voice for casual, authentic conversations                                              | Voice Agents, Customer Support |
| `8e14933d-ecd7-402b-9505-795130d69b35` | Luke - Broadway Voice               | <AudioPlayer title="Luke - Broadway Voice" />               | masculine | Adult | Seasoned male voice for casual, authentic conversations                                              | Voice Agents, Customer Support |
| `79b8126f-c5d9-4a73-8585-ba5e1a077ed6` | Luke - Disgusted Broadway Voice     | <AudioPlayer title="Luke - Disgusted Broadway Voice" />     | masculine | Adult | Seasoned male voice for casual, authentic conversations                                              | Voice Agents, Customer Support |
| `3d79b1fd-daaa-439c-bff3-903dc18e7684` | Luke - Happy Broadway Voice         | <AudioPlayer title="Luke - Happy Broadway Voice" />         | masculine | Adult | Seasoned male voice for casual, authentic conversations                                              | Voice Agents, Customer Support |
| `5c7b66c2-3b58-464d-8a12-093410a269c5` | Luke - Sad Broadway Voice           | <AudioPlayer title="Luke - Sad Broadway Voice" />           | masculine | Adult | Seasoned male voice for casual, authentic conversations                                              | Voice Agents, Customer Support |
| `63426c82-a0c9-4f23-a175-50eb64c95ec1` | Luke - Scared Broadway Voice        | <AudioPlayer title="Luke - Scared Broadway Voice" />        | masculine | Adult | Seasoned male voice for casual, authentic conversations                                              | Voice Agents, Customer Support |
| `725d43d6-1196-480e-bd87-728ae5eff9e1` | Luke - Surprised Broadway Voice     | <AudioPlayer title="Luke - Surprised Broadway Voice" />     | masculine | Adult | Seasoned male voice for casual, authentic conversations                                              | Voice Agents, Customer Support |
| `e13cae5c-ec59-4f71-b0a6-266df3c9bb8e` | Lulu - Madame Mischief              | <AudioPlayer title="Lulu - Madame Mischief" />              | feminine  | Adult | Squeaky, young female for media and entertainment for kids                                           | Voice Agents, Customer Support |
| `d7e54830-4754-4b17-952c-bcdb7e80a2fb` | Mabel - Grandma                     | <AudioPlayer title="Mabel - Grandma" />                     | feminine  | Adult | Friendly, grandmotherly female for empathetic conversations                                          | Voice Agents, Customer Support |
| `02fe5732-a072-4767-83e3-a91d41d274ca` | Madison - Best Friend               | <AudioPlayer title="Madison - Best Friend" />               | feminine  | Adult | Enthusiastic, young adult female for emotive discussions                                             | Voice Agents, Customer Support |
| `134838f5-ce7e-4876-ac32-6367b99daf83` | Madison - Best Friend               | <AudioPlayer title="Madison - Best Friend" />               | feminine  | Adult | Enthusiastic, young adult female for emotive discussions                                             | Voice Agents, Customer Support |
| `98c87826-dba2-44f4-b123-4c7e3c8a2647` | Madison - Curious Best Friend       | <AudioPlayer title="Madison - Curious Best Friend" />       | feminine  | Adult | Enthusiastic, young adult female for emotive discussions                                             | Voice Agents, Customer Support |
| `5993c2c9-5d59-403e-b459-946c8b302086` | Madison - Disgusted Best Friend     | <AudioPlayer title="Madison - Disgusted Best Friend" />     | feminine  | Adult | Enthusiastic young adult female for emotive discussions                                              | Voice Agents, Customer Support |
| `62305e79-9d39-4643-b003-5e0b096fe4f4` | Madison - Happy Best Friend         | <AudioPlayer title="Madison - Happy Best Friend" />         | feminine  | Adult | Enthusiastic young adult female for emotive discussions                                              | Voice Agents, Customer Support |
| `27c12970-3efb-4f39-a78a-2fbb7bddc941` | Madison - Sad Best Friend           | <AudioPlayer title="Madison - Sad Best Friend" />           | feminine  | Adult | Enthusiastic young adult female for emotive discussions                                              | Voice Agents, Customer Support |
| `30236d07-62d0-4c63-abf7-df46aa45e473` | Madison - Scared Best Friend        | <AudioPlayer title="Madison - Scared Best Friend" />        | feminine  | Adult | Enthusiastic, young adult female for emotive discussions                                             | Voice Agents, Customer Support |
| `a5def41e-2e73-433f-92f7-5f1d99fef05d` | Madison - Surprised Best Friend     | <AudioPlayer title="Madison - Surprised Best Friend" />     | feminine  | Adult | Enthusiastic, young adult female for emotive discussions                                             | Voice Agents, Customer Support |
| `63ff761f-c1e8-414b-b969-d1833d1c870c` | Malcom - Talk Show Host             | <AudioPlayer title="Malcom - Talk Show Host" />             | masculine | Adult | Lively and experienced male voice ideal for natural, engaging conversations                          | Voice Agents, Customer Support |
| `9301949d-b7cd-40d9-a246-5a4430992d6b` | Marcus - Reliable Guy               | <AudioPlayer title="Marcus - Reliable Guy" />               | masculine | Adult | Composed voice with approachable warmth, perfect for customer service and support                    | Voice Agents, Customer Support |
| `a2364c9d-1fe3-4553-9eff-100c4fe5ffc8` | Marge - Seasoned Grace              | <AudioPlayer title="Marge - Seasoned Grace" />              | feminine  | Adult | Wise matured voice with expressive warmth and character, perfect for storytelling and entertainment  | Voice Agents, Customer Support |
| `26403c37-80c1-4a1a-8692-540551ca2ae5` | Marian - Poised Narrator            | <AudioPlayer title="Marian - Poised Narrator" />            | feminine  | Adult | Matured female voice with calm authority and smooth pacing, perfect for narrations and storytelling  | Voice Agents, Customer Support |
| `f9fc912e-52f0-448a-8bfa-47e9ca75f25a` | Marilyn - Explainer                 | <AudioPlayer title="Marilyn - Explainer" />                 | feminine  | Adult | smooth and supportive young adult woman great for natural conversations and explaining               | Voice Agents, Customer Support |
| `3d9b50f9-10c5-4026-9ae1-c4a698f67fc5` | Marjorie - Encouraging Aunt         | <AudioPlayer title="Marjorie - Encouraging Aunt" />         | feminine  | Adult | Encouraging matured voice with warm reassurance and steady tone, perfect for motivational and…       | Voice Agents, Customer Support |
| `5619d38c-cf51-4d8e-9575-48f61a280413` | Mark - Promotion Lead               | <AudioPlayer title="Mark - Promotion Lead" />               | masculine | Adult | Deep, confident male voice with strong presence - ideal for commercials, promos, and broadcast…      | Voice Agents, Customer Support |
| `7360f116-6306-4e9a-b487-1235f35a0f21` | Marty - Commercial King             | <AudioPlayer title="Marty - Commercial King" />             | masculine | Adult | Bold and enthusiastic male voice suited for energetic, attention-grabbing ads                        | Voice Agents, Customer Support |
| `49808e4c-998a-40a8-b2ea-8ac8e8ce779e` | Marvin - Steady Ally                | <AudioPlayer title="Marvin - Steady Ally" />                | masculine | Adult | Deep, comforting voice with calm authority and warmth, perfect for reassuring and professional…      | Voice Agents, Customer Support |
| `5c42302c-194b-4d0c-ba1a-8cb485c84ab9` | Mary - Nurse                        | <AudioPlayer title="Mary - Nurse" />                        | feminine  | Adult | Mature adult female for instructional videos and empathetic conversations                            | Voice Agents, Customer Support |
| `b58b6b46-1a27-46ba-8648-bc203a5d394e` | Mason - Calm Vibe                   | <AudioPlayer title="Mason - Calm Vibe" />                   | masculine | Adult | Chill voice with a smooth, conversational tone that feels relaxed and genuine                        | Voice Agents, Customer Support |
| `bfd3644b-d561-4b1c-a01f-d9af98cb67c0` | Matt - Goofy Friend                 | <AudioPlayer title="Matt - Goofy Friend" />                 | masculine | Adult | High pitched, silly male for fun characters and entertainment use cases                              | Voice Agents, Customer Support |
| `6fbca103-0f7f-4e49-97ed-49a53b4f3534` | Maxine - Relaxed Energy             | <AudioPlayer title="Maxine - Relaxed Energy" />             | feminine  | Adult | Smooth voice with a calm, laid-back tone that brings an easy sense of comfort to any conversation    | Voice Agents, Customer Support |
| `cbaf8084-f009-4838-a096-07ee2e6612b1` | Maya - Easygoing Ally               | <AudioPlayer title="Maya - Easygoing Ally" />               | feminine  | Adult | Friendly, casual female voice with clear articulation, ideal for natural conversations and…          | Voice Agents, Customer Support |
| `dcc82bcd-647e-4478-955f-8232d5122f8b` | Melanie - Lively Spirit             | <AudioPlayer title="Melanie - Lively Spirit" />             | feminine  | Adult | Enthusiastic voice with bright, engaging energy that brings excitement to any conversation           | Voice Agents, Customer Support |
| `d6b0c62a-c7ff-477c-9a1f-eadd64b94360` | Melina - Bright Spirit              | <AudioPlayer title="Melina - Bright Spirit" />              | feminine  | Adult | Outgoing voice with lively warmth and friendly tone, perfect for casual chats and everyday…          | Voice Agents, Customer Support |
| `1d3ba41a-96e6-44ad-aabb-9817c56caa68` | Mia - Agent                         | <AudioPlayer title="Mia - Agent" />                         | feminine  | Adult | Firm, young female for customer support and casual, natural conversation                             | Voice Agents, Customer Support |
| `d7bf7d75-64b7-4c1e-86c0-79d647366587` | Michelle - Empathetic Voice         | <AudioPlayer title="Michelle - Empathetic Voice" />         | feminine  | Adult | Gentle and reassuring tone designed to offer comfort and build trust.                                | Voice Agents, Customer Support |
| `f114a467-c40a-4db8-964d-aaba89cd08fa` | Miles - Yogi                        | <AudioPlayer title="Miles - Yogi" />                        | masculine | Adult | Deep, soothing mature male for providing guidance                                                    | Voice Agents, Customer Support |
| `d6905573-8e91-4e32-b103-fd4d1205cd87` | Mindy - Spirited Ally               | <AudioPlayer title="Mindy - Spirited Ally" />               | feminine  | Adult | Enthusiastic female voice with bright energy and cheerful tone, great for lively conversations…      | Voice Agents, Customer Support |
| `03b1c65d-4b7f-4c09-91a8-e2f6f78cb2c9` | Molly - Upbeat Conversationalist    | <AudioPlayer title="Molly - Upbeat Conversationalist" />    | feminine  | Adult | Bright and cheerful American-accented female voice for upbeat conversations, advertisements, and…    | Voice Agents, Customer Support |
| `1b4ea5fb-b1c0-43ee-a7be-4e315878c2b1` | Monica - Emotive Voice              | <AudioPlayer title="Monica - Emotive Voice" />              | feminine  | Adult | English female adult voice with rich emotional range and expressive delivery                         | Voice Agents, Customer Support |
| `0ee8beaa-db49-4024-940d-c7ea09b590b3` | Morgan - Executive Expert           | <AudioPlayer title="Morgan - Executive Expert" />           | feminine  | Adult | Polished American female for highly professional interactions.                                       | Voice Agents, Customer Support |
| `efddb3d2-4464-45e0-9f8a-fcd5fd4fc54f` | Nadia - Singaporean Female          | <AudioPlayer title="Nadia - Singaporean Female" />          | feminine  | Adult | Friendly and clear Singaporean female voice.                                                         | Voice Agents, Customer Support |
| `e2d08065-b658-466b-ad52-cef8ee21d307` | Natasha - Upbeat Guide              | <AudioPlayer title="Natasha - Upbeat Guide" />              | feminine  | Adult | English female adult voice with a lively, upbeat tone for energetic conversations                    | Voice Agents, Customer Support |
| `97f4b8fb-f2fe-444b-bb9a-c109783a857a` | Nathan - Easy Talker                | <AudioPlayer title="Nathan - Easy Talker" />                | masculine | Adult | Confident, firm young adult male with a slight edge for conversational use cases                     | Voice Agents, Customer Support |
| `a924b0e6-9253-4711-8fc3-5cb8e0188c94` | Noah - Calming Presence             | <AudioPlayer title="Noah - Calming Presence" />             | masculine | Adult | Slow-paced voice with gentle warmth and soothing tone, perfect for ASMR and relaxation content       | Voice Agents, Customer Support |
| `f4c1a0b2-669d-403f-b440-4b34b34856aa` | Nora - Calm Companion               | <AudioPlayer title="Nora - Calm Companion" />               | feminine  | Adult | Balanced, neutral female voice that sounds natural and approachable for everyday conversations       | Voice Agents, Customer Support |
| `ee7ea9f8-c0c1-498c-9279-764d6b56d189` | Oliver - Customer Chap              | <AudioPlayer title="Oliver - Customer Chap" />              | masculine | Adult | Polite, young adult male for customer facing use cases                                               | Voice Agents, Customer Support |
| `f31cc6a7-c1e8-4764-980c-60a361443dd1` | Olivia - Sunny Woman                | <AudioPlayer title="Olivia - Sunny Woman" />                | feminine  | Adult | Friendly, happy adult female for engaging conversations                                              | Voice Agents, Customer Support |
| `4c2dcd38-5608-45ca-8f11-51c88208d01c` | Orin - Velvet Gentleman             | <AudioPlayer title="Orin - Velvet Gentleman" />             | masculine | Adult | Deep, silky male voice that delivers authority and allure, perfect for impactful ads and promos      | Voice Agents, Customer Support |
| `bd9120b6-7761-47a6-a446-77ca49132781` | Owen - Tutorial Man                 | <AudioPlayer title="Owen - Tutorial Man" />                 | masculine | Adult | Elevated, mature adult male for providing guidance and instruction                                   | Voice Agents, Customer Support |
| `e5a6cd18-d552-4192-9533-82a08cac8f23` | Patricia - Veteran Support          | <AudioPlayer title="Patricia - Veteran Support" />          | feminine  | Adult | Matured voice with lively warmth and enthusiasm, perfect for engaging and energetic customer service | Voice Agents, Customer Support |
| `3e1ed423-17e5-4773-b87c-25b031106e41` | Paul - Straight Talker              | <AudioPlayer title="Paul - Straight Talker" />              | masculine | Adult | Deep and firm male voice with a relaxed, conversational delivery                                     | Voice Agents, Customer Support |
| `baf84392-fa95-4d44-8871-d32ee36b0e01` | Pieter - Polished Analyst           | <AudioPlayer title="Pieter - Polished Analyst" />           | masculine | Adult | Clear, articulate South African male ideal for business briefings.                                   | Voice Agents, Customer Support |
| `cd6256ef-2b2a-41f6-a8d8-c1307af5061f` | Preston - Relatable Pal             | <AudioPlayer title="Preston - Relatable Pal" />             | masculine | Adult | Confident voice with expressive tone and charismatic delivery, great for engaging conversations      | Voice Agents, Customer Support |
| `f6141af3-5f94-418c-80ed-a45d450e7e2e` | Priya - Trusted Operator            | <AudioPlayer title="Priya - Trusted Operator" />            | feminine  | Adult | Authoritative, adult female for customer support                                                     | Voice Agents, Customer Support |
| `045f0292-0731-4a4c-971d-64594fc2c35a` | Quinn - Calm Authority              | <AudioPlayer title="Quinn - Calm Authority" />              | feminine  | Adult | Confident voice with clear articulation and poised tone, perfect for presentations and customer…     | Voice Agents, Customer Support |
| `10bd4af4-825b-49b8-b8bd-0ca11865536e` | Rachel - Polished Presence          | <AudioPlayer title="Rachel - Polished Presence" />          | feminine  | Adult | Refined and smooth articulation for high-quality corporate messaging.                                | Voice Agents, Customer Support |
| `1ce291a1-0771-4732-a3f7-8cca29bf055f` | Ralph - Dynamic Commentator         | <AudioPlayer title="Ralph - Dynamic Commentator" />         | masculine | Adult | Matured male voice with powerful projection and crisp delivery, perfect for announcements and…       | Voice Agents, Customer Support |
| `565510e8-6b45-45de-8758-13588fbaec73` | Ray - Conversationalist             | <AudioPlayer title="Ray - Conversationalist" />             | masculine | Adult | Approachable male voice with a laid-back, natural delivery for everyday conversations                | Voice Agents, Customer Support |
| `57b6bf63-c7a1-4ffc-8e10-23bf45152dd6` | Rebecca - Counselor                 | <AudioPlayer title="Rebecca - Counselor" />                 | feminine  | Adult | Soft-spoken, empathetic female voice suited for thoughtful, calming dialogue                         | Voice Agents, Customer Support |
| `c7c790c5-2bf4-47e4-bc83-5f43e61f3803` | Reese - Warm Companion              | <AudioPlayer title="Reese - Warm Companion" />              | feminine  | Adult | Casual, friendly female voice with a bright and welcoming tone suited for everyday conversations.    | Voice Agents, Customer Support |
| `a3520a8f-226a-428d-9fcd-b0a4711a6829` | Reflective Woman                    | <AudioPlayer title="Reflective Woman" />                    | feminine  | Adult | This voice is even, full, and reflective, perfect for a young narrator for an audiobook or movie     | Voice Agents, Customer Support |
| `74f42072-6245-4fe2-b5dc-3dc9b56fdbd0` | Regis - News Anchor                 | <AudioPlayer title="Regis - News Anchor" />                 | masculine | Adult | Authoritative voice with polished clarity and balanced tone, perfect for news delivery and…          | Voice Agents, Customer Support |
| `c2ac25f9-ecc4-4f56-9095-651354df60c0` | Renee - Commander                   | <AudioPlayer title="Renee - Commander" />                   | feminine  | Adult | Firm adult female fit for broadcasts and narrations                                                  | Voice Agents, Customer Support |
| `21b81c14-f85b-436d-aff5-43f2e788ecf8` | Riley - Chill Friend                | <AudioPlayer title="Riley - Chill Friend" />                | feminine  | Adult | Casual, young female for authentic and everyday conversations                                        | Voice Agents, Customer Support |
| `8985388c-1332-4ce7-8d55-789628aa3df4` | Robyn - Storycrafter                | <AudioPlayer title="Robyn - Storycrafter" />                | feminine  | Adult | Neutral, mature female for narrations                                                                | Voice Agents, Customer Support |
| `f688c0a6-dddd-48ba-8246-c099d494a162` | Romeo - Calm Narrator               | <AudioPlayer title="Romeo - Calm Narrator" />               | masculine | Adult | Relaxing voice with smooth depth and calm pacing, perfect for storytelling and immersive narrations  | Voice Agents, Customer Support |
| `5ee9feff-1265-424a-9d7f-8e4d431a12c7` | Ronald - Thinker                    | <AudioPlayer title="Ronald - Thinker" />                    | masculine | Adult | Intense, deep young adult male for casual conversations                                              | Voice Agents, Customer Support |
| `8d7d11ff-d985-48a2-a737-1da0b6fedc8b` | Ronan - Warm Buddy                  | <AudioPlayer title="Ronan - Warm Buddy" />                  | masculine | Adult | Friendly male voice with an easygoing tone that feels natural and inviting in any context            | Voice Agents, Customer Support |
| `9329fbdb-e285-4fba-95ec-592e15f14476` | Rory - Maternal Vibe                | <AudioPlayer title="Rory - Maternal Vibe" />                | feminine  | Adult | Motherlike female voice with a calm, nurturing tone that brings warmth and reassurance to any…       | Voice Agents, Customer Support |
| `f24ae0b7-a3d2-4dd1-89df-959bdc4ab179` | Ross - Reliable Partner             | <AudioPlayer title="Ross - Reliable Partner" />             | masculine | Adult | Steady voice with balanced tone and clear delivery, ideal for customer support and service           | Voice Agents, Customer Support |
| `701a96e1-7fdd-4a6c-a81e-a4a450403599` | Rowan - Team Leader                 | <AudioPlayer title="Rowan - Team Leader" />                 | masculine | Adult | Confident male for narrations                                                                        | Voice Agents, Customer Support |
| `ed9ccfa4-8fa1-40f8-bfb2-cb7d67d2f9cd` | Ruby - Helpful Handler              | <AudioPlayer title="Ruby - Helpful Handler" />              | feminine  | Adult | Adult female for everyday dialogue.                                                                  | Voice Agents, Customer Support |
| `0ad65e7f-006c-47cf-bd31-52279d487913` | Rupert - Caring Dad                 | <AudioPlayer title="Rupert - Caring Dad" />                 | masculine | Adult | Warm, mature voice for caring, reassuring conversations                                              | Voice Agents, Customer Support |
| `ab109683-f31f-40d7-b264-9ec3e26fb85e` | Russell - Mentor                    | <AudioPlayer title="Russell - Mentor" />                    | masculine | Adult | Friendly, deep mature adult male for providing instructions and guidance                             | Voice Agents, Customer Support |
| `11af83e2-23eb-452f-956e-7fee218ccb5c` | Ruth - Manager                      | <AudioPlayer title="Ruth - Manager" />                      | feminine  | Adult | Firm, authoritative female for providing guidance                                                    | Voice Agents, Customer Support |
| `0a9a5903-0a30-4d2e-b6b6-891f73d4b4e0` | Sabrina - Casual Ally               | <AudioPlayer title="Sabrina - Casual Ally" />               | feminine  | Adult | Relaxed female voice with an easy, conversational tone that feels approachable and genuine           | Voice Agents, Customer Support |
| `6adbb439-0865-468c-9e68-adbb0eb2e71c` | Sally - Soft Spoken Guide           | <AudioPlayer title="Sally - Soft Spoken Guide" />           | feminine  | Adult | Gentle female for calm conversations                                                                 | Voice Agents, Customer Support |
| `04bfd756-4fd4-42c2-9ccf-37f647c5bf54` | Samantha - Angry Support Leader     | <AudioPlayer title="Samantha - Angry Support Leader" />     | feminine  | Adult | Firm, confident adult female for conversational support                                              | Voice Agents, Customer Support |
| `761afc95-bef5-44dd-aa07-d3c678912e43` | Samantha - Happy Support Leader     | <AudioPlayer title="Samantha - Happy Support Leader" />     | feminine  | Adult | Firm, confident adult female for conversational support                                              | Voice Agents, Customer Support |
| `5e10a334-7fa5-46d4-a64b-5ae6185da3fd` | Samantha - Sad Support Leader       | <AudioPlayer title="Samantha - Sad Support Leader" />       | feminine  | Adult | Firm, confident adult female for conversational support                                              | Voice Agents, Customer Support |
| `f4e8781b-a420-4080-81cf-576331238efa` | Samantha - Support Leader           | <AudioPlayer title="Samantha - Support Leader" />           | feminine  | Adult | Firm, confident adult female for conversational support                                              | Voice Agents, Customer Support |
| `d3e03deb-5439-4203-add1-ca9a7501eaa7` | Samantha - Yelling Support Leader   | <AudioPlayer title="Samantha - Yelling Support Leader" />   | feminine  | Adult | Firm, confident adult female for conversational support                                              | Voice Agents, Customer Support |
| `638efaaa-4d0c-442e-b701-3fae16aad012` | Sameer - Problem Solver             | <AudioPlayer title="Sameer - Problem Solver" />             | masculine | Adult | Friendly male for customer support use cases                                                         | Voice Agents, Customer Support |
| `3f38cbe2-ce6a-4051-b5dc-2b2ee20b9bc1` | Sasha - Cool Friend                 | <AudioPlayer title="Sasha - Cool Friend" />                 | feminine  | Adult | Chill female voice with a smooth, laid-back tone that brings ease and calm to any conversation       | Voice Agents, Customer Support |
| `78ab82d5-25be-4f7d-82b3-7ad64e5b85b2` | Savannah - Magnolia Belle           | <AudioPlayer title="Savannah - Magnolia Belle" />           | feminine  | Adult | Adult female for casual, authentic conservations                                                     | Voice Agents, Customer Support |
| `2f22b9bc-b0eb-4cb6-b5ae-0c099a0fdfad` | Scott - Sportscaster                | <AudioPlayer title="Scott - Sportscaster" />                | masculine | Adult | Energetic American adult male voice with the excitement of a sportscaster for live commentary,…      | Voice Agents, Customer Support |
| `1cb5b8bc-77c9-4e7c-a251-da02348e2727` | Sean - Steady Companion             | <AudioPlayer title="Sean - Steady Companion" />             | masculine | Adult | Casual voice with an easy, relaxed tone that feels natural and effortlessly approachable             | Voice Agents, Customer Support |
| `63927f41-9616-4ac2-89cf-f3afa346e0ef` | Selene - Soothing Aura              | <AudioPlayer title="Selene - Soothing Aura" />              | feminine  | Adult | Relaxing and calm voice with gentle flow and serene tone, ideal for meditation and mindfulness…      | Voice Agents, Customer Support |
| `3ef78ba6-9aaa-46a2-b5b5-f9ded76a2370` | Serena - Laidback Girl              | <AudioPlayer title="Serena - Laidback Girl" />              | feminine  | Adult | Female adult voice with a relaxed, easygoing tone and laid-back delivery                             | Voice Agents, Customer Support |
| `8cbfe3ab-8364-4e72-b606-93f749519c66` | Shane - Helpful Guide               | <AudioPlayer title="Shane - Helpful Guide" />               | masculine | Adult | Casual male voice with clear, steady delivery that makes troubleshooting steps easy to follow…       | Voice Agents, Customer Support |
| `64462aed-aafc-45d4-84cd-ecb4b3763a0a` | Shawn - Ad Reader                   | <AudioPlayer title="Shawn - Ad Reader" />                   | masculine | Adult | Upbeat male for commercials, announcements, and promotions                                           | Voice Agents, Customer Support |
| `39b376fc-488e-4d0c-8b37-e00b72059fdd` | Sheldon - Help Desk Man             | <AudioPlayer title="Sheldon - Help Desk Man" />             | masculine | Adult | Enunciating male for customer support use cases                                                      | Voice Agents, Customer Support |
| `0d2162c2-2fe9-40a7-b3c1-43eab576a64b` | Shelly - Warm Companion             | <AudioPlayer title="Shelly - Warm Companion" />             | feminine  | Adult | Friendly voice with a bright, approachable tone that feels natural and welcoming in any setting      | Voice Agents, Customer Support |
| `4e41a434-85fc-4614-b203-af79ba44d473` | Sienna - Encourager                 | <AudioPlayer title="Sienna - Encourager" />                 | feminine  | Adult | Soft-spoken American-accented female voice with a motivating and reassuring tone for guidance,…      | Voice Agents, Customer Support |
| `b7d50908-b17c-442d-ad8d-810c63997ed9` | Sierra - California Girl            | <AudioPlayer title="Sierra - California Girl" />            | feminine  | Adult | Slow, chill young adult female for casual conversations                                              | Voice Agents, Customer Support |
| `7e19344f-9f17-47d7-a13a-4366ad06ebf3` | Silas - Nighttime Narrator          | <AudioPlayer title="Silas - Nighttime Narrator" />          | masculine | Adult | Gentle and steady male voice with a nurturing tone for calm conversations and serene narration       | Voice Agents, Customer Support |
| `3b554273-4299-48b9-9aaf-eefd438e3941` | Simi - Support Specialist           | <AudioPlayer title="Simi - Support Specialist" />           | feminine  | Adult | Firm, young accented female for customer support use cases                                           | Voice Agents, Customer Support |
| `d79d2b77-9192-4e10-9407-5d43ca034803` | Siobhan - Warm Welcomer             | <AudioPlayer title="Siobhan - Warm Welcomer" />             | feminine  | Adult | Approachable Irish female for friendly, everyday dialogue.                                           | Voice Agents, Customer Support |
| `db6b0ed5-d5d3-463d-ae85-518a07d3c2b4` | Skylar - Friendly Guide             | <AudioPlayer title="Skylar - Friendly Guide" />             | feminine  | Adult | Approachable American female ideal for customer care and support.                                    | Voice Agents, Customer Support |
| `01fd7d67-d2a0-4e4e-8c48-42611c71a926` | Skyler - Laidback Partner           | <AudioPlayer title="Skyler - Laidback Partner" />           | masculine | Adult | Easygoing voice with effortless tone that feels natural and approachable                             | Voice Agents, Customer Support |
| `3bf35adc-bcc4-464b-b834-c90c88cf6492` | Spencer - Chill Gentleman           | <AudioPlayer title="Spencer - Chill Gentleman" />           | masculine | Adult | Casual voice with an engaging, upbeat tone that feels friendly and effortlessly conversational       | Voice Agents, Customer Support |
| `6d287143-8db3-434a-959c-df147192da27` | Stacy - Mentor                      | <AudioPlayer title="Stacy - Mentor" />                      | feminine  | Adult | Mature-sounding female voice with kindness and ease, perfect for natural interactions                | Voice Agents, Customer Support |
| `6a73e45f-3fa6-427c-97da-0fc6a7a1bc0d` | Stephanie - Steady Professional     | <AudioPlayer title="Stephanie - Steady Professional" />     | feminine  | Adult | Steady and even pacing that offers a grounding presence for any script.                              | Voice Agents, Customer Support |
| `b134c304-d095-4d2b-a77a-914f5e8e84e7` | Sterling - Monarch                  | <AudioPlayer title="Sterling - Monarch" />                  | masculine | Adult | Deep voice with commanding presence and dignified tone, perfect for narrations and authoritative…    | Voice Agents, Customer Support |
| `7c8ba972-4960-4c43-bea0-8178e2205696` | Steve - Angry Baritone              | <AudioPlayer title="Steve - Angry Baritone" />              | masculine | Adult | Deep, firm adult male for narrations and voiceovers                                                  | Voice Agents, Customer Support |
| `9fb269e7-70fe-4cbe-aa3f-28bdb67e3e84` | Steve - Baritone                    | <AudioPlayer title="Steve - Baritone" />                    | masculine | Adult | Deep, firm adult male for narrations and voiceovers                                                  | Voice Agents, Customer Support |
| `c1c65fc2-528a-4dde-a2c4-f822785c2704` | Steve - Curious Baritone            | <AudioPlayer title="Steve - Curious Baritone" />            | masculine | Adult | Deep, firm adult male for narrations and voiceovers                                                  | Voice Agents, Customer Support |
| `f96dc0b1-7900-4894-a339-81fb46d515a7` | Steve - Disgusted Baritone          | <AudioPlayer title="Steve - Disgusted Baritone" />          | masculine | Adult | Deep, firm adult male for narrations and voiceovers                                                  | Voice Agents, Customer Support |
| `adde00e9-c98f-42ae-a94d-fc9f92f11c76` | Steve - Happy Baritone              | <AudioPlayer title="Steve - Happy Baritone" />              | masculine | Adult | Deep, firm adult male for narrations and voiceovers                                                  | Voice Agents, Customer Support |
| `80713a53-e484-4f69-9852-7891096016ac` | Steve - Sad Baritone                | <AudioPlayer title="Steve - Sad Baritone" />                | masculine | Adult | Deep, firm adult male for narrations and voiceovers                                                  | Voice Agents, Customer Support |
| `b1ce5126-4d08-42c3-adef-d3eb39e90c7a` | Steve - Scared Baritone             | <AudioPlayer title="Steve - Scared Baritone" />             | masculine | Adult | Deep, firm adult male for narrations and voiceovers                                                  | Voice Agents, Customer Support |
| `6fd4f468-0345-4f41-81d0-3f48ebc295e0` | Steve - Surprised Baritone          | <AudioPlayer title="Steve - Surprised Baritone" />          | masculine | Adult | Deep, firm adult male for narrations and voiceovers                                                  | Voice Agents, Customer Support |
| `17488b72-f815-44d8-bdd9-869971c3ec06` | Steven - Big Brother                | <AudioPlayer title="Steven - Big Brother" />                | masculine | Adult | Conversational voice with a relaxed, natural tone that feels genuine and easy to engage with         | Voice Agents, Customer Support |
| `156fb8d2-335b-4950-9cb3-a2d33befec77` | Sunny - Pep Talker                  | <AudioPlayer title="Sunny - Pep Talker" />                  | feminine  | Adult | Upbeat female for engaging conversations                                                             | Voice Agents, Customer Support |
| `8634bd27-0acf-4056-b014-4fea0385ed9e` | Suzanne - Laidback Aunt             | <AudioPlayer title="Suzanne - Laidback Aunt" />             | feminine  | Adult | Matured voice with a natural, conversational tone that feels warm, relatable, and approachable       | Voice Agents, Customer Support |
| `573e3144-a684-4e72-ac2b-9b2063a50b53` | Sylvia - Librarian                  | <AudioPlayer title="Sylvia - Librarian" />                  | feminine  | Adult | Firm female for instructions and guidance                                                            | Voice Agents, Customer Support |
| `b56c6aac-f35f-46f7-9361-e8f078cec72e` | Tabitha - Smooth Energy             | <AudioPlayer title="Tabitha - Smooth Energy" />             | feminine  | Adult | Smooth voice with easy warmth and relaxed tone, perfect for casual conversations                     | Voice Agents, Customer Support |
| `373e661a-f0ef-4e34-a09e-183184a443e6` | Tanner - Laidback Spirit            | <AudioPlayer title="Tanner - Laidback Spirit" />            | masculine | Adult | Laidback voice with smooth tone and easy rhythm, great for conversational and approachable content   | Voice Agents, Customer Support |
| `710feaa3-b550-42f3-b3eb-6f37f2a7cc0a` | Tanner - Upbeat Assistant           | <AudioPlayer title="Tanner - Upbeat Assistant" />           | masculine | Adult | English male adult voice with an upbeat and energetic tone                                           | Voice Agents, Customer Support |
| `3308b492-50cc-417e-89dd-1f446c574546` | Tara - Confident Ally               | <AudioPlayer title="Tara - Confident Ally" />               | feminine  | Adult | Confident voice with clear, composed tone, perfect for professional and customer service settings    | Voice Agents, Customer Support |
| `6ccbfb76-1fc6-48f7-b71d-91ac6298247b` | Tessa - Kind Companion              | <AudioPlayer title="Tessa - Kind Companion" />              | feminine  | Adult | Friendly female voice with a warm, conversational tone that feels like chatting with a close friend  | Voice Agents, Customer Support |
| `692846ad-1a6b-49b8-bfc5-86421fd41a19` | Thandi - Direct Dispatcher          | <AudioPlayer title="Thandi - Direct Dispatcher" />          | feminine  | Adult | Professional South African female for structured support.                                            | Voice Agents, Customer Support |
| `fb26447f-308b-471e-8b00-8e9f04284eb5` | Thistle - Troublemaker              | <AudioPlayer title="Thistle - Troublemaker" />              | neutral   | Adult | Cheery, expressive gender neutral character for whimsical personas in entertainment content          | Voice Agents, Customer Support |
| `86600680-b836-41e1-9916-8475728dcc14` | Tiffany - Dynamic Presence          | <AudioPlayer title="Tiffany - Dynamic Presence" />          | feminine  | Adult | Engaging voice with lively clarity and confident warmth, ideal for keeping listeners interested…     | Voice Agents, Customer Support |
| `146485fd-8736-41c7-88a8-7cdd0da34d84` | Tim - Pal                           | <AudioPlayer title="Tim - Pal" />                           | masculine | Adult | Nasal-y male for casual conversations                                                                | Voice Agents, Customer Support |
| `91b4cf29-5166-44eb-8054-30d40ecc8081` | Tina - Customer Ally                | <AudioPlayer title="Tina - Customer Ally" />                | feminine  | Adult | Natural, firm adult female for authentic conversation and customer support                           | Voice Agents, Customer Support |
| `3d5ce2fb-e56c-42f0-9ed9-4662484063b4` | Toby - Genuine Guide                | <AudioPlayer title="Toby - Genuine Guide" />                | masculine | Adult | Warm, conversational British male with a polished tone.                                              | Voice Agents, Customer Support |
| `efd255c7-f030-43d3-b5d8-c7b72063be70` | Todd - Matter of Fact Salesman      | <AudioPlayer title="Todd - Matter of Fact Salesman" />      | masculine | Adult | English male adult voice with a direct, matter-of-fact delivery                                      | Voice Agents, Customer Support |
| `40104aff-a015-4da1-9912-af950fbec99e` | Travis - How To Guide               | <AudioPlayer title="Travis - How To Guide" />               | masculine | Adult | Firm, young male for instructional videos and customer support                                       | Voice Agents, Customer Support |
| `c45bc5ec-dc68-4feb-8829-6e6b2748095d` | Trevor - Movieman                   | <AudioPlayer title="Trevor - Movieman" />                   | masculine | Adult | Deep, elderly male for narrations and entertainment use cases                                        | Voice Agents, Customer Support |
| `726d5ae5-055f-4c3d-8355-d9677de68937` | Troy - Fix It Man                   | <AudioPlayer title="Troy - Fix It Man" />                   | masculine | Adult | Strong, dependable male voice designed for trust-building in customer-facing interactions            | Voice Agents, Customer Support |
| `820a3788-2b37-4d21-847a-b65d8a68c99a` | Tyler - Friendly Salesman           | <AudioPlayer title="Tyler - Friendly Salesman" />           | masculine | Adult | Direct and confidence inspiring adult male for sales and friendly interpersonal conversations        | Voice Agents, Customer Support |
| `af346552-54bf-4c2b-a4d4-9d2820f51b6c` | Valerie - Support Authority         | <AudioPlayer title="Valerie - Support Authority" />         | feminine  | Adult | Authoritative mature female for frontline customer support use cases                                 | Voice Agents, Customer Support |
| `643f5eee-459d-4b41-b4fc-0b8407139be6` | Vicky - Businesswoman               | <AudioPlayer title="Vicky - Businesswoman" />               | feminine  | Adult | Clear and crisp voice with precise delivery and bright tone, ideal for professional and…             | Voice Agents, Customer Support |
| `7fe6faca-172f-4fd9-a193-25642b8fdb07` | Victor - Voiceover Man              | <AudioPlayer title="Victor - Voiceover Man" />              | masculine | Adult | Versatile, engaging adult male for professional use cases, narrations, and voiceovers                | Voice Agents, Customer Support |
| `dc30854e-e398-4579-9dc8-16f6cb2c19b9` | Victoria - Refined Coordinator      | <AudioPlayer title="Victoria - Refined Coordinator" />      | feminine  | Adult | Crisp, professional British female for reassuring communication.                                     | Voice Agents, Customer Support |
| `ca31ce53-ebf6-4e51-b87d-2f65d5d1f7f8` | Vivian - Fierce Narrator            | <AudioPlayer title="Vivian - Fierce Narrator" />            | feminine  | Adult | Voice with rich emotion and expressive depth, perfect for dramatic readings and heartfelt narratio   | Voice Agents, Customer Support |
| `3d83e30f-c31b-4f26-b442-7075feafa53a` | Wade - Southern Soul                | <AudioPlayer title="Wade - Southern Soul" />                | masculine | Adult | Country-sounding male voice with a warm drawl and genuine charm, perfect for friendly storytelling   | Voice Agents, Customer Support |
| `fbf7d2ec-ebea-49f2-8889-a482b9b0a7ed` | Wade 2.0 - Southern Soul            | <AudioPlayer title="Wade 2.0 - Southern Soul" />            | masculine | Adult | Country-sounding male voice with a warm drawl and genuine charm, perfect for friendly storytelling   | Voice Agents, Customer Support |
| `79bfcec0-720c-41f2-a33a-f12383e9627f` | Wang - Guide                        | <AudioPlayer title="Wang - Guide" />                        | masculine | Adult | Clear and firm adult male voice with an authoritative tone for customer support, giving…             | Voice Agents, Customer Support |
| `2a4d065a-ac91-4203-a015-eb3fc3ee3365` | Wes - Customer Companion            | <AudioPlayer title="Wes - Customer Companion" />            | masculine | Adult | Kind male for engaging with customers                                                                | Voice Agents, Customer Support |
| `6fccb471-26f7-4f7a-93dd-542935db6c20` | Wesley - Chill Flow                 | <AudioPlayer title="Wesley - Chill Flow" />                 | masculine | Adult | Casual voice with a relaxed, friendly tone that feels natural and easy to listen to                  | Voice Agents, Customer Support |
| `5f621418-ab01-4bf4-9a9d-73d66032234e` | Willow - Approachable Ally          | <AudioPlayer title="Willow - Approachable Ally" />          | feminine  | Adult | Friendly female for approachable, down-to-earth support.                                             | Voice Agents, Customer Support |
| `5fc5c797-12c5-4f2b-ac9b-d4e53c08098f` | Wyatt - Dependable Dispatcher       | <AudioPlayer title="Wyatt - Dependable Dispatcher" />       | masculine | Adult | Friendly, clear American male with a subtle Southern drawl.                                          | Voice Agents, Customer Support |
| `daf747c6-6bc2-4083-bd59-aa94dce23f5d` | Yasmin - Dialogue Anchor            | <AudioPlayer title="Yasmin - Dialogue Anchor" />            | feminine  | Adult | Firm adult female for conversational use cases                                                       | Voice Agents, Customer Support |
| `ed81fd13-2016-4a49-8fe3-c0d2761695fc` | Zack - Sportsman                    | <AudioPlayer title="Zack - Sportsman" />                    | masculine | Adult | Firm, energetic male for lively announcing                                                           | Voice Agents, Customer Support |
| `afb19d1b-4044-4f34-a962-f4aef640a002` | Zander - Energetic Announcer        | <AudioPlayer title="Zander - Energetic Announcer" />        | masculine | Adult | Enthusiastic voice with energetic delivery and bold tone, perfect for advertisements and…            | Voice Agents, Customer Support |
| `263b9cc0-0d99-44e7-ae92-3d4ad5d2ad18` | Zanele - Vibrant Advocate           | <AudioPlayer title="Zanele - Vibrant Advocate" />           | feminine  | Adult | Lively, positive delivery that brings authentic energy.                                              | Voice Agents, Customer Support |
| `e00d0e4c-a5c8-443f-a8a3-473eb9a62355` | Zeke - Friendly Sidekick            | <AudioPlayer title="Zeke - Friendly Sidekick" />            | masculine | Adult | High pitched, friendly, young adult male for gaming and entertainment characters                     | Voice Agents, Customer Support |
| `48369ca9-0645-40de-9821-0d55e18a03c2` | Zoey - Bright Voice                 | <AudioPlayer title="Zoey - Bright Voice" />                 | feminine  | Adult | Upbeat female voice with lively energy and warmth, perfect for energetic and engaging conversations  | Voice Agents, Customer Support |
| `694f9389-aac1-45b6-b726-9d9369183238` | Sarah - Mindful Woman               | <AudioPlayer title="Sarah - Mindful Woman" />               | feminine  | Adult | Soothing female for meditations and calming conversations                                            | Voice Agents, Customer Support |
| `bf0a246a-8642-498a-9950-80c35e9276b5` | Sophie - Teacher                    | <AudioPlayer title="Sophie - Teacher" />                    | feminine  | Adult | Mature female for natural conversations                                                              | Voice Agents, Customer Support |
| `00a77add-48d5-4ef6-8157-71e5437b282d` | Callie - Encourager                 | <AudioPlayer title="Callie - Encourager" />                 | feminine  | Adult | Smooth, young adult female for empathetic conversation                                               | Voice Agents, Customer Support |
| `87bc56aa-ab01-4baa-9071-77d497064686` | Jordan - Chill Pal                  | <AudioPlayer title="Jordan - Chill Pal" />                  | masculine | Adult | Welcoming adult male for engaging conversations                                                      | Voice Agents, Customer Support |
| `79f8b5fb-2cc8-479a-80df-29f7a7cf1a3e` | Theo - Modern Narrator              | <AudioPlayer title="Theo - Modern Narrator" />              | masculine | Adult | Steady, enunciating, confident young male for narrations                                             | Voice Agents, Customer Support |

## Spanish

| Voice ID                               | Name                                | Sample                                                      | Gender    | Age   | Tone                                                                                             | Use Case                       |
| -------------------------------------- | ----------------------------------- | ----------------------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------ | ------------------------------ |
| `f4d6bb07-f876-4464-ba70-cd48d8701890` | Adriana - Bright Entertainer        | <AudioPlayer title="Adriana - Bright Entertainer" />        | feminine  | Adult | Bright, expressive voice for promotional and entertainment use                                   | Voice Agents, Customer Support |
| `2695b6b5-5543-4be1-96d9-3967fb5e7fec` | Agustin - Clear Storyteller         | <AudioPlayer title="Agustin - Clear Storyteller" />         | masculine | Adult | Intentional, clear adult for concise reports or storytelling                                     | Voice Agents, Customer Support |
| `3a35daa1-ba81-451c-9b21-59332e9db2f3` | Alejandro - Calm Mentor             | <AudioPlayer title="Alejandro - Calm Mentor" />             | masculine | Adult | Warm voice with a rich tone and calm cadence, ideal for reflective narration, heartfelt…         | Voice Agents, Customer Support |
| `ccfea4bf-b3f4-421e-87ed-dd05dae01431` | Alondra - Reassuring Sister         | <AudioPlayer title="Alondra - Reassuring Sister" />         | feminine  | Adult | Warm, friendly voice with a supportive, big-sister tone                                          | Voice Agents, Customer Support |
| `59b37da2-92ba-401a-9e4e-b1d16898d9bc` | Andrea - Clear Communicator         | <AudioPlayer title="Andrea - Clear Communicator" />         | feminine  | Adult | Professional Spanish female for direct and reliable support.                                     | Voice Agents, Customer Support |
| `d46e87a1-7c6d-4b18-9359-926f4a35ffdf` | Andres - Trusted Voice              | <AudioPlayer title="Andres - Trusted Voice" />              | masculine | Adult | Dependable, measured Mexican male ideal for professional communication.                          | Voice Agents, Customer Support |
| `02aeee94-c02b-456e-be7a-659672acf82d` | Benito - Digital Voice              | <AudioPlayer title="Benito - Digital Voice" />              | masculine | Adult | Consistent voice for clear, conversational exchanges                                             | Voice Agents, Customer Support |
| `538a8872-3799-4df5-b373-b78493b766c6` | Blanca - Graceful Host              | <AudioPlayer title="Blanca - Graceful Host" />              | feminine  | Adult | Warm, welcoming Spanish female that puts listeners at ease instantly.                            | Voice Agents, Customer Support |
| `30212483-5c20-479c-8121-f93cd24e30a6` | Camila                              | <AudioPlayer title="Camila" />                              | feminine  | Adult | Lively voice for relaxed, casual conversations and light support.                                | Voice Agents, Customer Support |
| `bef2ba57-5c10-433b-b215-3bef35110a81` | Camila - Happy Conversationalist    | <AudioPlayer title="Camila - Happy Conversationalist" />    | feminine  | Adult | Lively voice for relaxed, casual conversations and light support.                                | Voice Agents, Customer Support |
| `9ebc775b-c579-4c31-b37c-2306cbe9cc91` | Carlos                              | <AudioPlayer title="Carlos" />                              | masculine | Adult | Warm, lively young adult male voice for expressive narrations and upbeat advertising.            | Voice Agents, Customer Support |
| `727f663b-0e90-4031-90f2-558b7334425b` | Carmen - Friendly Neighbor          | <AudioPlayer title="Carmen - Friendly Neighbor" />          | feminine  | Adult | Natural adult female voice for casual conversations and everyday interactions                    | Voice Agents, Customer Support |
| `162e0f37-8504-474c-bb33-c606c01890dc` | Catalina - Neighborly Guide         | <AudioPlayer title="Catalina - Neighborly Guide" />         | feminine  | Adult | Natural, approachable for everyday conversations                                                 | Voice Agents, Customer Support |
| `5c5ad5e7-1020-476b-8b91-fdcbe9cc313c` | Daniela - Relaxed Woman             | <AudioPlayer title="Daniela - Relaxed Woman" />             | feminine  | Adult | Calm and trusting Mexican accented female for natural conversations and efficient assistance     | Voice Agents, Customer Support |
| `399002e9-7f7d-42d4-a6a8-9b91bd809b9d` | Diego - Hype Guy                    | <AudioPlayer title="Diego - Hype Guy" />                    | masculine | Adult | Lively young adult male voice for energetic, natural-sounding conversations and product-forward… | Voice Agents, Customer Support |
| `b0689631-eee7-4a6c-bb86-195f1d267c2e` | Emilio - Friendly Optimist          | <AudioPlayer title="Emilio - Friendly Optimist" />          | masculine | Adult | Upbeat voice with a friendly tone for positive customer service interactions                     | Voice Agents, Customer Support |
| `b4b8e2af-6139-466e-a93a-30c20d2e1fc5` | Fernanda - Friendly Guide           | <AudioPlayer title="Fernanda - Friendly Guide" />           | feminine  | Adult | Approachable, Mexican female ideal for customer care and support.                                | Voice Agents, Customer Support |
| `5ef98b2a-68d2-4a35-ac52-632a2d288ea6` | Gabriel - Serious Old Man           | <AudioPlayer title="Gabriel - Serious Old Man" />           | masculine | Adult | Serious, elderly Spanish man for slow and insightful stories                                     | Voice Agents, Customer Support |
| `58e531e3-b212-49df-adee-c335a19c2429` | Gonzalo - Grounded Storyteller      | <AudioPlayer title="Gonzalo - Grounded Storyteller" />      | masculine | Adult | Warm, authentic Spanish male perfect for natural communication.                                  | Voice Agents, Customer Support |
| `dbaa1a0d-e004-442d-866f-5431b18d8d54` | Guadalupe - Wise Storyteller        | <AudioPlayer title="Guadalupe - Wise Storyteller" />        | feminine  | Adult | Character-rich voice for storytelling and dramatic narration                                     | Voice Agents, Customer Support |
| `b042270c-d46f-4d4f-8fb0-7dd7c5fe5615` | Hector - Tour Leader                | <AudioPlayer title="Hector - Tour Leader" />                | masculine | Adult | Energetic and captivating male with a bright Castilian accent for providing instructions         | Voice Agents, Customer Support |
| `c0c374aa-09be-42d9-9828-4d2d7df86962` | Isabel - Teacher                    | —                                                           | feminine  | Adult | Smooth and approachable female with a gentle Castilian accent for guidance and teaching          | Voice Agents, Customer Support |
| `e9f0368b-3662-4a01-b037-e13ca5203c74` | Javier - Gentle Advisor             | <AudioPlayer title="Javier - Gentle Advisor" />             | feminine  | Adult | Approachable adult male voice for casual conversations and natural dialogue                      | Voice Agents, Customer Support |
| `7c1ecd2d-1c83-4d5d-a25c-b3820a274a2e` | Jeronimo - Empathetic Advisor       | <AudioPlayer title="Jeronimo - Empathetic Advisor" />       | masculine | Adult | Friendly, emotionally aware voice for trust-based customer interactions                          | Voice Agents, Customer Support |
| `7b001dff-b8b2-4da7-92e4-5c794798effa` | Jorge - Regular Guy                 | <AudioPlayer title="Jorge - Regular Guy" />                 | masculine | Adult | Seasoned, relaxed voice with a warm tone, ideal for casual narration and conversational support. | Voice Agents, Customer Support |
| `c68a8bd0-f99e-4e7f-915d-a097da6d024c` | Juanita - Helpful Companion         | <AudioPlayer title="Juanita - Helpful Companion" />         | feminine  | Adult | Friendly, reassuring voice for customer support and assistance                                   | Voice Agents, Customer Support |
| `b503f001-80b8-49d3-8666-8d7700fc5ca2` | Liliana - Doting Mother             | <AudioPlayer title="Liliana - Doting Mother" />             | feminine  | Adult | Gentle, motherly middle-aged female voice for nurturing conversations, wellness guidance, and…   | Voice Agents, Customer Support |
| `c0925108-d541-4dc4-bbae-39f4e57ba10c` | Lucia - Radiant Host                | <AudioPlayer title="Lucia - Radiant Host" />                | feminine  | Adult | Bright, welcoming Spanish female that captures attention for events.                             | Voice Agents, Customer Support |
| `b5aa8098-49ef-475d-89b0-c9262ecf33fd` | Luis - News Caster                  | <AudioPlayer title="Luis - News Caster" />                  | masculine | Adult | Clear and distinctive male with a refined Castilian accent for clear communication               | Voice Agents, Customer Support |
| `948196a7-fe02-417b-9b6d-c45ee0803565` | Manuel - Newsman                    | <AudioPlayer title="Manuel - Newsman" />                    | masculine | Adult | Clear, mature male voice with a steady tone and authoritative presence, ideal for narrations,…   | Voice Agents, Customer Support |
| `ae823354-f9be-4aef-8543-f569644136b4` | Mariana - Nurturing Guide           | <AudioPlayer title="Mariana - Nurturing Guide" />           | feminine  | Adult | Motherly voice with a calm, nurturing tone                                                       | Voice Agents, Customer Support |
| `de38f545-c574-44e8-9b54-a7d6fec1c6b1` | Marta - Friendly Guide              | <AudioPlayer title="Marta - Friendly Guide" />              | feminine  | Adult | Approachable Spanish female ideal for customer care and support.                                 | Voice Agents, Customer Support |
| `2fc4f1ec-bfd0-46f1-8e6d-d4279eaaf838` | Mateo - Friendly Host               | <AudioPlayer title="Mateo - Friendly Host" />               | masculine | Adult | Warm, genuine Mexican male perfect for conversational platforms.                                 | Voice Agents, Customer Support |
| `9d8c6b2e-0a23-4a15-ae1b-121d5b5af417` | Nuria - Trusted Advisor             | <AudioPlayer title="Nuria - Trusted Advisor" />             | feminine  | Adult | Calm, dependable Spanish female perfect for professional communication.                          | Voice Agents, Customer Support |
| `d4db5fb9-f44b-4bd1-85fa-192e0f0d75f9` | Paloma - Clear Presenter Woman      | <AudioPlayer title="Paloma - Clear Presenter Woman" />      | feminine  | Adult | Clear and professional adult woman for reports, public speaking and customer assistance          | Voice Agents, Customer Support |
| `e361b786-2768-4308-9369-a09793d4dd73` | Paola - Expressive Performer        | <AudioPlayer title="Paola - Expressive Performer" />        | feminine  | Adult | Bold and lively voice for expressive performances and engaging content                           | Voice Agents, Customer Support |
| `15d0c2e2-8d29-44c3-be23-d585d5f154a1` | Pedro - Formal Speaker              | <AudioPlayer title="Pedro - Formal Speaker" />              | masculine | Adult | Formal and steady Mexican adult for clear and concise exchanges of information                   | Voice Agents, Customer Support |
| `d3793b7b-4996-409c-9d59-96dd09f47717` | Renata - Cheerful Conversationalist | <AudioPlayer title="Renata - Cheerful Conversationalist" /> | feminine  | Adult | Lively and upbeat matured voice, ideal for ads and narrations                                    | Voice Agents, Customer Support |
| `079e3a17-5545-4bc5-93e3-e11df6fe37b8` | Rodrigo - Calm Companion            | <AudioPlayer title="Rodrigo - Calm Companion" />            | masculine | Adult | Gentle, reassuring Latino male perfect for customer service.                                     | Voice Agents, Customer Support |
| `fb936dd1-66ea-43a0-86bd-18a6203dcda2` | Rosa - Optimist Mother              | <AudioPlayer title="Rosa - Optimist Mother" />              | feminine  | Adult | Happy, approachable middle-aged female voice for cheerful narration and casual conversations.    | Voice Agents, Customer Support |
| `bef24f4f-adc9-4cef-acbf-cc1ceb98224b` | Santiago - Modern Navigator         | <AudioPlayer title="Santiago - Modern Navigator" />         | masculine | Adult | Crisp, approachable Mexican male ideal for guided communication.                                 | Voice Agents, Customer Support |
| `ad8eee76-d702-4a1f-a1bd-7596755ae4c9` | Valeria - Cheerful Promoter         | <AudioPlayer title="Valeria - Cheerful Promoter" />         | feminine  | Adult | Expressive and upbeat young adult female voice for energetic commercials, entertainment, and…    | Voice Agents, Customer Support |
| `3597a26f-80ef-4bd5-8101-9699bc764917` | Ximena - Calm Navigator             | <AudioPlayer title="Ximena - Calm Navigator" />             | feminine  | Adult | Steady, clear Latina female ideal for guided experiences.                                        | Voice Agents, Customer Support |
| `13ff5deb-2591-42ad-a356-63a04e524411` | Marcos - Steady Advisor             | <AudioPlayer title="Marcos - Steady Advisor" />             | masculine | Adult | Calm, measured Spanish male suited for professional communication.                               | Voice Agents, Customer Support |
| `79743797-2087-422f-8dc7-86f9efca85f1` | Fran - Confident Young Professional | —                                                           | masculine | Adult | Confident and engaging male for conversational AI and phone interactions                         | Voice Agents, Customer Support |
| `846fa30b-6e1a-49b9-b7df-6be47092a09a` | Pablo - Clear Storyteller           | <AudioPlayer title="Pablo - Clear Storyteller" />           | masculine | Adult | Smooth and captivating male with a Castilian accent for conversational AI and interactions       | Voice Agents, Customer Support |
| `cefcb124-080b-4655-b31f-932f3ee743de` | Elena - Narrator                    | —                                                           | feminine  | Adult | Smooth and grounded female with a soft Castilian accent for podcasts and meditation              | Voice Agents, Customer Support |

## French

| Voice ID                               | Name                            | Sample                                                  | Gender    | Age   | Tone                                                                                            | Use Case                       |
| -------------------------------------- | ------------------------------- | ------------------------------------------------------- | --------- | ----- | ----------------------------------------------------------------------------------------------- | ------------------------------ |
| `5def377d-908b-4540-8bd7-3c968fcae351` | Benoît - Methodical Moderator   | <AudioPlayer title="Benoît - Methodical Moderator" />   | masculine | Adult | Clear, methodical French male for professional customer assistance.                             | Voice Agents, Customer Support |
| `a8a1eb38-5f15-4c1d-8722-7ac0f329727d` | Calm French Woman               | <AudioPlayer title="Calm French Woman" />               | feminine  | Adult | This voice is soft and calm, suited for soothing conversations in French                        | Voice Agents, Customer Support |
| `4325f426-c4e0-418e-a0e5-97fcdfcdf8e6` | Camille - Gracious Guide        | <AudioPlayer title="Camille - Gracious Guide" />        | feminine  | Adult | Elegant, articulated French female for customer support.                                        | Voice Agents, Customer Support |
| `6c64b57a-bc65-48e4-bff4-12dbe85606cd` | Eloise - Dialogue Anchor        | <AudioPlayer title="Eloise - Dialogue Anchor" />        | feminine  | Adult | Clear and well-paced adult female voice with a warm tone for customer service and professional… | Voice Agents, Customer Support |
| `735287ee-ce91-4b08-8de4-63315c5ba1fb` | Emmanuelle                      | <AudioPlayer title="Emmanuelle" />                      | feminine  | Adult | Energetic, upbeat young adult female great for friendly conversations                           | Voice Agents, Customer Support |
| `ab636c8b-9960-4fb3-bb0c-b7b655fb9745` | Erwan - Everyday Speaker        | <AudioPlayer title="Erwan - Everyday Speaker" />        | masculine | Adult | Clear voice for consistent, system-driven conversations                                         | Voice Agents, Customer Support |
| `8832a0b5-47b2-4751-bb22-6a8e2149303d` | French Narrator Lady            | <AudioPlayer title="French Narrator Lady" />            | feminine  | Adult | This voice is velvety and neutral, suited for narrating content in French                       | Voice Agents, Customer Support |
| `5c3c89e5-535f-43ef-b14d-f8ffe148c1f0` | French Narrator Man             | <AudioPlayer title="French Narrator Man" />             | masculine | Adult | This voice is even and rich, perfect for narrating content in French                            | Voice Agents, Customer Support |
| `ab7c61f5-3daa-47dd-a23b-4ac0aac5f5c3` | Friendly French Man             | —                                                       | masculine | Adult | This voice is friendly and calm, perfect for French customer support agents                     | Voice Agents, Customer Support |
| `5deeaea9-c3cf-4288-82ec-22d8f04eb158` | Gerard                          | <AudioPlayer title="Gerard" />                          | masculine | Adult | Deep, distinct middle-aged male voice for grounded narration and calm, authoritative guidance.  | Voice Agents, Customer Support |
| `2d693a9c-fc75-4313-aefb-c9cfaa17dd83` | Gerard - Monsieur Noir          | <AudioPlayer title="Gerard - Monsieur Noir" />          | masculine | Adult | Deep, distinct middle-aged male voice for grounded narration and calm, authoritative guidance.  | Voice Agents, Customer Support |
| `65b25c5d-ff07-4687-a04c-da2f43ef6fa9` | Helpful French Lady             | <AudioPlayer title="Helpful French Lady" />             | feminine  | Adult | This voice is helpful and cheery, like you're talking with a friend in French                   | Voice Agents, Customer Support |
| `7c58f4a4-a72c-42fa-a503-41b9408820f3` | Inès - Poised Communicator      | <AudioPlayer title="Inès - Poised Communicator" />      | feminine  | Adult | Confident, articulate French female suited for corporate narration.                             | Voice Agents, Customer Support |
| `22f1a356-56c2-4428-bc91-2ab2e6d0c215` | Isabelle - Professional Liaison | <AudioPlayer title="Isabelle - Professional Liaison" /> | feminine  | Adult | Formal adult female for professional conversations                                              | Voice Agents, Customer Support |
| `68db3d29-e0ab-4d4f-a5d5-e34ee47d38b7` | Joris - Command Coach           | <AudioPlayer title="Joris - Command Coach" />           | masculine | Adult | Deep voice with firm tone for providing instructions                                            | Voice Agents, Customer Support |
| `cc4276e6-1ebc-429a-8c7d-930993d51abc` | Julien - Polished Partner       | <AudioPlayer title="Julien - Polished Partner" />       | masculine | Adult | Professional, warm French male for reliable assistance.                                         | Voice Agents, Customer Support |
| `c9115185-0086-4cf4-bfdd-0d36425db387` | Juliette                        | <AudioPlayer title="Juliette" />                        | feminine  | Adult | Upbeat and inviting young female suited for lifestyle and brand narrations                      | Voice Agents, Customer Support |
| `7345dfa5-ee04-44d2-abf4-29262b880ab4` | Laurent - Dependable Anchor     | <AudioPlayer title="Laurent - Dependable Anchor" />     | masculine | Adult | Strong, definitive French male providing steady corporate messaging.                            | Voice Agents, Customer Support |
| `c96a7d7d-3457-4979-8665-522f7b3e36fb` | Léa - Logical Liaison           | <AudioPlayer title="Léa - Logical Liaison" />           | feminine  | Adult | Methodical French voice for precise customer guidance.                                          | Voice Agents, Customer Support |
| `adff5dcb-249f-463f-aa89-d98d8ca05e88` | Leo                             | <AudioPlayer title="Leo" />                             | masculine | Adult | High energy adult male great for motivational conversations                                     | Voice Agents, Customer Support |
| `3817fdb0-7ae1-42d2-b46e-734dd9601bf2` | Madeleine - Reliable Resident   | <AudioPlayer title="Madeleine - Reliable Resident" />   | feminine  | Adult | Warm, French Canadian female for helpful professional assistance.                               | Voice Agents, Customer Support |
| `2f8e82c4-cb94-4e6d-8b6a-29bf58ceb60a` | Manon - Bright Belle            | <AudioPlayer title="Manon - Bright Belle" />            | feminine  | Adult | Upbeat and inviting young female suited for lifestyle and brand narrations                      | Voice Agents, Customer Support |
| `ce74c4da-4aee-435d-bc6d-81d1a9367e12` | Marc - Conversational Buddy     | <AudioPlayer title="Marc - Conversational Buddy" />     | masculine | Adult | Friendly adult male for casual conversations                                                    | Voice Agents, Customer Support |
| `6d912a43-805f-4673-bbc8-a9e6c45a6ad0` | Marie-Eve - Team Mentor         | <AudioPlayer title="Marie-Eve - Team Mentor" />         | feminine  | Adult | Warm firm adult female for workplace conversations                                              | Voice Agents, Customer Support |
| `93c98a2b-7d15-4f7b-8236-294b1e02b1c0` | Mathieu - Assured Expert        | <AudioPlayer title="Mathieu - Assured Expert" />        | masculine | Adult | Knowledgeable French male conveying confidence for informative readings.                        | Voice Agents, Customer Support |
| `cc7d2711-69af-4072-9674-df588dd85682` | Maxime - Methodical Moderator   | —                                                       | masculine | Adult | Calm adult male for reassuring and capable service.                                             | Voice Agents, Customer Support |
| `187d1cc5-a771-4ccd-9110-9df8c4e39499` | Mika - Empathetic Friend        | <AudioPlayer title="Mika - Empathetic Friend" />        | feminine  | Adult | Friendly young adult female for emotive conversation                                            | Voice Agents, Customer Support |
| `bfd5390b-e4f9-4e44-95ab-9ebd223acd62` | Pierre                          | <AudioPlayer title="Pierre" />                          | masculine | Adult | Professional, calm adult male great for workplace conversations                                 | Voice Agents, Customer Support |
| `56df0456-8f47-4f7a-ac26-40c2f9797104` | Pierre - Baritone Storyteller   | <AudioPlayer title="Pierre - Baritone Storyteller" />   | masculine | Adult | Deep and resonant adult male voice for narration, audiobooks, and authoritative storytelling    | Voice Agents, Customer Support |
| `328e0683-d1a7-4cde-ad46-0ee69a3cbd6a` | Roxane - Problem-Solver         | <AudioPlayer title="Roxane - Problem-Solver" />         | feminine  | Adult | Warm French-Canadian female voice for customer service.                                         | Voice Agents, Customer Support |
| `0d09e991-5763-406e-b637-02bc431ef72d` | Valérie - Vibrant Voice         | —                                                       | feminine  | Adult | Energetic French female for engaging customer communication.                                    | Voice Agents, Customer Support |
| `dd951538-c475-4bde-a3f7-9fd7b3e4d8f5` | Vanessa                         | <AudioPlayer title="Vanessa" />                         | feminine  | Adult | Firm adult female great for providing clear instructions                                        | Voice Agents, Customer Support |
| `80e11491-2d8a-4361-ac61-c4f3e0a4f7e7` | Vincent                         | <AudioPlayer title="Vincent" />                         | masculine | Adult | Energetic, engaging adult male great for exciting conversations                                 | Voice Agents, Customer Support |
| `faa75703-00e3-4a57-9955-0703001e3231` | Amélie - Decisive Agent         | <AudioPlayer title="Amélie - Decisive Agent" />         | feminine  | Adult | Polished female for capable professional assistance.                                            | Voice Agents, Customer Support |
| `0418348a-0ca2-4e90-9986-800fb8b3bbc0` | Antoine - Stern Man             | <AudioPlayer title="Antoine - Stern Man" />             | masculine | Adult | Conversational                                                                                  | Voice Agents, Customer Support |

## German

| Voice ID                               | Name                               | Sample                                                     | Gender    | Age   | Tone                                                                                             | Use Case                       |
| -------------------------------------- | ---------------------------------- | ---------------------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------ | ------------------------------ |
| `38aabb6a-f52b-4fb0-a3d1-988518f4dc06` | Alina - Engaging Assistant         | <AudioPlayer title="Alina - Engaging Assistant" />         | feminine  | Adult | Warm female for phone systems, virtual assistants, and customer service                          | Voice Agents, Customer Support |
| `3264ada2-4a79-4666-badc-49e2267be692` | Christian                          | <AudioPlayer title="Christian" />                          | masculine | Adult | High energy adult male great for engaging and emotive conversations                              | Voice Agents, Customer Support |
| `c0c52199-e35f-4681-b68a-949ee499617e` | Eleni - Troubleshooter             | <AudioPlayer title="Eleni - Troubleshooter" />             | feminine  | Adult | Warm, approachable Swiss-German female for technical assistance.                                 | Voice Agents, Customer Support |
| `43a317e9-f1b9-45bf-bbdb-1d4a52e46f0d` | Emi                                | <AudioPlayer title="Emi" />                                | feminine  | Adult | Calm neutral adult female great for customer support                                             | Voice Agents, Customer Support |
| `f6f315e4-4fb3-4440-92ea-2edb01f9bf1b` | Hermann - Businessman              | <AudioPlayer title="Hermann - Businessman" />              | masculine | Adult | Warm, confident, and approachable voice, perfect for customer support and business conversations | Voice Agents, Customer Support |
| `42f14755-88c3-4124-aae3-5cc3a9618e8f` | Jan                                | <AudioPlayer title="Jan" />                                | masculine | Adult | Clear adult male great for providing guidance and instruction                                    | Voice Agents, Customer Support |
| `ac197a78-cec7-4c50-93e5-93bdc1910b11` | Jennifer                           | <AudioPlayer title="Jennifer" />                           | feminine  | Adult | Approachable adult female great for conversational support                                       | Voice Agents, Customer Support |
| `dff81230-ff75-49a4-af44-f6b2f43500d8` | Jonas                              | <AudioPlayer title="Jonas" />                              | masculine | Adult | Casual male voice thats warm, friendly, and conversational                                       | Voice Agents, Customer Support |
| `3f4ade23-6eb4-4279-ab05-6a144947c4d5` | Karin - Companion                  | <AudioPlayer title="Karin - Companion" />                  | feminine  | Adult | Friendly female for casual conversations                                                         | Voice Agents, Customer Support |
| `2578354e-4b18-4d28-832c-5943344b7085` | Klara - Empathetic Voice           | <AudioPlayer title="Klara - Empathetic Voice" />           | feminine  | Adult | Gentle and reassuring tone designed to offer comfort and build trust.                            | Voice Agents, Customer Support |
| `24c61c42-b538-468e-a9ad-16c7a032c9cb` | Klaus - Archivist                  | <AudioPlayer title="Klaus - Archivist" />                  | masculine | Adult | Deep, grounded male voice for narration, storytelling, and impactful brand content.              | Voice Agents, Customer Support |
| `1ade29fc-6b82-4607-9e70-361720139b12` | Lea - Breezy Voice                 | <AudioPlayer title="Lea - Breezy Voice" />                 | feminine  | Adult | Smooth female for casual conversations                                                           | Voice Agents, Customer Support |
| `758a5cff-af0b-4bdf-84bd-4c1b5525c249` | Leander                            | <AudioPlayer title="Leander" />                            | masculine | Adult | Warm and approachable voice, ideal for lifestyle content, social media, and casual explainers.   | Voice Agents, Customer Support |
| `4ab1ff51-476d-42bb-8019-4d315f7c0c05` | Lena - Muse                        | <AudioPlayer title="Lena - Muse" />                        | feminine  | Adult | Cool German female for clear communication and audiobooks                                        | Voice Agents, Customer Support |
| `adc919b3-6ebf-47fd-8a46-27c5169d6d94` | Leni - Daymaker                    | <AudioPlayer title="Leni - Daymaker" />                    | feminine  | Adult | Bright, cheerful voice with clear articulation and natural enthusiasm, ideal for upbeat…         | Voice Agents, Customer Support |
| `0b66a153-548f-4f2c-b734-09a13b0bd163` | Lorelei - Helpful Guide            | <AudioPlayer title="Lorelei - Helpful Guide" />            | feminine  | Adult | Calm and clearly enunciated voice, ideal for informative narration, mindfulness, and…            | Voice Agents, Customer Support |
| `e00dd3df-19e7-4cd4-827a-7ff6687b6954` | Lukas - Professional               | <AudioPlayer title="Lukas - Professional" />               | masculine | Adult | Confident male for phone systems and customer support                                            | Voice Agents, Customer Support |
| `9b4d08b6-0494-4301-ab92-9150f4ee2718` | Marlene - Elegant Speaker          | <AudioPlayer title="Marlene - Elegant Speaker" />          | feminine  | Adult | Refined, composed German female built for formal announcements.                                  | Voice Agents, Customer Support |
| `4ad22058-7cb6-402c-a115-196cbfc25dce` | Moritz - Modern Communicator       | <AudioPlayer title="Moritz - Modern Communicator" />       | masculine | Adult | Crisp, approachable German male ideal for digital assistants.                                    | Voice Agents, Customer Support |
| `afa425cf-5489-4a09-8a3f-d3cb1f82150d` | Nico - Friendly Agent              | <AudioPlayer title="Nico - Friendly Agent" />              | masculine | Adult | Casual male for phone calls and conversational agents                                            | Voice Agents, Customer Support |
| `d42fc8d7-efdd-44df-bb2e-a6e093601917` | Oskar - Steady Advisor             | <AudioPlayer title="Oskar - Steady Advisor" />             | masculine | Adult | Seasoned and composed voice with a calm and confident tone, ideal for guidance and thoughtful…   | Voice Agents, Customer Support |
| `de07efe3-b309-418b-bdca-42827223efd2` | Rena                               | <AudioPlayer title="Rena" />                               | feminine  | Adult | Emotive, energetic young adult female great for engaging conversations                           | Voice Agents, Customer Support |
| `6d4b1416-8d54-4d94-a788-8a802c086544` | Sabine - Firm Newscaster           | <AudioPlayer title="Sabine - Firm Newscaster" />           | feminine  | Adult | Soft yet commanding adult female voice for customer support, clear communication, and giving…    | Voice Agents, Customer Support |
| `b7187e84-fe22-4344-ba4a-bc013fcb533e` | Sebastian - Orator                 | <AudioPlayer title="Sebastian - Orator" />                 | masculine | Adult | Warm male for audiobooks and clear communication                                                 | Voice Agents, Customer Support |
| `11c61307-4f9e-4db8-ac3b-bfa5f2a731ce` | Serafina - Serene Storyteller      | <AudioPlayer title="Serafina - Serene Storyteller" />      | feminine  | Adult | Deep female for calming conversations and storytelling narrations                                | Voice Agents, Customer Support |
| `b629d743-2b5a-4ffd-b5bb-9de9b969a690` | Sibylle                            | <AudioPlayer title="Sibylle" />                            | feminine  | Adult | Clear and confident voice, ideal for announcements and customer support                          | Voice Agents, Customer Support |
| `384b625b-da5d-49e8-a76d-a2855d4f31eb` | Thomas - Anchor                    | <AudioPlayer title="Thomas - Anchor" />                    | masculine | Adult | Earnest male for conversations and customer support                                              | Voice Agents, Customer Support |
| `b9de4a89-2257-424b-94c2-db18ba68c81a` | Viktoria - Phone Conversationalist | <AudioPlayer title="Viktoria - Phone Conversationalist" /> | feminine  | Adult | Clear and smooth female for phone conversations                                                  | Voice Agents, Customer Support |
| `40e0f496-a220-46bb-975a-7ef465b3d92b` | Vreni - Diligent Advisor           | <AudioPlayer title="Vreni - Diligent Advisor" />           | feminine  | Adult | Composed, Swiss-German female for professional assistance.                                       | Voice Agents, Customer Support |
| `d1cbea67-e4d3-47cd-be2a-2bd4e646b002` | Henrik - Steady Analyst            | <AudioPlayer title="Henrik - Steady Analyst" />            | masculine | Adult | Articulate, dependable German male perfect for business briefings.                               | Voice Agents, Customer Support |
| `db229dfe-f5de-4be4-91fd-7b077c158578` | Andreas - Recorder                 | <AudioPlayer title="Andreas - Recorder" />                 | masculine | Adult | Smooth male for story narration                                                                  | Voice Agents, Customer Support |
| `2be00b67-d53f-4eb5-89e7-96c224d56fbc` | Dieter - Commercial Man            | <AudioPlayer title="Dieter - Commercial Man" />            | masculine | Adult | Loud and expressive adult male voice for storytelling, commercials, and energetic announcements  | Voice Agents, Customer Support |

## Hindi

| Voice ID                               | Name                         | Sample                                               | Gender    | Age   | Tone                                                                                      | Use Case                       |
| -------------------------------------- | ---------------------------- | ---------------------------------------------------- | --------- | ----- | ----------------------------------------------------------------------------------------- | ------------------------------ |
| `f91ab3e6-5071-4e15-b016-cde6f2bcd222` | Aadhya - Soother             | <AudioPlayer title="Aadhya - Soother" />             | feminine  | Adult | Slow female voice for casual conversation                                                 | Voice Agents, Customer Support |
| `9cebb910-d4b7-4a4a-85a4-12c79137724c` | Aarti - Conversationalist    | —                                                    | feminine  | Adult | Indian accented female for relatable dialogue                                             | Voice Agents, Customer Support |
| `209d9a43-03eb-40d8-a7b7-51a6d54c052f` | Anita - Meditation Guide     | <AudioPlayer title="Anita - Meditation Guide" />     | feminine  | Adult | Soft-spoken adult female voice for casual conversations, meditation, and calming dialogue | Voice Agents, Customer Support |
| `7e8cb11d-37af-476b-ab8f-25da99b18644` | Anuj - Engaging Narrator     | <AudioPlayer title="Anuj - Engaging Narrator" />     | masculine | Adult | Expressive male voice for storytelling and conversational content                         | Voice Agents, Customer Support |
| `95d51f79-c397-46f9-b49a-23763d3eaa2d` | Arushi - Hinglish Speaker    | <AudioPlayer title="Arushi - Hinglish Speaker" />    | feminine  | Adult | Hinglish female for bilingual content                                                     | Voice Agents, Customer Support |
| `7f423809-0011-4658-ba48-a411f5e516ba` | Ashwin - Warm Narrator       | <AudioPlayer title="Ashwin - Warm Narrator" />       | masculine | Adult | Warm and authoritative Hindi male for narrating stories, audiobooks, and documentaries    | Voice Agents, Customer Support |
| `791d5162-d5eb-40f0-8189-f19db44611d8` | Ayush - Friendly Neighbor    | <AudioPlayer title="Ayush - Friendly Neighbor" />    | masculine | Adult | Confident, young Indian male for delivering demos and instructions                        | Voice Agents, Customer Support |
| `910fb75e-1d20-4840-ac63-ac6b26a71bdc` | Dev - Friendly Host          | <AudioPlayer title="Dev - Friendly Host" />          | masculine | Adult | Warm, genuine Hindi male perfect for conversational platforms.                            | Voice Agents, Customer Support |
| `bdab08ad-4137-4548-b9db-6142854c7525` | Imran - Hindi Film Actor     | <AudioPlayer title="Imran - Hindi Film Actor" />     | masculine | Adult | Bollywood male artist for serious roles                                                   | Voice Agents, Customer Support |
| `fd2ada67-c2d9-4afe-b474-6386b87d8fc3` | Ishan - Ally                 | <AudioPlayer title="Ishan - Ally" />                 | masculine | Adult | Conversational male for Hinglish sales and customer support                               | Voice Agents, Customer Support |
| `56e35e2d-6eb6-4226-ab8b-9776515a7094` | Kavita - Customer Care Agent | <AudioPlayer title="Kavita - Customer Care Agent" /> | feminine  | Adult | Mature Indian female for customer care use cases                                          | Voice Agents, Customer Support |
| `a81fccdc-5595-4dfc-ae76-4de6a515b8a2` | Meera - Bright Companion     | <AudioPlayer title="Meera - Bright Companion" />     | feminine  | Adult | Friendly, approachable Hindi female perfect for everyday interactions.                    | Voice Agents, Customer Support |
| `9b953e7b-86a8-42f0-b625-1434fb15392b` | Neeraj - Tour Guide          | <AudioPlayer title="Neeraj - Tour Guide" />          | masculine | Adult | Deep male for excellent storytelling and providing instructions                           | Voice Agents, Customer Support |
| `47f3bbb1-e98f-4e0c-92c5-5f0325e1e206` | Neha - Virtual Assistant     | <AudioPlayer title="Neha - Virtual Assistant" />     | feminine  | Adult | Clear, composed female voice for virtual assistants and system prompts                    | Voice Agents, Customer Support |
| `0f14d8cb-f039-41fe-a813-a9b4bee7eed8` | Nisha - Elegant Speaker      | <AudioPlayer title="Nisha - Elegant Speaker" />      | feminine  | Adult | Refined, composed Hindi female perfect for formal announcements.                          | Voice Agents, Customer Support |
| `28ca2041-5dda-42df-8123-f58ea9c3da00` | Palak - Presenter            | —                                                    | feminine  | Adult | Friendly female with a slight English accent for teaching use cases                       | Voice Agents, Customer Support |
| `bec003e2-3cb3-429c-8468-206a393c67ad` | Parvati - Friendly Supporter | <AudioPlayer title="Parvati - Friendly Supporter" /> | feminine  | Adult | Friendly female for customer support use cases                                            | Voice Agents, Customer Support |
| `393dd459-f8d8-4c3e-a86b-ec43a1113d0b` | Rahul - Calm Office Guy      | <AudioPlayer title="Rahul - Calm Office Guy" />      | masculine | Adult | Approachable adult male voice for casual conversations and everyday interactions          | Voice Agents, Customer Support |
| `6b7468f5-d6b0-4d6b-b38a-46f6d6e5bac7` | Rakesh - Thoughtful Speaker  | —                                                    | masculine | Adult | Expressive male voice for informative narration and explanations                          | Voice Agents, Customer Support |
| `faf0731e-dfb9-4cfc-8119-259a79b27e12` | Riya - College Roommate      | <AudioPlayer title="Riya - College Roommate" />      | feminine  | Adult | Friendly woman for playful conversations                                                  | Voice Agents, Customer Support |
| `4877b818-c7fe-4c89-b1cf-eadf8e23da72` | Rohan - Steady Communicator  | <AudioPlayer title="Rohan - Steady Communicator" />  | masculine | Adult | Clear, measured Hindi male suited for corporate communication.                            | Voice Agents, Customer Support |
| `6303e5fb-a0a7-48f9-bb1a-dd42c216dc5d` | Sagar - Helpful Friend       | —                                                    | masculine | Adult | Energetic adult male for engaging customer support and conversations                      | Voice Agents, Customer Support |
| `55e2a153-c61e-4784-85c8-e954cb22fe29` | Sanjay - Clear Speaker       | <AudioPlayer title="Sanjay - Clear Speaker" />       | masculine | Adult | Formal male voice with clear pronunciation for professional narration and announcements   | Voice Agents, Customer Support |
| `432fc642-6a83-4975-b77a-c605903b5ba6` | Sanya - Modern Communicator  | <AudioPlayer title="Sanya - Modern Communicator" />  | feminine  | Adult | Crisp, approachable Hindi female built for digital assistance.                            | Voice Agents, Customer Support |
| `6b02ffe5-e3cb-48c0-a023-c72f85953375` | Sneha - Empathetic Voice     | <AudioPlayer title="Sneha - Empathetic Voice" />     | feminine  | Adult | Gentle and reassuring tone designed to offer comfort and build trust.                     | Voice Agents, Customer Support |
| `be79f378-47fe-4f9c-b92b-f02cefa62ccf` | Sunil - Official Announcer   | <AudioPlayer title="Sunil - Official Announcer" />   | masculine | Adult | Deep male for serious conversations                                                       | Voice Agents, Customer Support |
| `adf97b9d-905c-41de-9fe9-afb387116d06` | Vikas - Approachable Voice   | —                                                    | masculine | Adult | Polite, friendly male voice for customer support and service conversations                | Voice Agents, Customer Support |
| `098fb15d-2597-4186-8b74-25340050b6e7` | Vishal - Assured Expert      | <AudioPlayer title="Vishal - Assured Expert" />      | masculine | Adult | Grounded, knowledgeable delivery for professional communication.                          | Voice Agents, Customer Support |
| `20e68f5c-08e5-42d0-8e9b-6e716fd1ae66` | Vivek - Composed Voice       | —                                                    | masculine | Adult | Low-pitched, grounded male voice for formal communication                                 | Voice Agents, Customer Support |

## Japanese

| Voice ID                               | Name                                     | Sample                                                           | Gender    | Age   | Tone                                                                                                 | Use Case                       |
| -------------------------------------- | ---------------------------------------- | ---------------------------------------------------------------- | --------- | ----- | ---------------------------------------------------------------------------------------------------- | ------------------------------ |
| `498e7f37-7fa3-4e2c-b8e2-8b6e9276f956` | Aiko - Calming Voice                     | <AudioPlayer title="Aiko - Calming Voice" />                     | feminine  | Adult | Calm and composed voice for clear, conversational interactions                                       | Voice Agents, Customer Support |
| `446f922f-c43a-4aad-9a8b-ad2af568e882` | Akira - Professional Colleague           | <AudioPlayer title="Akira - Professional Colleague" />           | masculine | Adult | Clear and professional male for news announcements and business conversations                        | Voice Agents, Customer Support |
| `63d6f469-8c2c-489d-b53f-d36f0bbdcd4b` | Ayako                                    | <AudioPlayer title="Ayako" />                                    | feminine  | Adult | Friendly and calm adult female for providing instructions and conversational support                 | Voice Agents, Customer Support |
| `31c55968-a9f4-4115-8831-3a16952179c8` | Ayumi - Sales Guide                      | —                                                                | feminine  | Adult | Upbeat and enthusiastic adult female voice for sales, promotions, and engaging customer interactions | Voice Agents, Customer Support |
| `a759ecc5-ac21-487e-88c7-288bdfe76999` | Daichi - Baritone Narrator               | <AudioPlayer title="Daichi - Baritone Narrator" />               | masculine | Adult | Low pitched, intense male with a mysterious and brooding tone for villains, anti-heroes, and…        | Voice Agents, Customer Support |
| `e8a863c6-22c7-4671-86ca-91cacffc038d` | Daisuke - Businessman                    | <AudioPlayer title="Daisuke - Businessman" />                    | masculine | Adult | Business-like, clear male for professional use cases                                                 | Voice Agents, Customer Support |
| `c7eafe22-8b71-40cd-850b-c5a3bbd8f8d2` | Emi - Soft-Spoken Friend                 | <AudioPlayer title="Emi - Soft-Spoken Friend" />                 | feminine  | Adult | Soft and delicate female with a gentle, timid tone for female game characters and children's…        | Voice Agents, Customer Support |
| `97e7d7a9-dfaa-4758-a936-f5f844ac34cc` | Fuji - Positive Colleague                | <AudioPlayer title="Fuji - Positive Colleague" />                | masculine | Adult | Positive and gentle male for conversational settings                                                 | Voice Agents, Customer Support |
| `861213b7-f057-45c8-9527-0f4c144f1a03` | Haruka - Gracious Guide                  | <AudioPlayer title="Haruka - Gracious Guide" />                  | feminine  | Adult | Clear, polite Japanese female for welcoming customer assistance.                                     | Voice Agents, Customer Support |
| `d0ff6870-dd30-420d-8568-d756d806ea62` | Hinata - Graceful Guide                  | <AudioPlayer title="Hinata - Graceful Guide" />                  | feminine  | Adult | Polished Japanese female for polite, reassuring assistance.                                          | Voice Agents, Customer Support |
| `1d210168-d764-462c-8ab6-288a6d5a9579` | Hiroshi - Dependable Director            | <AudioPlayer title="Hiroshi - Dependable Director" />            | masculine | Adult | Steady Japanese male for clear transactional support.                                                | Voice Agents, Customer Support |
| `44863732-e415-4084-8ba1-deabe34ce3d2` | Kaori - Friendly Narrator                | <AudioPlayer title="Kaori - Friendly Narrator" />                | feminine  | Adult | Upbeat, positive, and gentle female for commercials and audiobooks                                   | Voice Agents, Customer Support |
| `9436e723-612d-4114-aeb0-fa00d4d639bf` | Katsuya - Promo Host                     | —                                                                | masculine | Adult | Lively confident male for advertising and announcing                                                 | Voice Agents, Customer Support |
| `6b92f628-be90-497c-8f4c-3b035002df71` | Kenji - Calm Man                         | <AudioPlayer title="Kenji - Calm Man" />                         | masculine | Adult | Calm, deep male for news narration and formal customer service                                       | Voice Agents, Customer Support |
| `177df681-25b1-48c2-bb47-03ca5fa27f0a` | Ren - Calm Navigator                     | <AudioPlayer title="Ren - Calm Navigator" />                     | masculine | Adult | Calm Japanese male suited for professional and reassuring communication.                             | Voice Agents, Customer Support |
| `9e7ef2cf-b69c-46ac-9e35-bbfd73ba82af` | Ren - High-Energy Character              | <AudioPlayer title="Ren - High-Energy Character" />              | masculine | Adult | Bold and lively male with high energy for fictional characters, dynamic narration, and…              | Voice Agents, Customer Support |
| `0cd0cde2-3b93-42b5-bcb9-f214a591aa29` | Sayuri - Peppy Colleague                 | <AudioPlayer title="Sayuri - Peppy Colleague" />                 | feminine  | Adult | Clear and bright female with a gentle tone of politeness and a naturally inquisitive cadence for…    | Voice Agents, Customer Support |
| `b8e1169c-f16a-4064-a6e0-95054169e553` | Takashi - Professional Conversationalist | <AudioPlayer title="Takashi - Professional Conversationalist" /> | masculine | Adult | Serious adult male voice with a steady but approachable tone for casual conversations and…           | Voice Agents, Customer Support |
| `06950fa3-534d-46b3-93bb-f852770ea0b5` | Takeshi - Hero                           | <AudioPlayer title="Takeshi - Hero" />                           | masculine | Adult | Smooth, expressive male with a warm mid-range and dynamic emotional range for dramatic storytelling  | Voice Agents, Customer Support |
| `49e02441-83ea-4c77-bda8-79fdd7f07e92` | Tohru - Career Coach                     | —                                                                | masculine | Adult | Young professional male for providing guidance and instruction                                       | Voice Agents, Customer Support |
| `59d4fd2f-f5eb-4410-8105-58db7661144f` | Yuki - Calm Woman                        | <AudioPlayer title="Yuki - Calm Woman" />                        | feminine  | Adult | Calm, more serious female for news narration and formal customer service                             | Voice Agents, Customer Support |
| `2b568345-1d48-4047-b25f-7baccf842eb0` | Yumiko - Friendly Agent                  | <AudioPlayer title="Yumiko - Friendly Agent" />                  | feminine  | Adult | Friendly, professional and upbeat woman for casual conversations                                     | Voice Agents, Customer Support |

## Korean

| Voice ID                               | Name                        | Sample                                              | Gender    | Age   | Tone                                                                                               | Use Case                       |
| -------------------------------------- | --------------------------- | --------------------------------------------------- | --------- | ----- | -------------------------------------------------------------------------------------------------- | ------------------------------ |
| `af6beeea-d732-40b6-8292-73af0035b740` | Byungtae - Enforcer         | <AudioPlayer title="Byungtae - Enforcer" />         | masculine | Adult | Authoritative male for providing instructions                                                      | Voice Agents, Customer Support |
| `4dd4630e-19e0-4243-bca0-676ff85119b7` | Haeun - Polished Presence   | <AudioPlayer title="Haeun - Polished Presence" />   | feminine  | Adult | Refined and smooth articulation for high-quality corporate messaging.                              | Voice Agents, Customer Support |
| `90dba946-774b-40ed-98d9-ac3835117827` | Hyerin - Graceful Host      | <AudioPlayer title="Hyerin - Graceful Host" />      | feminine  | Adult | Warm, welcoming Korean female that puts listeners at ease instantly.                               | Voice Agents, Customer Support |
| `663afeec-d082-4ab5-827e-2e41bf73a25b` | Jaechul - Disciplined Woman | <AudioPlayer title="Jaechul - Disciplined Woman" /> | feminine  | Adult | Serious female for formal conversation                                                             | Voice Agents, Customer Support |
| `89f4372f-1f73-4b85-8e1e-5d24ed8bc826` | Jaewon - Steady Advisor     | <AudioPlayer title="Jaewon - Steady Advisor" />     | masculine | Adult | Calm, measured Korean male suited for professional communication.                                  | Voice Agents, Customer Support |
| `304fdbd8-65e6-40d6-ab78-f9d18b9efdf9` | Jihyun - Anchorwoman        | <AudioPlayer title="Jihyun - Anchorwoman" />        | feminine  | Adult | Relaxing female for narrations and announcements                                                   | Voice Agents, Customer Support |
| `15628352-2ede-4f1b-89e6-ceda0c983fbc` | Jiwoo - Service Specialist  | <AudioPlayer title="Jiwoo - Service Specialist" />  | feminine  | Adult | Professional and polite adult female voice for customer service, support, and clear communication  | Voice Agents, Customer Support |
| `29e5f8b4-b953-4160-848f-40fae182235b` | Mimi - Show Stopper         | <AudioPlayer title="Mimi - Show Stopper" />         | feminine  | Adult | Cheery, young female for entertainment and content                                                 | Voice Agents, Customer Support |
| `537a82ae-4926-4bfb-9aec-aff0b80a12a5` | Minho - Friendly Spirit     | <AudioPlayer title="Minho - Friendly Spirit" />     | masculine | Adult | Laidback voice with a smooth, approachable tone that feels friendly and natural in conversation    | Voice Agents, Customer Support |
| `7706804e-ea85-443a-968a-b9bf363bdde8` | Minji - Modern Communicator | <AudioPlayer title="Minji - Modern Communicator" /> | feminine  | Adult | Crisp, natural Korean female built for platforms and digital assistants.                           | Voice Agents, Customer Support |
| `f7755efb-1848-4321-aa22-5e5be5d32486` | Ryeowook - Easygoing Pal    | <AudioPlayer title="Ryeowook - Easygoing Pal" />    | masculine | Adult | Relaxed voice with calm, natural pacing, ideal for easygoing everyday conversations                | Voice Agents, Customer Support |
| `ce9ca2b6-2bed-4452-99bb-052e1ec0b534` | Seoyun - Warm Guide         | <AudioPlayer title="Seoyun - Warm Guide" />         | feminine  | Adult | Inviting and approachable tone perfect for providing friendly guidance.                            | Voice Agents, Customer Support |
| `cd6c48a9-774b-4397-98b4-9948c0a790f0` | Soojin - Helpful Tone       | <AudioPlayer title="Soojin - Helpful Tone" />       | feminine  | Adult | Casual voice with a natural, friendly tone that feels relaxed and approachable in conversation     | Voice Agents, Customer Support |
| `69c18e1d-fab0-4747-b9da-58617cd8b9e4` | Soyeon - Bright Companion   | <AudioPlayer title="Soyeon - Bright Companion" />   | feminine  | Adult | Confident, friendly Korean female suited for conversation.                                         | Voice Agents, Customer Support |
| `a0fc16d3-01af-482b-910f-ed063c3d79d3` | Subin - Elegant Speaker     | <AudioPlayer title="Subin - Elegant Speaker" />     | feminine  | Adult | Refined, composed Korean female suited for formal announcements.                                   | Voice Agents, Customer Support |
| `e1717dc3-b87b-4720-aa7f-b6db290e0609` | Taehyun - Friendly Host     | <AudioPlayer title="Taehyun - Friendly Host" />     | masculine | Adult | Warm, genuine Korean for podcasts and conversational platforms.                                    | Voice Agents, Customer Support |
| `cac92886-4b7c-4bc1-a524-e0f79c0381be` | Yuna - Kind Unnie           | <AudioPlayer title="Yuna - Kind Unnie" />           | feminine  | Adult | Cheerful voice with a bright yet gentle tone, perfect for empathetic and friendly customer support | Voice Agents, Customer Support |

## Portuguese

| Voice ID                               | Name                          | Sample                                                | Gender    | Age   | Tone                                                                                             | Use Case                       |
| -------------------------------------- | ----------------------------- | ----------------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------ | ------------------------------ |
| `1cf751f6-8749-43ab-98bd-230dd633abdb` | Ana Paula - Marketer          | <AudioPlayer title="Ana Paula - Marketer" />          | feminine  | Adult | Warm, friendly female for natural, informal dialogue                                             | Voice Agents, Customer Support |
| `d4b44b9a-82bc-4b65-b456-763fce4c52f9` | Beatriz - Support Guide       | <AudioPlayer title="Beatriz - Support Guide" />       | feminine  | Adult | Friendly, natural female for engaging conversation                                               | Voice Agents, Customer Support |
| `b603811e-54c2-4a0a-8854-09eab9ffa63f` | Bruno - Reliable Communicator | <AudioPlayer title="Bruno - Reliable Communicator" /> | masculine | Adult | Clear, dependable Brazilian male built for corporate communication.                              | Voice Agents, Customer Support |
| `5063f45b-d9e0-4095-b056-8f3ee055d411` | Camilo - Supporter            | <AudioPlayer title="Camilo - Supporter" />            | masculine | Adult | Soothing, warm male for feel good conversations                                                  | Voice Agents, Customer Support |
| `fbee0e7d-a83a-4082-bad1-13c70f86da4e` | Diogo - Promotion Lead        | <AudioPlayer title="Diogo - Promotion Lead" />        | masculine | Adult | Strong and expressive adult male voice for narrations, commercials, and persuasive communication | Voice Agents, Customer Support |
| `a37639f0-2f0a-4de4-9942-875a187af878` | Felipe - Casual Talker        | <AudioPlayer title="Felipe - Casual Talker" />        | masculine | Adult | Relaxed, conversational male for reassuring conversation                                         | Voice Agents, Customer Support |
| `28a942b5-74f3-47bb-9b56-4c3f2562d3ba` | Gustavo - Steady Advisor      | <AudioPlayer title="Gustavo - Steady Advisor" />      | masculine | Adult | Calm, measured Brazilian male suited for professional communication.                             | Voice Agents, Customer Support |
| `b0f46533-d4bb-493f-a26f-a99e1f2e86e3` | Heitor - Easygoing Local      | <AudioPlayer title="Heitor - Easygoing Local" />      | masculine | Adult | Warm, relatable young adult male with a down-to-earth countryside charm                          | Voice Agents, Customer Support |
| `6a16c1f4-462b-44de-998d-ccdaa4125a0a` | Hidalgo - Anchorperson        | <AudioPlayer title="Hidalgo - Anchorperson" />        | masculine | Adult | Lively, confident male for announcements                                                         | Voice Agents, Customer Support |
| `f39bf583-3b3d-402f-9ffb-6179d9ec3e35` | Isabel - Confident Woman      | <AudioPlayer title="Isabel - Confident Woman" />      | feminine  | Adult | Confident, clear, and firm adult female voice for giving instructions, guidance, and…            | Voice Agents, Customer Support |
| `c9611be8-aae9-4a93-bb1c-98dd6b7d52a4` | Isabella - Warm Storyteller   | <AudioPlayer title="Isabella - Warm Storyteller" />   | feminine  | Adult | Rich, expressive Brazilian female perfect for narration.                                         | Voice Agents, Customer Support |
| `8d826d43-20ad-4c56-8d37-1048eccca1bf` | Larissa - Bright Companion    | <AudioPlayer title="Larissa - Bright Companion" />    | feminine  | Adult | Friendly, approachable Brazilian female for everyday interactions.                               | Voice Agents, Customer Support |
| `700d1ee3-a641-4018-ba6e-899dcadc9e2b` | Luana - Public Speaker        | <AudioPlayer title="Luana - Public Speaker" />        | feminine  | Adult | Pleasant, clear female for casual conversation                                                   | Voice Agents, Customer Support |
| `2f4d204f-a5dc-4196-81bc-155986b76ab6` | Mirella - Upbeat Speaker      | <AudioPlayer title="Mirella - Upbeat Speaker" />      | feminine  | Adult | Bright, youthful female voice for friendly, everyday dialogue                                    | Voice Agents, Customer Support |
| `07b6f895-78b9-4921-8e10-8a21c99c2e8a` | Rafael - Dynamic Speaker      | <AudioPlayer title="Rafael - Dynamic Speaker" />      | masculine | Adult | Engaging, charismatic Brazilian male that captures attention for media.                          | Voice Agents, Customer Support |
| `6a360542-a117-4ed5-9e09-e8bf9b05eabb` | Tiago - Narration Expert      | <AudioPlayer title="Tiago - Narration Expert" />      | masculine | Adult | Calm, clear male for narrations                                                                  | Voice Agents, Customer Support |

## Arabic

| Voice ID                               | Name                            | Sample                                                  | Gender    | Age   | Tone                                                                                             | Use Case                       |
| -------------------------------------- | ------------------------------- | ------------------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------ | ------------------------------ |
| `6304c635-6681-4f9e-85b6-a97f4d26461a` | Amira - Dreamy Whisperer        | <AudioPlayer title="Amira - Dreamy Whisperer" />        | feminine  | Adult | Calm, soft-spoken adult female for narrations and storytelling                                   | Voice Agents, Customer Support |
| `218a8026-7a26-4dc5-9753-9e75dffe1ea6` | Dina - Trusted Advisor          | <AudioPlayer title="Dina - Trusted Advisor" />          | feminine  | Adult | Confident, measured delivery that conveys expertise for communications.                          | Voice Agents, Customer Support |
| `731ace69-ee17-41bc-8c6f-665c9f1db95c` | Fatima - Graceful Guide         | <AudioPlayer title="Fatima - Graceful Guide" />         | feminine  | Adult | Polite, steady Arabic female for customer service.                                               | Voice Agents, Customer Support |
| `664aec8a-64a4-4437-8a0b-a61aa4f51fe6` | Hassan - Authoritative Narrator | <AudioPlayer title="Hassan - Authoritative Narrator" /> | masculine | Adult | Strong, authoritative voice for instructions, narration, and news-style delivery                 | Voice Agents, Customer Support |
| `002622d8-19d0-4567-a16a-f99c7397c062` | Huda - Approachable Speaker     | <AudioPlayer title="Huda - Approachable Speaker" />     | feminine  | Adult | Natural voice for clear, engaging conversations                                                  | Voice Agents, Customer Support |
| `9825cf5f-6aff-412a-80c5-bc58a8d55bc4` | Maryam - Friendly Voice         | <AudioPlayer title="Maryam - Friendly Voice" />         | feminine  | Adult | Voice with warm, conversational tone and natural rhythm, ideal for approachable conversations    | Voice Agents, Customer Support |
| `fc923f89-1de5-4ddf-b93c-6da2ba63428a` | Nour - Engaging Speaker         | <AudioPlayer title="Nour - Engaging Speaker" />         | feminine  | Adult | Smooth, expressive voice for engaging customer interactions                                      | Voice Agents, Customer Support |
| `e3087ad8-7018-4154-9a87-11577f916cd4` | Omar - High-Energy Presenter    | <AudioPlayer title="Omar - High-Energy Presenter" />    | masculine | Adult | Lively, energetic adult male for engaging conversations and dynamic narration                    | Voice Agents, Customer Support |
| `98bf39ce-b44a-49d7-9794-fb9a9329fd11` | Rania - Spirited Storyteller    | <AudioPlayer title="Rania - Spirited Storyteller" />    | feminine  | Adult | Expressive, lively Arabic female that brings scripts and ads to life.                            | Voice Agents, Customer Support |
| `db873303-3a70-4d9d-867a-0d70a6377195` | Tariq - Wise Advisor            | <AudioPlayer title="Tariq - Wise Advisor" />            | masculine | Adult | Calm, measured Arabic male suited for reassuring communication.                                  | Voice Agents, Customer Support |
| `f1cdfb4a-bf7d-4e83-916e-8f0802278315` | Walid - Steady Presence         | <AudioPlayer title="Walid - Steady Presence" />         | masculine | Adult | Warm, confident voice for clear, customer-facing conversations                                   | Voice Agents, Customer Support |
| `9cbad5f7-fbf6-4416-a22f-1ecc75ad40a2` | Youssef - Clear Communicator    | <AudioPlayer title="Youssef - Clear Communicator" />    | masculine | Adult | Articulate delivery designed for seamless instructional content.                                 | Voice Agents, Customer Support |
| `40f9b5d1-bc79-43a6-b5cc-1c692b3b40d2` | Zain - Dynamic Presenter        | <AudioPlayer title="Zain - Dynamic Presenter" />        | masculine | Adult | Engaging Arabic male that captures attention for customer experience.                            | Voice Agents, Customer Support |
| `b0aa4612-81d2-4df3-9730-3fc064754b1f` | Khalid - Bright Energy          | <AudioPlayer title="Khalid - Bright Energy" />          | masculine | Adult | Voice with cheerful tone and expressive clarity, perfect for engaging advertisements and lively… | Voice Agents, Customer Support |

## Chinese

| Voice ID                               | Name                       | Sample                                             | Gender    | Age   | Tone                                                                                             | Use Case                       |
| -------------------------------------- | -------------------------- | -------------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------ | ------------------------------ |
| `0b904166-a29f-4d2e-bb20-41ca302f98e9` | Fei - Broadcast Narrator   | <AudioPlayer title="Fei - Broadcast Narrator" />   | feminine  | Adult | Cheery, confident adult woman for narrations and announcements                                   | Voice Agents, Customer Support |
| `16212f18-4955-4be9-a6cd-2196ce2c11d1` | Hao - Friendly Guy         | <AudioPlayer title="Hao - Friendly Guy" />         | masculine | Adult | Warm and friendly adult male voice for approachable conversations, customer support, and casual… | Voice Agents, Customer Support |
| `7a5d4663-88ae-47b7-808e-8f9b9ee4127b` | Hua - Sunny Support        | <AudioPlayer title="Hua - Sunny Support" />        | feminine  | Adult | Upbeat, happy young adult woman for engaging conversations and conversational support            | Voice Agents, Customer Support |
| `7e2a44d1-76b8-42b8-9507-fedfe3a803c8` | Jian - Direct Dispatcher   | <AudioPlayer title="Jian - Direct Dispatcher" />   | masculine | Adult | Formal Mandarin male for structured and capable support.                                         | Voice Agents, Customer Support |
| `6eb8965c-e295-47bd-a9e4-3eeebb3abcff` | Jing - Clear Coordinator   | <AudioPlayer title="Jing - Clear Coordinator" />   | feminine  | Adult | Clear Mandarin female for reliable business communication.                                       | Voice Agents, Customer Support |
| `eda5bbff-1ff1-4886-8ef1-4e69a77640a0` | Kai - Commercial Man       | <AudioPlayer title="Kai - Commercial Man" />       | masculine | Adult | Deep, friendly adult male for commercials and advertising                                        | Voice Agents, Customer Support |
| `bf32f849-7bc9-4b91-8c62-954588efcc30` | Lan - Instructor           | <AudioPlayer title="Lan - Instructor" />           | feminine  | Adult | Firm, neutral adult woman for providing guidance and instruction                                 | Voice Agents, Customer Support |
| `653b9445-ae0c-4312-a3ce-375504cff31e` | Liu - Plain Talker         | <AudioPlayer title="Liu - Plain Talker" />         | masculine | Adult | Casual, neutral adult man for conversational support use cases                                   | Voice Agents, Customer Support |
| `a53c3509-ec3f-425c-a223-977f5f7424dd` | Mei - Expressive Assistant | <AudioPlayer title="Mei - Expressive Assistant" /> | feminine  | Adult | Expressive adult female voice with a lively and engaging tone for storytelling, advertisements,… | Voice Agents, Customer Support |
| `f9a4b3a6-b44b-469f-90e3-c8e19bd30e99` | Shuwen - Precision Guide   | <AudioPlayer title="Shuwen - Precision Guide" />   | feminine  | Adult | Neutral, firm female for providing guidance and instruction                                      | Voice Agents, Customer Support |
| `c59c247b-6aa9-4ab6-91f9-9eabea7dc69e` | Tao - Lecturer             | <AudioPlayer title="Tao - Lecturer" />             | masculine | Adult | Friendly young adult male for presentations and educational content                              | Voice Agents, Customer Support |
| `e90c6678-f0d3-4767-9883-5d0ecf5894a8` | Yue - Gentle Woman         | <AudioPlayer title="Yue - Gentle Woman" />         | feminine  | Adult | Kind adult female for empathetic conversations                                                   | Voice Agents, Customer Support |

## Dutch

| Voice ID                               | Name                          | Sample                                                | Gender    | Age   | Tone                                                                                         | Use Case                       |
| -------------------------------------- | ----------------------------- | ----------------------------------------------------- | --------- | ----- | -------------------------------------------------------------------------------------------- | ------------------------------ |
| `ac317dac-1b8f-434f-b198-a490e2a4914d` | Anneke - Trusted Guide        | <AudioPlayer title="Anneke - Trusted Guide" />        | feminine  | Adult | Soft-spoken adult female voice with a warm and caring tone for supportive conversations and… | Voice Agents, Customer Support |
| `225ba8cf-9fc2-4371-a78c-fe38ba38898a` | Anneliese - Methodical Guide  | <AudioPlayer title="Anneliese - Methodical Guide" />  | feminine  | Adult | Clear, articulate Dutch female for efficient professional assistance.                        | Voice Agents, Customer Support |
| `4aa74047-d005-4463-ba2e-a0d9b261fb87` | Bram - Instructional Voice    | <AudioPlayer title="Bram - Instructional Voice" />    | masculine | Adult | Clear male for tutorials and explainer videos                                                | Voice Agents, Customer Support |
| `9e8db62d-056f-47f3-b3b6-1b05767f9176` | Daan - Business Baritone      | <AudioPlayer title="Daan - Business Baritone" />      | masculine | Adult | Authoritative male for presentations                                                         | Voice Agents, Customer Support |
| `de075c71-b2dd-4723-848d-ea9aa9cd010b` | Fleur - Vibrant Voice         | <AudioPlayer title="Fleur - Vibrant Voice" />         | feminine  | Adult | Youthful, spirited Dutch female for friendly professional assistance.                        | Voice Agents, Customer Support |
| `60e94cf5-8069-459f-a91e-3ff852a51107` | Isa - Empathetic Ear          | <AudioPlayer title="Isa - Empathetic Ear" />          | feminine  | Adult | Warm, expressive Dutch female for supportive customer interactions                           | Voice Agents, Customer Support |
| `4b250449-c635-4b63-bd1d-b654b12ffcd4` | Jeroen - Clear Storyteller    | <AudioPlayer title="Jeroen - Clear Storyteller" />    | masculine | Adult | Clear and firm adult male voice for scientific reporting, documentaries, and professional…   | Voice Agents, Customer Support |
| `af482421-80f4-4379-b00c-a118def29cde` | Lucas - Storyteller           | <AudioPlayer title="Lucas - Storyteller" />           | masculine | Adult | Enunciating male for storytelling                                                            | Voice Agents, Customer Support |
| `96355f3d-0179-4c9a-a8d8-11ef0779a9b8` | Noa - Reassuring Responder    | <AudioPlayer title="Noa - Reassuring Responder" />    | feminine  | Adult | Soft, clear Dutch female for empathetic customer communication.                              | Voice Agents, Customer Support |
| `0eb213fe-4658-45bc-9442-33a48b24b133` | Sanne - Clear Companion       | <AudioPlayer title="Sanne - Clear Companion" />       | feminine  | Adult | Cheerful female for engaging conversations                                                   | Voice Agents, Customer Support |
| `da743a82-ddf2-4d9b-8eb8-ff67ca0b138e` | Stjin - Helpful Handler       | <AudioPlayer title="Stjin - Helpful Handler" />       | masculine | Adult | Approachable Dutch male for professional dialogue.                                           | Voice Agents, Customer Support |
| `95e9fdaf-cf0b-4739-b1de-3350ca50774a` | Thijs - Confident Coordinator | <AudioPlayer title="Thijs - Confident Coordinator" /> | masculine | Adult | Clear, methodical Dutch male for reassuring professional dialogue.                           | Voice Agents, Customer Support |

## Italian

| Voice ID                               | Name                               | Sample                                                     | Gender    | Age   | Tone                                                                                         | Use Case                       |
| -------------------------------------- | ---------------------------------- | ---------------------------------------------------------- | --------- | ----- | -------------------------------------------------------------------------------------------- | ------------------------------ |
| `0e21713a-5e9a-428a-bed4-90d410b87f13` | Alessandra - Melodic Guide         | <AudioPlayer title="Alessandra - Melodic Guide" />         | feminine  | Adult | Graceful female for providing instructions and guidance                                      | Voice Agents, Customer Support |
| `d609f27f-f1a4-410f-85bb-10037b4fba99` | Francesca - Elegant Partner        | <AudioPlayer title="Francesca - Elegant Partner" />        | feminine  | Adult | Enunciating female for natural conversations                                                 | Voice Agents, Customer Support |
| `029c3c7a-b6d9-44f0-814b-200d849830ff` | Giancarlo - Support Leader         | <AudioPlayer title="Giancarlo - Support Leader" />         | masculine | Adult | Deep male for conversational support                                                         | Voice Agents, Customer Support |
| `36d94908-c5b9-4014-b521-e69aee5bead0` | Giulia - Teacherly Voice           | <AudioPlayer title="Giulia - Teacherly Voice" />           | feminine  | Adult | Firm and clear adult female voice for lectures, guidance, and authoritative storytelling     | Voice Agents, Customer Support |
| `88b329db-85d7-47cc-a5c5-98225a756721` | Giuseppe - Retro Man               | <AudioPlayer title="Giuseppe - Retro Man" />               | masculine | Adult | Vintage-style adult male voice with a nostalgic old-radio tone for historical reenactments,… | Voice Agents, Customer Support |
| `d718e944-b313-4998-b011-d1cc078d4ef3` | Liv - Casual Friend                | <AudioPlayer title="Liv - Casual Friend" />                | feminine  | Adult | Casual female for natural conversations                                                      | Voice Agents, Customer Support |
| `ee16f140-f6dc-490e-a1ed-c1d537ea0086` | Lorenzo - Hospitable Host          | <AudioPlayer title="Lorenzo - Hospitable Host" />          | masculine | Adult | Approachable Italian adult male for natural, everyday communication.                         | Voice Agents, Customer Support |
| `e019ed7e-6079-4467-bc7f-b599a5dccf6f` | Luca - Everyday Friend             | <AudioPlayer title="Luca - Everyday Friend" />             | masculine | Adult | Casual male for natural conversations                                                        | Voice Agents, Customer Support |
| `e5923af7-a329-4e9b-b95a-5ace4a083535` | Lucio - Empath                     | <AudioPlayer title="Lucio - Empath" />                     | masculine | Adult | Charismatic and engaging male for expressive dialogue                                        | Voice Agents, Customer Support |
| `79693aee-1207-4771-a01e-20c393c89e6f` | Marco - Friendly Conversationalist | <AudioPlayer title="Marco - Friendly Conversationalist" /> | masculine | Adult | Friendly and professional male for conversational support                                    | Voice Agents, Customer Support |
| `408daed0-c597-4c27-aae8-fa0497d644bf` | Matteo - Gentle Narrator           | <AudioPlayer title="Matteo - Gentle Narrator" />           | masculine | Adult | Reassuring male for soothing dialogue                                                        | Voice Agents, Customer Support |
| `90c7d657-9599-4cd0-9ed2-2568359e4d1a` | Sofia - Methodical Moderator       | <AudioPlayer title="Sofia - Methodical Moderator" />       | feminine  | Adult | Polished adult female for efficient transactional assistance.                                | Voice Agents, Customer Support |

## Polish

| Voice ID                               | Name                              | Sample                                                  | Gender    | Age   | Tone                                                                                           | Use Case                       |
| -------------------------------------- | --------------------------------- | ------------------------------------------------------- | --------- | ----- | ---------------------------------------------------------------------------------------------- | ------------------------------ |
| `6bc7c014-022b-42ce-8b53-a5ec878a7ca7` | Agnieszka - Coordinator           | <AudioPlayer title="Agnieszka - Coordinator" />         | feminine  | Adult | Formal adult female for direct and capable assistance.                                         | Voice Agents, Customer Support |
| `887149a8-4616-42ad-b2ce-c3819176f45d` | Andrzej - Elder Voice             | —                                                       | masculine | Adult | Wise-sounding elderly male voice with a calm and casual tone for storytelling, guidance, and…  | Voice Agents, Customer Support |
| `f8aacd6e-1ac2-42d3-bcbf-125336ecd0f2` | Ewa - Efficient Envoy             | <AudioPlayer title="Ewa - Efficient Envoy" />           | feminine  | Adult | Professional Polish female for efficient, everyday dialogue.                                   | Voice Agents, Customer Support |
| `2a3503b2-b6b6-4534-a224-e8c0679cec4a` | Jakub - Gentle Guide              | <AudioPlayer title="Jakub - Gentle Guide" />            | masculine | Adult | Clear male for narrations                                                                      | Voice Agents, Customer Support |
| `43e52207-96fc-4e01-aaf8-cae317e43fdb` | Kacper - Diligent Detailer        | <AudioPlayer title="Kacper - Diligent Detailer" />      | masculine | Adult | Methodical Polish male for precise and efficient support.                                      | Voice Agents, Customer Support |
| `ea7b5eee-39d9-40b0-b241-1910cbca9c62` | Kasia - Natural Conversationalist | —                                                       | feminine  | Adult | Approachable adult female voice with a natural and casual tone for everyday conversations and… | Voice Agents, Customer Support |
| `575a5d29-1fdc-4d4e-9afa-5a9a71759864` | Katarzyna - Melodic Storyteller   | <AudioPlayer title="Katarzyna - Melodic Storyteller" /> | feminine  | Adult | Melodic female for storytelling                                                                | Voice Agents, Customer Support |
| `d358377a-cd1d-45c5-abd0-701314e36cbe` | Marcin - Charismatic Presenter    | <AudioPlayer title="Marcin - Charismatic Presenter" />  | masculine | Adult | Bright, energetic Polish male that brings scripts to life.                                     | Voice Agents, Customer Support |
| `3d335974-4c4a-400a-84dc-ebf4b73aada6` | Piotr - Corporate Lead            | <AudioPlayer title="Piotr - Corporate Lead" />          | masculine | Adult | Confident male for providing instructions                                                      | Voice Agents, Customer Support |
| `82a7fc13-2927-4e42-9b8a-bb1f9e506521` | Tomek - Casual Companion          | <AudioPlayer title="Tomek - Casual Companion" />        | masculine | Adult | Energetic male for casual conversations                                                        | Voice Agents, Customer Support |
| `4ef93bb3-682a-46e6-b881-8e157b6b4388` | Wojciech - Documentarian          | <AudioPlayer title="Wojciech - Documentarian" />        | masculine | Adult | Deep male for narrations and documentary media                                                 | Voice Agents, Customer Support |
| `dcf62f33-7cff-4f20-85b2-2efaa68cbc32` | Zofia - Audiobook Muse            | <AudioPlayer title="Zofia - Audiobook Muse" />          | feminine  | Adult | Expressive female for clear communication                                                      | Voice Agents, Customer Support |

## Russian

| Voice ID                               | Name                           | Sample                                                 | Gender    | Age   | Tone                                                                                          | Use Case                       |
| -------------------------------------- | ------------------------------ | ------------------------------------------------------ | --------- | ----- | --------------------------------------------------------------------------------------------- | ------------------------------ |
| `069ff31a-5524-4945-a403-f746ee617507` | Alexei - Articulate Analyst    | <AudioPlayer title="Alexei - Articulate Analyst" />    | masculine | Adult | Polished Russian voice for capable transactional assistance.                                  | Voice Agents, Customer Support |
| `25b7aaa6-1670-42dc-b791-419322400803` | Daria - Decisive Dispatcher    | <AudioPlayer title="Daria - Decisive Dispatcher" />    | feminine  | Adult | Confident adult female for direct and capable assistance.                                     | Voice Agents, Customer Support |
| `888b7df4-e165-4852-bfec-0ab2b96aaa46` | Dmitri - Gentle Voice          | <AudioPlayer title="Dmitri - Gentle Voice" />          | masculine | Adult | Approachable adult male voice with a relaxed tone for casual chats and everyday conversations | Voice Agents, Customer Support |
| `642014de-c0e3-4133-adc0-36b5309c23e6` | Irina - Poetic Voice           | <AudioPlayer title="Irina - Poetic Voice" />           | feminine  | Adult | Graceful female for narrations and audiobooks                                                 | Voice Agents, Customer Support |
| `7a62541e-5492-410e-95ff-3abd096fce87` | Natalia - Steady Strategist    | <AudioPlayer title="Natalia - Steady Strategist" />    | feminine  | Adult | Measured Russian female for highly structured communication.                                  | Voice Agents, Customer Support |
| `779673f3-895f-4935-b6b5-b031dc78b319` | Natalya - Soothing Guide       | <AudioPlayer title="Natalya - Soothing Guide" />       | feminine  | Adult | Serene female for relaxing audio                                                              | Voice Agents, Customer Support |
| `9ed9f7e7-3ef6-4773-9dd3-ffcb479ca1f0` | Olga - Confident Saleswoman    | <AudioPlayer title="Olga - Confident Saleswoman" />    | feminine  | Adult | Upbeat and confident adult female voice for presentations and engaging customer interactions  | Voice Agents, Customer Support |
| `1e4176b1-3db9-44d6-a601-4fe68b041942` | Sergei - Steady Supporter      | <AudioPlayer title="Sergei - Steady Supporter" />      | masculine | Adult | Reliable Russian male for clear, efficient dialogue.                                          | Voice Agents, Customer Support |
| `064b17af-d36b-4bfb-b003-be07dba1b649` | Tatiana - Friendly Storyteller | <AudioPlayer title="Tatiana - Friendly Storyteller" /> | feminine  | Adult | Friendly female for audiobooks and clear communication                                        | Voice Agents, Customer Support |

## Swedish

| Voice ID                               | Name                          | Sample                                                | Gender    | Age   | Tone                                                                                                | Use Case                       |
| -------------------------------------- | ----------------------------- | ----------------------------------------------------- | --------- | ----- | --------------------------------------------------------------------------------------------------- | ------------------------------ |
| `38a146c3-69d7-40ad-aada-76d5a2621758` | Anders - Nordic Baritone      | <AudioPlayer title="Anders - Nordic Baritone" />      | masculine | Adult | Deep male for historical narrations                                                                 | Voice Agents, Customer Support |
| `b576c504-cbd1-4224-af06-04067c5a5e3e` | Astrid - Direct Director      | <AudioPlayer title="Astrid - Direct Director" />      | feminine  | Adult | Polished Swedish female for efficient corporate assistance.                                         | Voice Agents, Customer Support |
| `0caedb75-417f-4e36-9b64-c21354cb94c8` | Cees - Nordic Narrator        | <AudioPlayer title="Cees - Nordic Narrator" />        | masculine | Adult | Enunciating male for smooth conversations                                                           | Voice Agents, Customer Support |
| `00510a15-4216-4fdc-a0ab-05d74cd9f795` | Elina - Clear Presenter Woman | <AudioPlayer title="Elina - Clear Presenter Woman" /> | feminine  | Adult | Firm and professional adult female voice for news delivery, announcements, and formal presentations | Voice Agents, Customer Support |
| `32a806e8-894e-41ad-a4d5-6d9154d7b1e6` | Erik - Social Speaker         | <AudioPlayer title="Erik - Social Speaker" />         | masculine | Adult | Relaxed and approachable adult male voice for casual conversations and natural everyday dialogue    | Voice Agents, Customer Support |
| `6c6b05bf-ae5f-4013-82ab-7348e99ffdb2` | Freja - Nordic Reader         | <AudioPlayer title="Freja - Nordic Reader" />         | feminine  | Adult | Expressive female for clear communication                                                           | Voice Agents, Customer Support |
| `eede54e1-c038-4b4d-b655-809eeaa45c4c` | Henrik - Refined Narrator     | <AudioPlayer title="Henrik - Refined Narrator" />     | masculine | Adult | Smooth, polished Swedish male suited for premium content.                                           | Voice Agents, Customer Support |
| `f852eb8d-a177-48cd-bf63-7e4dcab61a36` | Ingrid - Peaceful Guide       | <AudioPlayer title="Ingrid - Peaceful Guide" />       | feminine  | Adult | Serene female for relaxing narrations                                                               | Voice Agents, Customer Support |
| `8c889eba-5b31-4179-8fb2-37bbee22db64` | Nils - Friendly Host          | <AudioPlayer title="Nils - Friendly Host" />          | masculine | Adult | Warm, genuine Swedish male for podcasts and conversational platforms.                               | Voice Agents, Customer Support |

## Tagalog

| Voice ID                               | Name                      | Sample                                            | Gender    | Age   | Tone                                                                                             | Use Case                       |
| -------------------------------------- | ------------------------- | ------------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------ | ------------------------------ |
| `d1c819ba-0384-496b-b63b-eb57a96a43cc` | Angel - Welcoming Host    | <AudioPlayer title="Angel - Welcoming Host" />    | feminine  | Adult | Hospitable and warm articulation that puts the listener at ease.                                 | Voice Agents, Customer Support |
| `c4cbcb7d-d9fa-4eac-b547-46831718ef58` | Angelo - Calm Narrator    | <AudioPlayer title="Angelo - Calm Narrator" />    | masculine | Adult | Gentle young adult male voice with a calm and approachable tone for casual conversations,…       | Voice Agents, Customer Support |
| `42332792-6e9f-4b2c-a106-3ff97e34a79d` | Jerome - Empathetic Voice | <AudioPlayer title="Jerome - Empathetic Voice" /> | masculine | Adult | Gentle and reassuring tone designed to offer comfort and build trust.                            | Voice Agents, Customer Support |
| `8bfb1d08-a77a-4a7c-a4b7-af377380c6eb` | Joy - Crisp Narrator      | <AudioPlayer title="Joy - Crisp Narrator" />      | feminine  | Adult | Sharp and precise delivery ideal for clearly explaining complex topics.                          | Voice Agents, Customer Support |
| `5cd73b8e-703e-4f73-9e30-56876c620204` | Juan - Clear Communicator | <AudioPlayer title="Juan - Clear Communicator" /> | masculine | Adult | Crisp and articulate delivery designed for seamless information sharing.                         | Voice Agents, Customer Support |
| `21d8f579-b69c-42f0-8313-c50c6be05531` | Liezel - Steady Informer  | <AudioPlayer title="Liezel - Steady Informer" />  | feminine  | Adult | Reliable and consistent tone for general communication.                                          | Voice Agents, Customer Support |
| `9261664a-c3d0-4200-9038-5466bcf3a09c` | Luz - Casual Speaker      | <AudioPlayer title="Luz - Casual Speaker" />      | feminine  | Adult | Natural and conversational adult female voice for everyday dialogue, friendly interactions, and… | Voice Agents, Customer Support |
| `6d14ac2a-4dda-46f8-bd6f-0722db08ec00` | Mae - Calm Authority      | <AudioPlayer title="Mae - Calm Authority" />      | feminine  | Adult | Grounded and soothing voice that conveys confidence.                                             | Voice Agents, Customer Support |

## Telugu

| Voice ID                               | Name                            | Sample                                                  | Gender    | Age   | Tone                                                                                                | Use Case                       |
| -------------------------------------- | ------------------------------- | ------------------------------------------------------- | --------- | ----- | --------------------------------------------------------------------------------------------------- | ------------------------------ |
| `76961778-5ce4-4aa9-9cdf-66a029d61a8f` | Bhavani - Reassuring Companion  | <AudioPlayer title="Bhavani - Reassuring Companion" />  | feminine  | Adult | Soft and understanding tone for conveying genuine care and empathy.                                 | Voice Agents, Customer Support |
| `ebecd063-10f4-422e-a8ff-556ce5c4d4e4` | Pavan - Bright Voice            | <AudioPlayer title="Pavan - Bright Voice" />            | masculine | Adult | Voice with energetic clarity and upbeat tone, ideal for customer support and engaging communication | Voice Agents, Customer Support |
| `cf061d8b-a752-4865-81a2-57570a6e0565` | Ramya - Graceful Host           | <AudioPlayer title="Ramya - Graceful Host" />           | feminine  | Adult | Warm, welcoming Telugu female that puts listeners at ease instantly.                                | Voice Agents, Customer Support |
| `330c4fa0-1da3-4c55-8e97-951bfd724e20` | Sarika - Calm Spirit            | <AudioPlayer title="Sarika - Calm Spirit" />            | feminine  | Adult | Voice with laidback tone and gentle rhythm, perfect for relaxed, friendly, and conversational…      | Voice Agents, Customer Support |
| `4418bb06-8329-49a1-bb11-53bb64ca0547` | Shanti - Calm Authority         | <AudioPlayer title="Shanti - Calm Authority" />         | feminine  | Adult | Grounded and soothing voice that conveys confidence.                                                | Voice Agents, Customer Support |
| `07bc462a-c644-49f1-baf7-82d5599131be` | Sindhu - Conversational Partner | <AudioPlayer title="Sindhu - Conversational Partner" /> | feminine  | Adult | Clear and natural adult female voice for casual conversations and everyday interactions             | Voice Agents, Customer Support |
| `3a8e6fea-81e5-4d4d-8755-86093146cdb8` | Vidya - Empathetic Voice        | <AudioPlayer title="Vidya - Empathetic Voice" />        | feminine  | Adult | Gentle and reassuring tone designed to offer comfort and build trust.                               | Voice Agents, Customer Support |
| `38bded0a-3ab4-42d1-8e47-2e0b6b10ced9` | Vikram - Folk Narrator          | <AudioPlayer title="Vikram - Folk Narrator" />          | masculine | Adult | Expressive adult male voice with a colorful tone for storytelling, narrations, and engaging…        | Voice Agents, Customer Support |

## Turkish

| Voice ID                               | Name                          | Sample                                                | Gender    | Age   | Tone                                                                                         | Use Case                       |
| -------------------------------------- | ----------------------------- | ----------------------------------------------------- | --------- | ----- | -------------------------------------------------------------------------------------------- | ------------------------------ |
| `bb2347fe-69e9-4810-873f-ffd759fe8420` | Aylin - Warm Guide            | <AudioPlayer title="Aylin - Warm Guide" />            | feminine  | Adult | Friendly female for narrations and explainer videos                                          | Voice Agents, Customer Support |
| `0f95596c-09c4-4418-99fe-5c107e0713c0` | Azra - Service Specialist     | <AudioPlayer title="Azra - Service Specialist" />     | feminine  | Adult | Firm and clear adult voice with a professional tone for instructions, customer service, and… | Voice Agents, Customer Support |
| `8036098f-cff4-401e-bfba-f0a6a6e5e49b` | Elif - Structured Supporter   | <AudioPlayer title="Elif - Structured Supporter" />   | feminine  | Adult | Methodical adult female for precise and reliable assistance.                                 | Voice Agents, Customer Support |
| `39f753ef-b0eb-41cd-aa53-2f3c284f948f` | Emre - Calming Speaker        | <AudioPlayer title="Emre - Calming Speaker" />        | masculine | Adult | Soothing male for calming dialogue                                                           | Voice Agents, Customer Support |
| `fa7bfcdc-603c-4bf1-a600-a371400d2f8c` | Leyla - Story Companion       | <AudioPlayer title="Leyla - Story Companion" />       | feminine  | Adult | Expressive female for conversational support                                                 | Voice Agents, Customer Support |
| `5a31e4fb-f823-4359-aa91-82c0ae9a991c` | Murat - Anatolian Storyteller | <AudioPlayer title="Murat - Anatolian Storyteller" /> | masculine | Adult | Deep male for narrations and audiobooks                                                      | Voice Agents, Customer Support |
| `c1cfee3d-532d-47f8-8dd2-8e5b2b66bf1d` | Taylan - Expressive Voice     | <AudioPlayer title="Taylan - Expressive Voice" />     | masculine | Adult | Versatile articulate male for storytelling                                                   | Voice Agents, Customer Support |
| `91e91d74-8eb4-43cd-97d3-7466c21db00d` | Zehra - Friendly Companion    | <AudioPlayer title="Zehra - Friendly Companion" />    | masculine | Adult | Relaxed adult male voice with a natural and approachable tone for casual chats and everyday… | Voice Agents, Customer Support |

## Tamil

| Voice ID                               | Name                          | Sample                                                | Gender    | Age   | Tone                                                                                           | Use Case                       |
| -------------------------------------- | ----------------------------- | ----------------------------------------------------- | --------- | ----- | ---------------------------------------------------------------------------------------------- | ------------------------------ |
| `d4470f50-295e-4e11-82a2-158d45bf6abc` | Anitha - Warm Guide           | <AudioPlayer title="Anitha - Warm Guide" />           | feminine  | Adult | Inviting and approachable tone perfect for providing friendly guidance.                        | Voice Agents, Customer Support |
| `d2870b91-1b4c-47ab-81a8-3718d8e9c222` | Arun - Lively Voice           | <AudioPlayer title="Arun - Lively Voice" />           | masculine | Adult | Expressive adult voice with a lively tone for storytelling, narrations, and engaging cultural… | Voice Agents, Customer Support |
| `01d7796d-ac10-4ea3-8df0-3cc04f2d25ff` | Kavitha - Clear Communicator  | <AudioPlayer title="Kavitha - Clear Communicator" />  | feminine  | Adult | Crisp and articulate delivery designed for seamless information sharing.                       | Voice Agents, Customer Support |
| `25d2c432-139c-4035-bfd6-9baaabcdd006` | Kavya - Warm Presence         | <AudioPlayer title="Kavya - Warm Presence" />         | feminine  | Adult | Friendly voice with natural tone and smooth flow, ideal for everyday conversations             | Voice Agents, Customer Support |
| `7f98e662-142d-41ba-89a2-12452640ce6d` | Lakshmi - Everyday Voice      | <AudioPlayer title="Lakshmi - Everyday Voice" />      | feminine  | Adult | Casual and upbeat adult female voice for friendly conversations, everyday dialogue, and…       | Voice Agents, Customer Support |
| `4014f0c9-d3eb-4eca-af2b-fd6004f526be` | Meena - Measured Professional | <AudioPlayer title="Meena - Measured Professional" /> | feminine  | Adult | Steady and even pacing that offers a grounding presence for any script.                        | Voice Agents, Customer Support |
| `80e4e2b3-ec54-4930-97ac-667eba950352` | Nithya - Polished Presence    | <AudioPlayer title="Nithya - Polished Presence" />    | feminine  | Adult | Refined and smooth articulation suited for corporate messaging.                                | Voice Agents, Customer Support |

## Czech

| Voice ID                               | Name                           | Sample                                                 | Gender    | Age   | Tone                                                                                              | Use Case                       |
| -------------------------------------- | ------------------------------ | ------------------------------------------------------ | --------- | ----- | ------------------------------------------------------------------------------------------------- | ------------------------------ |
| `82db1f84-5b96-4364-b04a-4c7ff80e2f8a` | Jan - Capable Coordinator      | <AudioPlayer title="Jan - Capable Coordinator" />      | masculine | Adult | Clear, professional Czech male for trustworthy customer communication.                            | Voice Agents, Customer Support |
| `bdc4a3ce-2e22-4398-8cd6-76b7160d2298` | Jana - Crisp Conversationalist | <AudioPlayer title="Jana - Crisp Conversationalist" /> | feminine  | Adult | Clear and crisp female voice with a casual yet commanding tone for customer support and guidance  | Voice Agents, Customer Support |
| `0b6d3ccb-f421-4e49-80f7-4bfa39f6eb8e` | Marek - Steady Specialist      | <AudioPlayer title="Marek - Steady Specialist" />      | masculine | Adult | Resonant Czech male with a calm presence for expert support.                                      | Voice Agents, Customer Support |
| `b66b3a19-31b3-401f-8b08-40d46a61e4f1` | Milena - Composed Clarifier    | <AudioPlayer title="Milena - Composed Clarifier" />    | feminine  | Adult | Steady Czech voice for capable professional assistance.                                           | Voice Agents, Customer Support |
| `89266bab-6e15-455d-8654-e18c440b0656` | Petr - Pastor                  | <AudioPlayer title="Petr - Pastor" />                  | masculine | Adult | Resonant adult male voice, reminiscent of a priest delivering a sermon for narrations and formal… | Voice Agents, Customer Support |
| `f8685385-96f6-4c12-8520-49e4914bcbfe` | Tereza - Decisive Agent        | <AudioPlayer title="Tereza - Decisive Agent" />        | feminine  | Adult | Professional adult female for highly structured customer communication.                           | Voice Agents, Customer Support |

## Hebrew

| Voice ID                               | Name                        | Sample                                              | Gender    | Age   | Tone                                                                                             | Use Case                       |
| -------------------------------------- | --------------------------- | --------------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------ | ------------------------------ |
| `2821fd0c-35c7-4adf-9c42-32e394bf85cb` | Adi - Efficient Expert      | <AudioPlayer title="Adi - Efficient Expert" />      | feminine  | Adult | Articulate, professional Hebrew female for customer assistance.                                  | Voice Agents, Customer Support |
| `daa4d6bb-da62-4e16-8065-76cd87942475` | Eitan - Modern Communicator | <AudioPlayer title="Eitan - Modern Communicator" /> | masculine | Adult | Strong Hebrew male providing a clear tone for corporate messaging.                               | Voice Agents, Customer Support |
| `84b969ad-19c7-428d-b742-48d387f7f138` | Gil - Friendly Host         | <AudioPlayer title="Gil - Friendly Host" />         | masculine | Adult | Warm, genuine Hebrew male perfect for conversational experiences.                                | Voice Agents, Customer Support |
| `3e32f3c5-9ac0-4192-9994-87fdb277120f` | Noam - Broadcaster          | <AudioPlayer title="Noam - Broadcaster" />          | masculine | Adult | Clear and authoritative adult male voice for announcements, broadcasts, and formal presentations | Voice Agents, Customer Support |
| `431b7e77-b46d-4eda-8362-db430ac0913c` | Oren - Steady Advisor       | <AudioPlayer title="Oren - Steady Advisor" />       | masculine | Adult | Calm, measured Hebrew male suited for professional communication.                                | Voice Agents, Customer Support |
| `1daba551-67af-465e-a189-f91495aa2347` | Yael - Casual Presence      | <AudioPlayer title="Yael - Casual Presence" />      | feminine  | Adult | Voice with relaxed tone and friendly warmth, ideal for conversational dialogue and everyday…     | Voice Agents, Customer Support |

## Finnish

| Voice ID                               | Name                           | Sample                                                 | Gender    | Age   | Tone                                                                                        | Use Case                       |
| -------------------------------------- | ------------------------------ | ------------------------------------------------------ | --------- | ----- | ------------------------------------------------------------------------------------------- | ------------------------------ |
| `65c34eec-42c9-4a75-a8bd-b676fb847b72` | Helmi - Warm Friend            | <AudioPlayer title="Helmi - Warm Friend" />            | feminine  | Adult | Friendly adult female voice for casual conversations and everyday chat                      | Voice Agents, Customer Support |
| `8ccd7fcd-846a-4594-bde2-5feec2cba73a` | Jari - Reliable Representative | <AudioPlayer title="Jari - Reliable Representative" /> | masculine | Adult | Steady adult male for direct and efficient dialogue.                                        | Voice Agents, Customer Support |
| `7849a11e-4107-44ae-bc7e-77bea41ec019` | Matti - Measured Manager       | <AudioPlayer title="Matti - Measured Manager" />       | masculine | Adult | Steady adult male for structured professional interactions.                                 | Voice Agents, Customer Support |
| `ae1a833b-0d95-4b7f-8d05-d6418c6f8049` | Mikko - Narration Expert       | <AudioPlayer title="Mikko - Narration Expert" />       | masculine | Adult | Firm and strong adult male voice for narration, audiobooks, and authoritative communication | Voice Agents, Customer Support |
| `2835e382-643b-4ac6-8f6c-74df549a7ad0` | Milla - Modern Communicator    | <AudioPlayer title="Milla - Modern Communicator" />    | feminine  | Adult | Crisp, natural Finnish female for customer assistance.                                      | Voice Agents, Customer Support |

## Thai

| Voice ID                               | Name                            | Sample                                                  | Gender    | Age   | Tone                                                                                              | Use Case                       |
| -------------------------------------- | ------------------------------- | ------------------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------- | ------------------------------ |
| `aaa0bf6d-bc07-40f2-bc6b-66afc5fd42f6` | Chakrit - Reliable Communicator | <AudioPlayer title="Chakrit - Reliable Communicator" /> | masculine | Adult | Clear, dependable Thai male built for public communications.                                      | Voice Agents, Customer Support |
| `a50a04b8-35ee-487e-8b87-97f0eee68a64` | Krit - Efficient Envoy          | <AudioPlayer title="Krit - Efficient Envoy" />          | masculine | Adult | Professional adult male for smooth, everyday dialogue.                                            | Voice Agents, Customer Support |
| `5de076e9-7b28-4442-b279-e7d80d573505` | Somchai - Star                  | <AudioPlayer title="Somchai - Star" />                  | masculine | Adult | Upbeat and confident adult male voice for commercials, brand promotions, and lively presentations | Voice Agents, Customer Support |
| `ccc7bb22-dcd0-42e4-822e-0731b950972f` | Suda - Fortune Teller           | <AudioPlayer title="Suda - Fortune Teller" />           | feminine  | Adult | Expressive adult female voice with lively pronunciation for storytelling, advertisements, and…    | Voice Agents, Customer Support |
| `db938869-18b5-4c21-be8b-2ffdfba6d8d4` | Thaksin - Tactful Tracker       | <AudioPlayer title="Thaksin - Tactful Tracker" />       | masculine | Adult | Methodical adult male for structured professional interactions.                                   | Voice Agents, Customer Support |

## Danish

| Voice ID                               | Name                         | Sample                                               | Gender    | Age   | Tone                                                                                           | Use Case                       |
| -------------------------------------- | ---------------------------- | ---------------------------------------------------- | --------- | ----- | ---------------------------------------------------------------------------------------------- | ------------------------------ |
| `c323c793-41f9-47b8-99dc-9b44b0440b84` | Katrine - Calm Caregiver     | <AudioPlayer title="Katrine - Calm Caregiver" />     | feminine  | Adult | Soft and calm adult female voice for meditation, relaxation, and gentle conversations          | Voice Agents, Customer Support |
| `eb929394-68e7-4e08-bd2f-e7055728a5e1` | Mette - Polished Facilitator | <AudioPlayer title="Mette - Polished Facilitator" /> | feminine  | Adult | Bright, professional Danish female for welcoming customer service.                             | Voice Agents, Customer Support |
| `926e0766-f380-4d77-aeb0-9aa4ebb16b38` | Soren - Executive Voice      | <AudioPlayer title="Soren - Executive Voice" />      | masculine | Adult | Voice with confident, businesslike tone and clear precision, perfect for professional dialogue | Voice Agents, Customer Support |
| `a466f9e2-28eb-4bb7-925c-8e8984950700` | Søren - Steady Strategist    | <AudioPlayer title="Søren - Steady Strategist" />    | masculine | Adult | Steady, Danish male voice for reassuring professional dialogue.                                | Voice Agents, Customer Support |

## Hungarian

| Voice ID                               | Name                        | Sample                                              | Gender    | Age   | Tone                                                                                                | Use Case                       |
| -------------------------------------- | --------------------------- | --------------------------------------------------- | --------- | ----- | --------------------------------------------------------------------------------------------------- | ------------------------------ |
| `4c5c7be8-6b3b-4c62-b915-c54d049c198f` | Bence - Focused Facilitator | <AudioPlayer title="Bence - Focused Facilitator" /> | masculine | Adult | Professional adult male for highly structured communication.                                        | Voice Agents, Customer Support |
| `e97c3b37-1aa5-46af-afb7-9545086aaa92` | Eszter - Customer Companion | <AudioPlayer title="Eszter - Customer Companion" /> | feminine  | Adult | Clear and cheerful adult female voice for customer support and friendly interactions                | Voice Agents, Customer Support |
| `36e0c00b-1bfd-4ad7-a0e8-928d4cadca00` | Gabor - Reassuring Voice    | <AudioPlayer title="Gabor - Reassuring Voice" />    | masculine | Adult | Firm and well-paced adult male voice for customer support, guidance, and professional communication | Voice Agents, Customer Support |

## Vietnamese

| Voice ID                               | Name                          | Sample                                                | Gender    | Age   | Tone                                                                                               | Use Case                       |
| -------------------------------------- | ----------------------------- | ----------------------------------------------------- | --------- | ----- | -------------------------------------------------------------------------------------------------- | ------------------------------ |
| `935a9060-373c-49e4-b078-f4ea6326987a` | Linh - Soft Presence          | <AudioPlayer title="Linh - Soft Presence" />          | feminine  | Adult | Voice with gentle tone and natural warmth, perfect for natural conversations and friendly dialogue | Voice Agents, Customer Support |
| `0e58d60a-2f1a-4252-81bd-3db6af45fb41` | Minh - Conversational Partner | <AudioPlayer title="Minh - Conversational Partner" /> | masculine | Adult | Easygoing adult male voice with a friendly tone for light conversation, casual dialogue, and…      | Voice Agents, Customer Support |
| `b8cd71e3-bc14-4538-a530-d6314731c036` | Xia - Calm Companion          | <AudioPlayer title="Xia - Calm Companion" />          | feminine  | Adult | Soft-spoken adult female voice for calm conversations and customer support                         | Voice Agents, Customer Support |

## Bengali

| Voice ID                               | Name                       | Sample                                             | Gender    | Age   | Tone                                                                         | Use Case                       |
| -------------------------------------- | -------------------------- | -------------------------------------------------- | --------- | ----- | ---------------------------------------------------------------------------- | ------------------------------ |
| `59ba7dee-8f9a-432f-a6c0-ffb33666b654` | Pooja - Everyday Assistant | <AudioPlayer title="Pooja - Everyday Assistant" /> | feminine  | Adult | Soft-spoken adult female voice for casual conversations and natural dialogue | Voice Agents, Customer Support |
| `2ba861ea-7cdc-43d1-8608-4045b5a41de5` | Rubel - City Guide         | <AudioPlayer title="Rubel - City Guide" />         | masculine | Adult | Casual adult male voice for everyday conversations and relatable dialogue    | Voice Agents, Customer Support |

## Bulgarian

| Voice ID                               | Name                         | Sample                                               | Gender    | Age   | Tone                                                                                              | Use Case                       |
| -------------------------------------- | ---------------------------- | ---------------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------- | ------------------------------ |
| `d132064c-b931-4a80-bf0d-02a331ec4572` | Georgi - Conversationalist   | <AudioPlayer title="Georgi - Conversationalist" />   | masculine | Adult | Friendly adult male with a casual tone for everyday conversations and relatable dialogue          | Voice Agents, Customer Support |
| `fcbecbcc-0cef-4615-8b5a-712fe1b39dd0` | Ivana - Instruction Provider | <AudioPlayer title="Ivana - Instruction Provider" /> | feminine  | Adult | Clear and authoritative adult female voice for giving instructions and professional communication | Voice Agents, Customer Support |

## Croatian

| Voice ID                               | Name                    | Sample                                          | Gender    | Age   | Tone                                                                                       | Use Case                       |
| -------------------------------------- | ----------------------- | ----------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------ | ------------------------------ |
| `a1a16724-b1f3-4b27-9e47-8a175115e93c` | Ivan - Bar Companion    | <AudioPlayer title="Ivan - Bar Companion" />    | masculine | Adult | Relaxed adult male voice for easygoing conversations                                       | Voice Agents, Customer Support |
| `2a2624ad-bd06-4563-81fd-0519742e25d2` | Petra - Strict Lecturer | <AudioPlayer title="Petra - Strict Lecturer" /> | feminine  | Adult | Firm and strict adult female voice for storytelling, guidance, and instructional use cases | Voice Agents, Customer Support |

## Georgian

| Voice ID                               | Name                        | Sample                                              | Gender    | Age   | Tone                                                                                      | Use Case                       |
| -------------------------------------- | --------------------------- | --------------------------------------------------- | --------- | ----- | ----------------------------------------------------------------------------------------- | ------------------------------ |
| `dbebd077-80cb-4bcf-b43b-4552f96341bb` | Levan - Support Guide       | <AudioPlayer title="Levan - Support Guide" />       | masculine | Adult | Casual and approachable adult male voice for customer support and everyday conversations  | Voice Agents, Customer Support |
| `0bfbea6c-2f8f-4f86-b411-aa2316561e36` | Tamara - Support Specialist | <AudioPlayer title="Tamara - Support Specialist" /> | feminine  | Adult | Professional and clear adult female voice for customer service, guidance, and supportive… | Voice Agents, Customer Support |

## Greek

| Voice ID                               | Name                      | Sample                                            | Gender    | Age   | Tone                                                                                              | Use Case                       |
| -------------------------------------- | ------------------------- | ------------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------- | ------------------------------ |
| `50849023-76e9-46c7-af52-9ec39888a165` | Despina - Motherly Woman  | <AudioPlayer title="Despina - Motherly Woman" />  | feminine  | Adult | Warm yet authoritative middle-aged female voice, with a motherly tone for guidance, reassurance,… | Voice Agents, Customer Support |
| `b45eba5b-2215-4da7-9c7c-121c95ed7b81` | Nikos - Radio Storyteller | <AudioPlayer title="Nikos - Radio Storyteller" /> | masculine | Adult | Nostalgic, middle-aged male voice with an old-radio tone for historical reenactments, vintage…    | Voice Agents, Customer Support |

## Gujarati

| Voice ID                               | Name                  | Sample                                        | Gender    | Age   | Tone                                                                                              | Use Case                       |
| -------------------------------------- | --------------------- | --------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------- | ------------------------------ |
| `91925fe5-42ee-4ebe-96c1-c84b12a85a32` | Amit - Sports Student | <AudioPlayer title="Amit - Sports Student" /> | masculine | Adult | Friendly young adult male voice for casual conversations and natural everyday dialogue            | Voice Agents, Customer Support |
| `4590a461-bc68-4a50-8d14-ac04f5923d22` | Isha - Learner        | <AudioPlayer title="Isha - Learner" />        | feminine  | Adult | Youthful female voice with a clear and approachable tone for narration, educational content, and… | Voice Agents, Customer Support |

## Indonesian

| Voice ID                               | Name                     | Sample                                           | Gender    | Age   | Tone                                                                                           | Use Case                       |
| -------------------------------------- | ------------------------ | ------------------------------------------------ | --------- | ----- | ---------------------------------------------------------------------------------------------- | ------------------------------ |
| `a053f6bc-7df4-40de-96d4-de026bc47ce8` | Andi - Dynamic Presenter | <AudioPlayer title="Andi - Dynamic Presenter" /> | masculine | Adult | Expressive adult male voice with an upbeat tone for advertisements, promotions, and lively…    | Voice Agents, Customer Support |
| `b441c4fd-4910-4c55-ae56-f0291057e2cc` | Siti - Ad Narrator       | <AudioPlayer title="Siti - Ad Narrator" />       | feminine  | Adult | Cheerful and optimistic adult female voice for brand placements, advertisements, and engaging… | Voice Agents, Customer Support |

## Kannada

| Voice ID                               | Name                    | Sample                                          | Gender    | Age   | Tone                                                                                              | Use Case                       |
| -------------------------------------- | ----------------------- | ----------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------- | ------------------------------ |
| `7c6219d2-e8d2-462c-89d8-7ecba7c75d65` | Divya - Joyful Narrator | <AudioPlayer title="Divya - Joyful Narrator" /> | feminine  | Adult | Lively and cheerful adult female voice for product advertisements, upbeat promotions, and happy…  | Voice Agents, Customer Support |
| `6baae46d-1226-45b5-a976-c7f9b797aae2` | Prakash - Instructor    | <AudioPlayer title="Prakash - Instructor" />    | masculine | Adult | Firm and articulate middle-aged male voice for lectures, presentations, and instructional content | Voice Agents, Customer Support |

## Malay

| Voice ID                               | Name                  | Sample                                        | Gender    | Age   | Tone                                                                                           | Use Case                       |
| -------------------------------------- | --------------------- | --------------------------------------------- | --------- | ----- | ---------------------------------------------------------------------------------------------- | ------------------------------ |
| `83604597-55fa-4ccc-8357-730b313f353f` | Aisyah - Chat Partner | <AudioPlayer title="Aisyah - Chat Partner" /> | feminine  | Adult | Friendly and upbeat adult female voice for casual conversations and engaging everyday dialogue | Voice Agents, Customer Support |
| `8281db18-6ac5-47bb-91a8-ce23a1f1d951` | Faiz - Family Guide   | <AudioPlayer title="Faiz - Family Guide" />   | masculine | Adult | Warm and fatherly adult male voice for casual conversations and comforting dialogue            | Voice Agents, Customer Support |

## Malayalam

| Voice ID                               | Name                  | Sample                                        | Gender    | Age   | Tone                                                                                      | Use Case                       |
| -------------------------------------- | --------------------- | --------------------------------------------- | --------- | ----- | ----------------------------------------------------------------------------------------- | ------------------------------ |
| `b426013c-002b-4e89-8874-8cd20b68373a` | Latha - Friendly Host | <AudioPlayer title="Latha - Friendly Host" /> | feminine  | Adult | Bright and clear adult female voice for customer support, greetings, and welcoming guests | Voice Agents, Customer Support |
| `374b80da-e622-4dfc-90f6-1eeb13d331c9` | Vijay - Comfort Voice | <AudioPlayer title="Vijay - Comfort Voice" /> | masculine | Adult | Friendly and easygoing male voice for casual conversations and everyday support           | Voice Agents, Customer Support |

## Marathi

| Voice ID                               | Name                        | Sample                                              | Gender    | Age   | Tone                                                                                              | Use Case                       |
| -------------------------------------- | --------------------------- | --------------------------------------------------- | --------- | ----- | ------------------------------------------------------------------------------------------------- | ------------------------------ |
| `5c32dce6-936a-4892-b131-bafe474afe5f` | Anika - Enthusiastic Seller | <AudioPlayer title="Anika - Enthusiastic Seller" /> | feminine  | Adult | Energetic and approachable adult female voice for sales conversations, casual chat, and customer… | Voice Agents, Customer Support |
| `f227bc18-3704-47fe-b759-8c78a450fdfa` | Suresh - Instruction Voice  | <AudioPlayer title="Suresh - Instruction Voice" />  | masculine | Adult | Clear and well-enunciated adult male voice for instructions, narrations, and professional…        | Voice Agents, Customer Support |

## Norwegian

| Voice ID                               | Name                            | Sample                                                  | Gender    | Age   | Tone                                                                                                 | Use Case                       |
| -------------------------------------- | ------------------------------- | ------------------------------------------------------- | --------- | ----- | ---------------------------------------------------------------------------------------------------- | ------------------------------ |
| `4f7b1820-6263-4615-87a7-b105768d8f64` | Kari - Crisp Coordinator        | <AudioPlayer title="Kari - Crisp Coordinator" />        | feminine  | Adult | Polished Norwegian voice for efficient transactional assistance.                                     | Voice Agents, Customer Support |
| `d6dca1b6-cdd8-4e9c-823c-e03979261740` | Lars - Casual Conversationalist | <AudioPlayer title="Lars - Casual Conversationalist" /> | masculine | Adult | Approachable adult male voice with a relaxed tone for casual conversations and everyday interactions | Voice Agents, Customer Support |

## Punjabi

| Voice ID                               | Name                        | Sample                                              | Gender    | Age   | Tone                                                                                            | Use Case                       |
| -------------------------------------- | --------------------------- | --------------------------------------------------- | --------- | ----- | ----------------------------------------------------------------------------------------------- | ------------------------------ |
| `8bacd442-a107-4ec1-b6f1-2fcb3f6f4d56` | Gurpreet - Companion        | <AudioPlayer title="Gurpreet - Companion" />        | masculine | Adult | Soft and caring adult male voice for empathetic conversations, support, and reassuring dialogue | Voice Agents, Customer Support |
| `991c62ce-631f-48b0-8060-2a0ebecbd15b` | Jaspreet - Commercial Woman | <AudioPlayer title="Jaspreet - Commercial Woman" /> | feminine  | Adult | Expressive adult female voice with an engaging tone for commercials, promotions, and lively…    | Voice Agents, Customer Support |

## Romanian

| Voice ID                               | Name                           | Sample                                                 | Gender    | Age   | Tone                                                                                              | Use Case                       |
| -------------------------------------- | ------------------------------ | ------------------------------------------------------ | --------- | ----- | ------------------------------------------------------------------------------------------------- | ------------------------------ |
| `34acfaee-c556-41ee-a5f6-c687fb20357c` | Andrada - Steady Speaker       | <AudioPlayer title="Andrada - Steady Speaker" />       | feminine  | Adult | Clear and monotone adult female voice for instructions formal announcements, and straightforward… | Voice Agents, Customer Support |
| `3f64ef99-d87b-4b51-b217-df7351f7886a` | Andrei - Conversationalist Guy | <AudioPlayer title="Andrei - Conversationalist Guy" /> | masculine | Adult | Casual yet firm middle-aged male voice for everyday conversations, guidance, and professional…    | Voice Agents, Customer Support |

## Slovak

| Voice ID                               | Name                      | Sample                                            | Gender    | Age   | Tone                                                                                               | Use Case                       |
| -------------------------------------- | ------------------------- | ------------------------------------------------- | --------- | ----- | -------------------------------------------------------------------------------------------------- | ------------------------------ |
| `abf68668-6549-462c-8426-1fa7b466b91d` | Katarina - Friendly Sales | <AudioPlayer title="Katarina - Friendly Sales" /> | feminine  | Adult | Warm and approachable adult female voice for customer service, support, and friendly communication | Voice Agents, Customer Support |
| `ca590fdc-df56-4d2e-94a4-ef5b423c7ddf` | Peter - Narrator Man      | <AudioPlayer title="Peter - Narrator Man" />      | masculine | Adult | Steady and articulate adult male voice for narrations, audiobooks, and professional storytelling   | Voice Agents, Customer Support |

## Ukrainian

| Voice ID                               | Name                    | Sample                                          | Gender    | Age   | Tone                                                                                          | Use Case                       |
| -------------------------------------- | ----------------------- | ----------------------------------------------- | --------- | ----- | --------------------------------------------------------------------------------------------- | ------------------------------ |
| `05ffab9c-d380-4909-8375-cd12f59238c3` | Oleh - Professional Guy | <AudioPlayer title="Oleh - Professional Guy" /> | masculine | Adult | Approachable adult male voice with a professional tone for casual conversations and everyday… | Voice Agents, Customer Support |


# Deepgram Aura
Source: https://docs.slng.ai/voices/deepgram-aura

Browse Deepgram Aura 2 voices on SLNG with audio samples — natural conversational TTS across English, Spanish, Dutch, French, German, Italian, and Japanese.

Deepgram Aura 2 offers a variety of high-quality, natural-sounding voices for text-to-speech. You can specify a voice by passing its model ID in your TTS request.

```json theme={null}
{
  "model": "aura-2-thalia-en"
}
```

SLNG provides two ways to use Deepgram Aura voices:

* **SLNG-hosted**: voices are hosted on SLNG infrastructure. English and Spanish are currently supported. Use the [SLNG Deepgram Aura 2](/api-reference/tts/deepgram-aura-2/aura-2-english-ws) endpoints.
* **Deepgram proxy**: requests are forwarded to Deepgram's API, giving you access to their full voice catalog across all languages. Use the [Deepgram Aura 2](/api-reference/tts/deepgram-aura-2/aura-2-ws) endpoint. See [Deepgram's TTS models documentation](https://developers.deepgram.com/docs/tts-models) for the complete list of available voices.

## Supported languages

| Language              | Code | Voices |
| --------------------- | ---- | ------ |
| [English](#english)   | `en` | 41     |
| [Spanish](#spanish)   | `es` | 17     |
| [Dutch](#dutch)       | `nl` | 9      |
| [French](#french)     | `fr` | 2      |
| [German](#german)     | `de` | 7      |
| [Italian](#italian)   | `it` | 10     |
| [Japanese](#japanese) | `ja` | 5      |

## English

| Voice ID              | Name      | Sample                            | Gender    | Age   | Tone                                            | Use Case                                  |
| --------------------- | --------- | --------------------------------- | --------- | ----- | ----------------------------------------------- | ----------------------------------------- |
| `aura-2-amalthea-en`  | Amalthea  | <AudioPlayer title="Amalthea" />  | feminine  | Adult | Engaging, Natural, Cheerful                     | Casual Chat                               |
| `aura-2-andromeda-en` | Andromeda | <AudioPlayer title="Andromeda" /> | feminine  | Adult | Casual, Expressive, Comfortable                 | Customer Service, IVR                     |
| `aura-2-apollo-en`    | Apollo    | <AudioPlayer title="Apollo" />    | masculine | Adult | Confident, Comfortable, Casual                  | Casual Chat                               |
| `aura-2-arcas-en`     | Arcas     | <AudioPlayer title="Arcas" />     | masculine | Adult | Natural, Smooth, Clear, Comfortable             | Customer Service, Casual Chat             |
| `aura-2-aries-en`     | Aries     | <AudioPlayer title="Aries" />     | masculine | Adult | Warm, Energetic, Caring                         | Casual Chat                               |
| `aura-2-asteria-en`   | Asteria   | <AudioPlayer title="Asteria" />   | feminine  | Adult | Clear, Confident, Knowledgeable, Energetic      | Advertising                               |
| `aura-2-athena-en`    | Athena    | <AudioPlayer title="Athena" />    | feminine  | Adult | Calm, Smooth, Professional                      | Storytelling                              |
| `aura-2-atlas-en`     | Atlas     | <AudioPlayer title="Atlas" />     | masculine | Adult | Enthusiastic, Confident, Approachable, Friendly | Advertising                               |
| `aura-2-aurora-en`    | Aurora    | <AudioPlayer title="Aurora" />    | feminine  | Adult | Cheerful, Expressive, Energetic                 | Interview                                 |
| `aura-2-callista-en`  | Callista  | <AudioPlayer title="Callista" />  | feminine  | Adult | Clear, Energetic, Professional, Smooth          | IVR                                       |
| `aura-2-cora-en`      | Cora      | <AudioPlayer title="Cora" />      | feminine  | Adult | Smooth, Melodic, Caring                         | Storytelling                              |
| `aura-2-cordelia-en`  | Cordelia  | <AudioPlayer title="Cordelia" />  | feminine  | Adult | Approachable, Warm, Polite                      | Storytelling                              |
| `aura-2-delia-en`     | Delia     | <AudioPlayer title="Delia" />     | feminine  | Adult | Casual, Friendly, Cheerful, Breathy             | Interview                                 |
| `aura-2-draco-en`     | Draco     | <AudioPlayer title="Draco" />     | masculine | Adult | Warm, Approachable, Trustworthy, Baritone       | Storytelling                              |
| `aura-2-electra-en`   | Electra   | <AudioPlayer title="Electra" />   | feminine  | Adult | Professional, Engaging, Knowledgeable           | IVR, Advertising, Customer Service        |
| `aura-2-harmonia-en`  | Harmonia  | <AudioPlayer title="Harmonia" />  | feminine  | Adult | Empathetic, Clear, Calm, Confident              | Customer Service                          |
| `aura-2-helena-en`    | Helena    | <AudioPlayer title="Helena" />    | feminine  | Adult | Caring, Natural, Positive, Friendly, Raspy      | IVR, Casual Chat                          |
| `aura-2-hera-en`      | Hera      | <AudioPlayer title="Hera" />      | feminine  | Adult | Smooth, Warm, Professional                      | Informative                               |
| `aura-2-hermes-en`    | Hermes    | <AudioPlayer title="Hermes" />    | masculine | Adult | Expressive, Engaging, Professional              | Informative                               |
| `aura-2-hyperion-en`  | Hyperion  | <AudioPlayer title="Hyperion" />  | masculine | Adult | Caring, Warm, Empathetic                        | Interview                                 |
| `aura-2-iris-en`      | Iris      | <AudioPlayer title="Iris" />      | feminine  | Adult | Cheerful, Positive, Approachable                | IVR, Advertising, Customer Service        |
| `aura-2-janus-en`     | Janus     | <AudioPlayer title="Janus" />     | feminine  | Adult | Southern, Smooth, Trustworthy                   | Storytelling                              |
| `aura-2-juno-en`      | Juno      | <AudioPlayer title="Juno" />      | feminine  | Adult | Natural, Engaging, Melodic, Breathy             | Interview                                 |
| `aura-2-jupiter-en`   | Jupiter   | <AudioPlayer title="Jupiter" />   | masculine | Adult | Expressive, Knowledgeable, Baritone             | Informative                               |
| `aura-2-luna-en`      | Luna      | <AudioPlayer title="Luna" />      | feminine  | Adult | Friendly, Natural, Engaging                     | IVR                                       |
| `aura-2-mars-en`      | Mars      | <AudioPlayer title="Mars" />      | masculine | Adult | Smooth, Patient, Trustworthy, Baritone          | Customer Service                          |
| `aura-2-minerva-en`   | Minerva   | <AudioPlayer title="Minerva" />   | feminine  | Adult | Positive, Friendly, Natural                     | Storytelling                              |
| `aura-2-neptune-en`   | Neptune   | <AudioPlayer title="Neptune" />   | masculine | Adult | Professional, Patient, Polite                   | Customer Service                          |
| `aura-2-odysseus-en`  | Odysseus  | <AudioPlayer title="Odysseus" />  | masculine | Adult | Calm, Smooth, Comfortable, Professional         | Advertising                               |
| `aura-2-ophelia-en`   | Ophelia   | <AudioPlayer title="Ophelia" />   | feminine  | Adult | Expressive, Enthusiastic, Cheerful              | Interview                                 |
| `aura-2-orion-en`     | Orion     | <AudioPlayer title="Orion" />     | masculine | Adult | Approachable, Comfortable, Calm, Polite         | Informative                               |
| `aura-2-orpheus-en`   | Orpheus   | <AudioPlayer title="Orpheus" />   | masculine | Adult | Professional, Clear, Confident, Trustworthy     | Customer Service, Storytelling            |
| `aura-2-pandora-en`   | Pandora   | <AudioPlayer title="Pandora" />   | feminine  | Adult | Smooth, Calm, Melodic, Breathy                  | IVR, Informative                          |
| `aura-2-phoebe-en`    | Phoebe    | <AudioPlayer title="Phoebe" />    | feminine  | Adult | Energetic, Warm, Casual                         | Customer Service                          |
| `aura-2-pluto-en`     | Pluto     | <AudioPlayer title="Pluto" />     | masculine | Adult | Smooth, Calm, Empathetic, Baritone              | Interview, Storytelling                   |
| `aura-2-saturn-en`    | Saturn    | <AudioPlayer title="Saturn" />    | masculine | Adult | Knowledgeable, Confident, Baritone              | Customer Service                          |
| `aura-2-selene-en`    | Selene    | <AudioPlayer title="Selene" />    | feminine  | Adult | Expressive, Engaging, Energetic                 | Informative                               |
| `aura-2-thalia-en`    | Thalia    | <AudioPlayer title="Thalia" />    | feminine  | Adult | Clear, Confident, Energetic, Enthusiastic       | Casual Chat, Customer Service, IVR        |
| `aura-2-theia-en`     | Theia     | <AudioPlayer title="Theia" />     | feminine  | Adult | Expressive, Polite, Sincere                     | Informative                               |
| `aura-2-vesta-en`     | Vesta     | <AudioPlayer title="Vesta" />     | feminine  | Adult | Natural, Expressive, Patient, Empathetic        | Customer Service, Interview, Storytelling |
| `aura-2-zeus-en`      | Zeus      | <AudioPlayer title="Zeus" />      | masculine | Adult | Deep, Trustworthy, Smooth                       | IVR                                       |

## Spanish

| Voice ID             | Name     | Sample                           | Gender    | Age         | Tone                                                        | Use Case                                 |
| -------------------- | -------- | -------------------------------- | --------- | ----------- | ----------------------------------------------------------- | ---------------------------------------- |
| `aura-2-agustina-es` | Agustina | <AudioPlayer title="Agustina" /> | feminine  | Adult       | Calm, Clear, Expressive, Knowledgeable, Professional        | Interview, Casual Chat                   |
| `aura-2-alvaro-es`   | Alvaro   | <AudioPlayer title="Alvaro" />   | masculine | Adult       | Calm, Professional, Clear, Knowledgeable, Approachable      | Interview, Customer Service              |
| `aura-2-antonia-es`  | Antonia  | <AudioPlayer title="Antonia" />  | feminine  | Adult       | Approachable, Enthusiastic, Friendly, Natural, Professional | Customer Service, Interview, Casual Chat |
| `aura-2-aquila-es`   | Aquila   | <AudioPlayer title="Aquila" />   | masculine | Adult       | Expressive, Enthusiastic, Confident, Casual, Comfortable    | Casual Chat, Informative                 |
| `aura-2-carina-es`   | Carina   | <AudioPlayer title="Carina" />   | feminine  | Adult       | Professional, Raspy, Energetic, Breathy, Confident          | Interview, Customer Service, IVR         |
| `aura-2-celeste-es`  | Celeste  | <AudioPlayer title="Celeste" />  | feminine  | Young Adult | Clear, Energetic, Positive, Friendly, Enthusiastic          | Casual Chat, Advertising, IVR            |
| `aura-2-diana-es`    | Diana    | <AudioPlayer title="Diana" />    | feminine  | Adult       | Professional, Confident, Expressive, Polite, Knowledgeable  | Storytelling, Advertising                |
| `aura-2-estrella-es` | Estrella | <AudioPlayer title="Estrella" /> | feminine  | Mature      | Approachable, Natural, Calm, Comfortable, Expressive        | Casual Chat, Interview                   |
| `aura-2-gloria-es`   | Gloria   | <AudioPlayer title="Gloria" />   | feminine  | Adult       | Casual, Clear, Expressive, Natural, Smooth                  | Customer Service, Casual Chat            |
| `aura-2-javier-es`   | Javier   | <AudioPlayer title="Javier" />   | masculine | Adult       | Approachable, Professional, Friendly, Comfortable, Calm     | Casual Chat, IVR, Storytelling           |
| `aura-2-luciano-es`  | Luciano  | <AudioPlayer title="Luciano" />  | masculine | Adult       | Charismatic, Cheerful, Energetic, Expressive, Friendly      | Customer Service, Casual Chat            |
| `aura-2-nestor-es`   | Nestor   | <AudioPlayer title="Nestor" />   | masculine | Adult       | Calm, Professional, Approachable, Clear, Confident          | Casual Chat, Customer Service            |
| `aura-2-olivia-es`   | Olivia   | <AudioPlayer title="Olivia" />   | feminine  | Adult       | Breathy, Calm, Casual, Expressive, Warm                     | Customer Service, Casual Chat            |
| `aura-2-selena-es`   | Selena   | <AudioPlayer title="Selena" />   | feminine  | Young Adult | Approachable, Casual, Friendly, Calm, Positive              | Customer Service, Informative            |
| `aura-2-silvia-es`   | Silvia   | <AudioPlayer title="Silvia" />   | feminine  | Adult       | Charismatic, Clear, Expressive, Natural, Warm               | Customer Service, Casual Chat            |
| `aura-2-sirio-es`    | Sirio    | <AudioPlayer title="Sirio" />    | masculine | Adult       | Calm, Professional, Comfortable, Empathetic, Baritone       | Casual Chat, Interview                   |
| `aura-2-valerio-es`  | Valerio  | <AudioPlayer title="Valerio" />  | masculine | Adult       | Deep, Knowledgeable, Natural, Polite, Professional          | Customer Service, Informative            |

## Dutch

| Voice ID             | Name     | Sample                           | Gender    | Age   | Tone                                                      | Use Case                                      |
| -------------------- | -------- | -------------------------------- | --------- | ----- | --------------------------------------------------------- | --------------------------------------------- |
| `aura-2-beatrix-nl`  | Beatrix  | <AudioPlayer title="Beatrix" />  | feminine  | Adult | Cheerful, Enthusiastic, Friendly, Trustworthy, Warm       | Customer Service                              |
| `aura-2-cornelia-nl` | Cornelia | <AudioPlayer title="Cornelia" /> | feminine  | Adult | Approachable, Friendly, Polite, Positive, Warm            | Customer Service                              |
| `aura-2-daphne-nl`   | Daphne   | <AudioPlayer title="Daphne" />   | feminine  | Adult | Calm, Clear, Confident, Professional, Smooth              | Healthcare, Interview, Casual Chat, Audiobook |
| `aura-2-hestia-nl`   | Hestia   | <AudioPlayer title="Hestia" />   | feminine  | Adult | Approachable, Caring, Expressive, Friendly, Knowledgeable | Customer Service                              |
| `aura-2-lars-nl`     | Lars     | <AudioPlayer title="Lars" />     | masculine | Adult | Breathy, Casual, Comfortable, Sincere, Trustworthy        | Customer Service                              |
| `aura-2-leda-nl`     | Leda     | <AudioPlayer title="Leda" />     | feminine  | Adult | Caring, Comfortable, Empathetic, Friendly, Sincere        | Sales                                         |
| `aura-2-rhea-nl`     | Rhea     | <AudioPlayer title="Rhea" />     | feminine  | Adult | Caring, Knowledgeable, Positive, Smooth, Warm             | Customer Service                              |
| `aura-2-roman-nl`    | Roman    | <AudioPlayer title="Roman" />    | masculine | Adult | Calm, Casual, Deep, Natural, Patient                      | Customer Service                              |
| `aura-2-sander-nl`   | Sander   | <AudioPlayer title="Sander" />   | masculine | Adult | Calm, Clear, Deep, Professional, Smooth                   | Customer Service                              |

## French

| Voice ID           | Name   | Sample                         | Gender    | Age   | Tone                                                   | Use Case         |
| ------------------ | ------ | ------------------------------ | --------- | ----- | ------------------------------------------------------ | ---------------- |
| `aura-2-agathe-fr` | Agathe | <AudioPlayer title="Agathe" /> | feminine  | Adult | Charismatic, Cheerful, Enthusiastic, Friendly, Natural | Customer Service |
| `aura-2-hector-fr` | Hector | <AudioPlayer title="Hector" /> | masculine | Adult | Confident, Empathetic, Expressive, Friendly, Patient   | Customer Service |

## German

| Voice ID             | Name     | Sample                           | Gender    | Age   | Tone                                                    | Use Case                                                |
| -------------------- | -------- | -------------------------------- | --------- | ----- | ------------------------------------------------------- | ------------------------------------------------------- |
| `aura-2-aurelia-de`  | Aurelia  | <AudioPlayer title="Aurelia" />  | feminine  | Adult | Approachable, Casual, Comfortable, Natural, Sincere     | Healthcare, Customer Service, Sales, Financial Services |
| `aura-2-elara-de`    | Elara    | <AudioPlayer title="Elara" />    | feminine  | Adult | Calm, Clear, Natural, Patient, Trustworthy              | Healthcare, Customer Service, Sales, Financial Services |
| `aura-2-fabian-de`   | Fabian   | <AudioPlayer title="Fabian" />   | masculine | Adult | Confident, Knowledgeable, Natural, Polite, Professional | Healthcare, Customer Service, Sales, Financial Services |
| `aura-2-julius-de`   | Julius   | <AudioPlayer title="Julius" />   | masculine | Adult | Casual, Cheerful, Engaging, Expressive, Friendly        | Customer Service                                        |
| `aura-2-kara-de`     | Kara     | <AudioPlayer title="Kara" />     | feminine  | Adult | Caring, Empathetic, Expressive, Professional, Warm      | Healthcare, Customer Service, Sales, Financial Services |
| `aura-2-lara-de`     | Lara     | <AudioPlayer title="Lara" />     | feminine  | Adult | Caring, Cheerful, Empathetic, Expressive, Warm          | Healthcare, Customer Service, Sales, Financial Services |
| `aura-2-viktoria-de` | Viktoria | <AudioPlayer title="Viktoria" /> | feminine  | Adult | Charismatic, Cheerful, Enthusiastic, Friendly, Warm     | Customer Service                                        |

## Italian

| Voice ID             | Name     | Sample                           | Gender    | Age   | Tone                                                   | Use Case                                      |
| -------------------- | -------- | -------------------------------- | --------- | ----- | ------------------------------------------------------ | --------------------------------------------- |
| `aura-2-cesare-it`   | Cesare   | <AudioPlayer title="Cesare" />   | masculine | Adult | Clear, Empathetic, Knowledgeable, Natural, Smooth      | Casual Chat, Customer Service, Interview, IVR |
| `aura-2-cinzia-it`   | Cinzia   | <AudioPlayer title="Cinzia" />   | feminine  | Adult | Approachable, Friendly, Smooth, Trustworthy, Warm      | Customer Service, Interview, Narration        |
| `aura-2-demetra-it`  | Demetra  | <AudioPlayer title="Demetra" />  | feminine  | Adult | Calm, Comfortable, Patient                             | Casual Chat, Interview, Narration             |
| `aura-2-dionisio-it` | Dionisio | <AudioPlayer title="Dionisio" /> | masculine | Adult | Confident, Engaging, Friendly, Melodic, Positive       | Sales                                         |
| `aura-2-elio-it`     | Elio     | <AudioPlayer title="Elio" />     | masculine | Adult | Breathy, Calm, Professional, Smooth, Trustworthy       | Interview, Casual Chat, Customer Service      |
| `aura-2-flavio-it`   | Flavio   | <AudioPlayer title="Flavio" />   | masculine | Adult | Confident, Deep, Empathetic, Professional, Trustworthy | Casual Chat, Interview, Customer Service      |
| `aura-2-livia-it`    | Livia    | <AudioPlayer title="Livia" />    | feminine  | Adult | Approachable, Cheerful, Clear, Engaging, Expressive    | Customer Service                              |
| `aura-2-maia-it`     | Maia     | <AudioPlayer title="Maia" />     | feminine  | Adult | Caring, Energetic, Expressive, Professional, Warm      | Interview, Casual Chat, Customer Service      |
| `aura-2-melia-it`    | Melia    | <AudioPlayer title="Melia" />    | feminine  | Adult | Clear, Comfortable, Engaging, Friendly, Natural        | Casual Chat, Customer Service, Interview      |
| `aura-2-perseo-it`   | Perseo   | —                                | masculine | Adult | Casual, Clear, Natural, Polite, Smooth                 | Casual Chat, Customer Service                 |

## Japanese

| Voice ID            | Name    | Sample                          | Gender    | Age   | Tone                                                     | Use Case                                      |
| ------------------- | ------- | ------------------------------- | --------- | ----- | -------------------------------------------------------- | --------------------------------------------- |
| `aura-2-ama-ja`     | Ama     | <AudioPlayer title="Ama" />     | feminine  | Adult | Casual, Comfortable, Confident, Knowledgeable, Natural   | Interview, IVR                                |
| `aura-2-ebisu-ja`   | Ebisu   | <AudioPlayer title="Ebisu" />   | masculine | Adult | Calm, Deep, Natural, Patient, Sincere                    | Casual Chat, Customer Service                 |
| `aura-2-fujin-ja`   | Fujin   | <AudioPlayer title="Fujin" />   | masculine | Adult | Calm, Confident, Knowledgeable, Professional, Smooth     | Interview, Casual Chat, IVR                   |
| `aura-2-izanami-ja` | Izanami | <AudioPlayer title="Izanami" /> | feminine  | Adult | Approachable, Clear, Knowledgeable, Polite, Professional | Casual Chat, Customer Service, Interview, IVR |
| `aura-2-uzume-ja`   | Uzume   | <AudioPlayer title="Uzume" />   | feminine  | Adult | Approachable, Clear, Polite, Professional, Trustworthy   | Customer Service, Interview, IVR, Commercial  |


# Kugel
Source: https://docs.slng.ai/voices/kugel

Browse KugelAudio Kugel voices on SLNG with audio samples — expressive multilingual TTS across 25+ languages including English, Hindi, and Chinese.

KugelAudio's Kugel is a multilingual TTS model with expressiveness control. It comes in two variants:

* **Kugel 1 Turbo**: low-latency, optimized for real-time voice agents
* **Kugel 1**: standard quality with full expressiveness control

You can control expressiveness with `cfg_scale` (0–10, default 2) and playback speed with `speed` (0.8–1.2). The same voice catalog is shared across both variants.

```json theme={null}
{
  "type": "config",
  "voice_id": 272,
  "model_id": "kugel-1-turbo",
  "cfg_scale": 2,
  "speed": 1.0,
  "sample_rate": 24000
}
```

## Supported languages

| Language                  | Code | Voices |
| ------------------------- | ---- | ------ |
| [English](#english)       | `en` | 8      |
| [Spanish](#spanish)       | `es` | 4      |
| [French](#french)         | `fr` | 4      |
| [German](#german)         | `de` | 55     |
| [Italian](#italian)       | `it` | 4      |
| [Portuguese](#portuguese) | `pt` | 4      |
| [Dutch](#dutch)           | `nl` | 5      |
| [Polish](#polish)         | `pl` | 4      |
| [Czech](#czech)           | `cs` | 4      |
| [Slovenian](#slovenian)   | `sl` | 4      |
| [Turkish](#turkish)       | `tr` | 4      |

## English

| Voice ID | Name               | Sample                                     | Gender    | Age   | Tone                     | Use Case                       |
| -------- | ------------------ | ------------------------------------------ | --------- | ----- | ------------------------ | ------------------------------ |
| `285`    | Angela Teacher     | <AudioPlayer title="Angela Teacher" />     | feminine  | Adult | informative\_educational | Voice Agents, Customer Support |
| `287`    | Chucker            | <AudioPlayer title="Chucker" />            | masculine | Adult | Conversational           | Voice Agents, Customer Support |
| `290`    | Edina              | <AudioPlayer title="Edina" />              | feminine  | Adult | informative\_educational | Voice Agents, Customer Support |
| `293`    | Fred               | <AudioPlayer title="Fred" />               | masculine | Adult | Conversational           | Voice Agents, Customer Support |
| `292`    | Gustav             | <AudioPlayer title="Gustav" />             | masculine | Elder | Conversational           | Voice Agents, Customer Support |
| `284`    | Justin News Anchor | <AudioPlayer title="Justin News Anchor" /> | masculine | Adult | entertainment\_tv        | Voice Agents, Customer Support |
| `289`    | Lukas Storyteller  | <AudioPlayer title="Lukas Storyteller" />  | masculine | Elder | Conversational           | Voice Agents, Customer Support |
| `286`    | Tim                | <AudioPlayer title="Tim" />                | masculine | Adult | Conversational           | Voice Agents, Customer Support |

## Spanish

| Voice ID | Name             | Sample                                   | Gender    | Age   | Tone           | Use Case                       |
| -------- | ---------------- | ---------------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `594`    | Carlos Fernández | <AudioPlayer title="Carlos Fernández" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `595`    | Héctor Aguilar   | <AudioPlayer title="Héctor Aguilar" />   | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `592`    | Isabel Torres    | <AudioPlayer title="Isabel Torres" />    | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `588`    | Paula Vega       | <AudioPlayer title="Paula Vega" />       | feminine  | Adult | Conversational | Voice Agents, Customer Support |

## French

| Voice ID | Name           | Sample                                 | Gender    | Age   | Tone           | Use Case                       |
| -------- | -------------- | -------------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `732`    | Camille Dupont | <AudioPlayer title="Camille Dupont" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `735`    | Julien Faure   | <AudioPlayer title="Julien Faure" />   | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `734`    | Manon Petit    | <AudioPlayer title="Manon Petit" />    | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `736`    | Nicolas Leroy  | <AudioPlayer title="Nicolas Leroy" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |

## German

| Voice ID | Name                    | Sample                                          | Gender     | Age         | Tone                  | Use Case                       |
| -------- | ----------------------- | ----------------------------------------------- | ---------- | ----------- | --------------------- | ------------------------------ |
| `468`    | Amelie Kraft            | <AudioPlayer title="Amelie Kraft" />            | feminine   | Young Adult | Conversational        | Voice Agents, Customer Support |
| `448`    | Andreas Schwarz         | <AudioPlayer title="Andreas Schwarz" />         | masculine  | Adult       | Conversational        | Voice Agents, Customer Support |
| `265`    | Angela Österreicherin   | <AudioPlayer title="Angela Österreicherin" />   | feminine   | Adult       | narrative\_story      | Voice Agents, Customer Support |
| `410`    | Anna Hoffmann           | <AudioPlayer title="Anna Hoffmann" />           | feminine   | Adult       | Conversational        | Voice Agents, Customer Support |
| `973`    | Anna Martin             | <AudioPlayer title="Anna Martin" />             | feminine   | Adult       | Conversational        | Voice Agents, Customer Support |
| `480`    | Carla Brandt            | <AudioPlayer title="Carla Brandt" />            | feminine   | Young Adult | Conversational        | Voice Agents, Customer Support |
| `439`    | Christine Kühn          | <AudioPlayer title="Christine Kühn" />          | feminine   | Young Adult | Conversational        | Voice Agents, Customer Support |
| `977`    | Dominik Grund           | <AudioPlayer title="Dominik Grund" />           | masculine  | Adult       | Conversational        | Voice Agents, Customer Support |
| `255`    | Durchsage               | <AudioPlayer title="Durchsage" />               | masculine  | Adult       | narrative\_story      | Voice Agents, Customer Support |
| `422`    | Elisabeth Fuchs         | <AudioPlayer title="Elisabeth Fuchs" />         | feminine   | Adult       | Conversational        | Voice Agents, Customer Support |
| `412`    | Felix Richter           | <AudioPlayer title="Felix Richter" />           | masculine  | Young Adult | Conversational        | Voice Agents, Customer Support |
| `272`    | Friedrich               | <AudioPlayer title="Friedrich" />               | masculine  | Adult       | narrative\_story      | Voice Agents, Customer Support |
| `270`    | Friedrich Sänger        | <AudioPlayer title="Friedrich Sänger" />        | masculine  | Elder       | narrative\_story      | Voice Agents, Customer Support |
| `476`    | Greta Winkler           | <AudioPlayer title="Greta Winkler" />           | feminine   | Adult       | Conversational        | Voice Agents, Customer Support |
| `446`    | Hannah Vogel            | <AudioPlayer title="Hannah Vogel" />            | feminine   | Young Adult | Conversational        | Voice Agents, Customer Support |
| `262`    | Hans                    | <AudioPlayer title="Hans" />                    | masculine  | Elder       | characters\_animation | Voice Agents, Customer Support |
| `268`    | Hans                    | <AudioPlayer title="Hans" />                    | masculine  | Elder       | narrative\_story      | Voice Agents, Customer Support |
| `267`    | Heike die Vorleserin    | <AudioPlayer title="Heike die Vorleserin" />    | feminine   | Elder       | narrative\_story      | Voice Agents, Customer Support |
| `269`    | Heinrich                | <AudioPlayer title="Heinrich" />                | masculine  | Elder       | narrative\_story      | Voice Agents, Customer Support |
| `274`    | Heinrich                | <AudioPlayer title="Heinrich" />                | masculine  | Elder       | narrative\_story      | Voice Agents, Customer Support |
| `409`    | Helmut Drechsler        | <AudioPlayer title="Helmut Drechsler" />        | masculine  | Elder       | Conversational        | Voice Agents, Customer Support |
| `416`    | Jan Schulz              | <AudioPlayer title="Jan Schulz" />              | masculine  | Young Adult | Conversational        | Voice Agents, Customer Support |
| `276`    | Jens                    | <AudioPlayer title="Jens" />                    | masculine  | Adult       | narrative\_story      | Voice Agents, Customer Support |
| `271`    | Johann                  | <AudioPlayer title="Johann" />                  | masculine  | Adult       | narrative\_story      | Voice Agents, Customer Support |
| `280`    | Johann                  | <AudioPlayer title="Johann" />                  | masculine  | Young Adult | Conversational        | Voice Agents, Customer Support |
| `256`    | Jörg                    | <AudioPlayer title="Jörg" />                    | masculine  | Elder       | narrative\_story      | Voice Agents, Customer Support |
| `264`    | Katrin                  | <AudioPlayer title="Katrin" />                  | feminine   | Elder       | narrative\_story      | Voice Agents, Customer Support |
| `978`    | Lea Huber               | <AudioPlayer title="Lea Huber" />               | feminine   | Young Adult | Conversational        | Voice Agents, Customer Support |
| `402`    | Lena Berger             | <AudioPlayer title="Lena Berger" />             | feminine   | Young Adult | Conversational        | Voice Agents, Customer Support |
| `450`    | Lisa Hofmann            | <AudioPlayer title="Lisa Hofmann" />            | feminine   | Young Adult | Conversational        | Voice Agents, Customer Support |
| `258`    | Lukas der Flüsterer     | <AudioPlayer title="Lukas der Flüsterer" />     | masculine  | Adult       | narrative\_story      | Voice Agents, Customer Support |
| `413`    | Lukas Ehlers            | <AudioPlayer title="Lukas Ehlers" />            | masculine  | Young Adult | Conversational        | Voice Agents, Customer Support |
| `980`    | Marius Behnke           | <AudioPlayer title="Marius Behnke" />           | masculine  | Adult       | Conversational        | Voice Agents, Customer Support |
| `279`    | Markus der Analyst      | <AudioPlayer title="Markus der Analyst" />      | masculine  | Adult       | Conversational        | Voice Agents, Customer Support |
| `404`    | Markus Lehmann          | <AudioPlayer title="Markus Lehmann" />          | masculine  | Adult       | Conversational        | Voice Agents, Customer Support |
| `458`    | Monika Weiß             | <AudioPlayer title="Monika Weiß" />             | feminine   | Adult       | Conversational        | Voice Agents, Customer Support |
| `420`    | Niklas Bauer            | <AudioPlayer title="Niklas Bauer" />            | masculine  | Young Adult | Conversational        | Voice Agents, Customer Support |
| `283`    | Notfallsystem           | <AudioPlayer title="Notfallsystem" />           | feminine   | Adult       | advertisement         | Voice Agents, Customer Support |
| `263`    | Österreichische Irmgard | <AudioPlayer title="Österreichische Irmgard" /> | feminine   | Elder       | narrative\_story      | Voice Agents, Customer Support |
| `282`    | Otto der Vorleser       | <AudioPlayer title="Otto der Vorleser" />       | masculine  | Adult       | narrative\_story      | Voice Agents, Customer Support |
| `436`    | Patrick Müller          | <AudioPlayer title="Patrick Müller" />          | masculine  | Young Adult | Conversational        | Voice Agents, Customer Support |
| `465`    | Paula Beckmann          | <AudioPlayer title="Paula Beckmann" />          | feminine   | Young Adult | Conversational        | Voice Agents, Customer Support |
| `266`    | Petra die Vorleserin    | <AudioPlayer title="Petra die Vorleserin" />    | feminine   | Elder       | narrative\_story      | Voice Agents, Customer Support |
| `277`    | Radio Lars              | <AudioPlayer title="Radio Lars" />              | masculine  | Elder       | advertisement         | Voice Agents, Customer Support |
| `462`    | Renate Haas             | <AudioPlayer title="Renate Haas" />             | feminine   | Elder       | Conversational        | Voice Agents, Customer Support |
| `273`    | Rita die Vorleserin     | <AudioPlayer title="Rita die Vorleserin" />     | non-binary | Elder       | narrative\_story      | Voice Agents, Customer Support |
| `438`    | Sabine Neumann          | <AudioPlayer title="Sabine Neumann" />          | feminine   | Young Adult | Conversational        | Voice Agents, Customer Support |
| `979`    | Sara Wagner             | <AudioPlayer title="Sara Wagner" />             | feminine   | Adult       | Conversational        | Voice Agents, Customer Support |
| `261`    | Sauerer Felix           | <AudioPlayer title="Sauerer Felix" />           | masculine  | Elder       | narrative\_story      | Voice Agents, Customer Support |
| `974`    | Selina Netz             | <AudioPlayer title="Selina Netz" />             | feminine   | Adult       | Conversational        | Voice Agents, Customer Support |
| `281`    | Suffi Thomas            | <AudioPlayer title="Suffi Thomas" />            | masculine  | Elder       | narrative\_story      | Voice Agents, Customer Support |
| `972`    | Tim Schröder            | <AudioPlayer title="Tim Schröder" />            | masculine  | Adult       | Conversational        | Voice Agents, Customer Support |
| `460`    | Tobias Kraft            | <AudioPlayer title="Tobias Kraft" />            | masculine  | Young Adult | Conversational        | Voice Agents, Customer Support |
| `976`    | Tobias Kühn             | <AudioPlayer title="Tobias Kühn" />             | masculine  | Young Adult | Conversational        | Voice Agents, Customer Support |
| `259`    | Verrückter Bernd        | <AudioPlayer title="Verrückter Bernd" />        | masculine  | Elder       | narrative\_story      | Voice Agents, Customer Support |

## Italian

| Voice ID | Name             | Sample                                   | Gender    | Age   | Tone           | Use Case                       |
| -------- | ---------------- | ---------------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `684`    | Alessandro Ricci | <AudioPlayer title="Alessandro Ricci" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `682`    | Beatrice Serra   | <AudioPlayer title="Beatrice Serra" />   | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `685`    | Simone Barbieri  | <AudioPlayer title="Simone Barbieri" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `683`    | Valentina Bruna  | <AudioPlayer title="Valentina Bruna" />  | feminine  | Adult | Conversational | Voice Agents, Customer Support |

## Portuguese

| Voice ID | Name             | Sample                                   | Gender    | Age   | Tone           | Use Case                       |
| -------- | ---------------- | ---------------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `604`    | André Cardoso    | <AudioPlayer title="André Cardoso" />    | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `601`    | Daniela Campos   | <AudioPlayer title="Daniela Campos" />   | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `603`    | Marcelo Teixeira | <AudioPlayer title="Marcelo Teixeira" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `606`    | Mariana Ferreira | <AudioPlayer title="Mariana Ferreira" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |

## Dutch

| Voice ID | Name              | Sample                                    | Gender    | Age   | Tone                  | Use Case                       |
| -------- | ----------------- | ----------------------------------------- | --------- | ----- | --------------------- | ------------------------------ |
| `966`    | Claudy Focan      | <AudioPlayer title="Claudy Focan" />      | masculine | Adult | characters\_animation | Voice Agents, Customer Support |
| `910`    | Daan Mulder       | <AudioPlayer title="Daan Mulder" />       | masculine | Adult | Conversational        | Voice Agents, Customer Support |
| `913`    | Hanna Kuiper      | <AudioPlayer title="Hanna Kuiper" />      | feminine  | Adult | Conversational        | Voice Agents, Customer Support |
| `911`    | Lars de Vries     | <AudioPlayer title="Lars de Vries" />     | masculine | Adult | Conversational        | Voice Agents, Customer Support |
| `912`    | Rosa van den Berg | <AudioPlayer title="Rosa van den Berg" /> | feminine  | Adult | Conversational        | Voice Agents, Customer Support |

## Polish

| Voice ID | Name                  | Sample                                        | Gender    | Age   | Tone           | Use Case                       |
| -------- | --------------------- | --------------------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `744`    | Dawid Kwiatkowski     | <AudioPlayer title="Dawid Kwiatkowski" />     | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `742`    | Dominika Nowak        | <AudioPlayer title="Dominika Nowak" />        | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `743`    | Katarzyna Lewandowska | <AudioPlayer title="Katarzyna Lewandowska" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `745`    | Krzysztof Wiśniewski  | <AudioPlayer title="Krzysztof Wiśniewski" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |

## Czech

| Voice ID | Name              | Sample                                    | Gender    | Age   | Tone           | Use Case                       |
| -------- | ----------------- | ----------------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `741`    | Jakub Dvořák      | <AudioPlayer title="Jakub Dvořák" />      | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `737`    | Tereza Nováková   | <AudioPlayer title="Tereza Nováková" />   | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `740`    | Tomáš Horák       | <AudioPlayer title="Tomáš Horák" />       | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `739`    | Veronika Benešová | <AudioPlayer title="Veronika Benešová" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |

## Slovenian

| Voice ID | Name            | Sample                                  | Gender    | Age   | Tone           | Use Case                       |
| -------- | --------------- | --------------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `849`    | Ana Novak       | <AudioPlayer title="Ana Novak" />       | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `847`    | Andrej Potočnik | <AudioPlayer title="Andrej Potočnik" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `850`    | Katja Breznik   | <AudioPlayer title="Katja Breznik" />   | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `848`    | Matej Kovač     | <AudioPlayer title="Matej Kovač" />     | masculine | Adult | Conversational | Voice Agents, Customer Support |

## Turkish

| Voice ID | Name           | Sample                                 | Gender    | Age   | Tone           | Use Case                       |
| -------- | -------------- | -------------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `583`    | İbrahim Yıldız | <AudioPlayer title="İbrahim Yıldız" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `584`    | Mehmet Kaya    | <AudioPlayer title="Mehmet Kaya" />    | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `585`    | Seda\_Aktaş    | <AudioPlayer title="Seda_Aktaş" />     | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `586`    | Zeynep Arslan  | <AudioPlayer title="Zeynep Arslan" />  | feminine  | Adult | Conversational | Voice Agents, Customer Support |


# Murf Falcon
Source: https://docs.slng.ai/voices/murf

Browse Murf Falcon voices on SLNG — real-time multilingual TTS over WebSocket with English, Spanish, French, German, Italian, Hindi, and Chinese.

Murf Falcon is a real-time multilingual text-to-speech model accessed over WebSocket. Voices are referenced by `voice_id` in the form `{locale}-{name}` (for example `en-US-natalie`). Pass the `voice_id` from the tables below as the `voice` field in your init message.

```json theme={null}
{
  "type": "init",
  "model": "murftts:falcon",
  "voice": "en-US-natalie"
}
```

Each voice supports one or more locales; pick a `voice_id` whose locale matches the language you want to synthesize.

## Supported languages

| Language                                | Code       | Voices |
| --------------------------------------- | ---------- | ------ |
| [English (en-US)](#english-en-us)       | `en-US`    | 19     |
| [English (en-UK)](#english-en-uk)       | `en-UK`    | 6      |
| [English (en-AU)](#english-en-au)       | `en-AU`    | 5      |
| [English (en-IN)](#english-en-in)       | `en-IN`    | 6      |
| [English (Scottish)](#english-scottish) | `en-SCOTT` | 2      |
| [Spanish (es-ES)](#spanish-es-es)       | `es-ES`    | 5      |
| [Spanish (es-MX)](#spanish-es-mx)       | `es-MX`    | 4      |
| [French (fr-FR)](#french-fr-fr)         | `fr-FR`    | 2      |
| [French (fr-CA)](#french-fr-ca)         | `fr-CA`    | 1      |
| [German (de-DE)](#german-de-de)         | `de-DE`    | 7      |
| [Italian (it-IT)](#italian-it-it)       | `it-IT`    | 2      |
| [Portuguese (pt-BR)](#portuguese-pt-br) | `pt-BR`    | 7      |
| [Dutch (nl-NL)](#dutch-nl-nl)           | `nl-NL`    | 3      |
| [Polish (pl-PL)](#polish-pl-pl)         | `pl-PL`    | 3      |
| [Greek (el-GR)](#greek-el-gr)           | `el-GR`    | 1      |
| [Croatian (hr-HR)](#croatian-hr-hr)     | `hr-HR`    | 1      |
| [Hindi (hi-IN)](#hindi-hi-in)           | `hi-IN`    | 5      |
| [Tamil (ta-IN)](#tamil-ta-in)           | `ta-IN`    | 5      |
| [Telugu (te-IN)](#telugu-te-in)         | `te-IN`    | 2      |
| [Malayalam (ml-IN)](#malayalam-ml-in)   | `ml-IN`    | 2      |
| [Marathi (mr-IN)](#marathi-mr-in)       | `mr-IN`    | 3      |
| [Bengali (bn-IN)](#bengali-bn-in)       | `bn-IN`    | 3      |
| [Gujarati (gu-IN)](#gujarati-gu-in)     | `gu-IN`    | 2      |
| [Kannada (kn-IN)](#kannada-kn-in)       | `kn-IN`    | 2      |
| [Punjabi (pa-IN)](#punjabi-pa-in)       | `pa-IN`    | 1      |
| [Japanese (ja-JP)](#japanese-ja-jp)     | `ja-JP`    | 3      |
| [Korean (ko-KR)](#korean-ko-kr)         | `ko-KR`    | 3      |
| [Chinese (zh-CN)](#chinese-zh-cn)       | `zh-CN`    | 6      |

## English (en-US)

| Voice ID         | Name     | Sample                           | Gender    | Age   | Tone                                   | Use Case                       |
| ---------------- | -------- | -------------------------------- | --------- | ----- | -------------------------------------- | ------------------------------ |
| `en-US-alicia`   | Alicia   | <AudioPlayer title="Alicia" />   | feminine  | Adult | Conversation                           | Voice Agents, Customer Support |
| `en-US-alina`    | Alina    | <AudioPlayer title="Alina" />    | feminine  | Adult | Conversational                         | Voice Agents, Customer Support |
| `en-US-amara`    | Amara    | <AudioPlayer title="Amara" />    | feminine  | Adult | Conversational                         | Voice Agents, Customer Support |
| `en-US-caleb`    | Caleb    | <AudioPlayer title="Caleb" />    | masculine | Adult | Conversation, Promo                    | Voice Agents, Customer Support |
| `en-US-charles`  | Charles  | <AudioPlayer title="Charles" />  | masculine | Adult | Conversational                         | Voice Agents, Customer Support |
| `en-US-delilah`  | Delilah  | <AudioPlayer title="Delilah" />  | feminine  | Adult | Conversational                         | Voice Agents, Customer Support |
| `en-US-heather`  | Heather  | <AudioPlayer title="Heather" />  | feminine  | Adult | Conversational                         | Voice Agents, Customer Support |
| `en-US-jonathan` | Jonathan | <AudioPlayer title="Jonathan" /> | masculine | Adult | Conversational                         | Voice Agents, Customer Support |
| `en-US-judith`   | Judith   | <AudioPlayer title="Judith" />   | feminine  | Adult | Conversational                         | Voice Agents, Customer Support |
| `en-US-ken`      | Ken      | <AudioPlayer title="Ken" />      | masculine | Adult | Conversational, Promo                  | Voice Agents, Customer Support |
| `en-US-matthew`  | Matthew  | <AudioPlayer title="Matthew" />  | masculine | Adult | Conversation                           | Voice Agents, Customer Support |
| `en-US-miles`    | Miles    | <AudioPlayer title="Miles" />    | masculine | Adult | Conversational, Customer Support Agent | Voice Agents, Customer Support |
| `en-US-natalie`  | Natalie  | <AudioPlayer title="Natalie" />  | feminine  | Adult | Conversation, Promo                    | Voice Agents, Customer Support |
| `en-US-phoebe`   | Phoebe   | <AudioPlayer title="Phoebe" />   | feminine  | Adult | Conversational                         | Voice Agents, Customer Support |
| `en-US-ronnie`   | Ronnie   | <AudioPlayer title="Ronnie" />   | masculine | Adult | Conversational                         | Voice Agents, Customer Support |
| `en-US-samantha` | Samantha | <AudioPlayer title="Samantha" /> | feminine  | Adult | Conversational                         | Voice Agents, Customer Support |
| `en-US-terrell`  | Terrell  | <AudioPlayer title="Terrell" />  | masculine | Adult | Conversational                         | Voice Agents, Customer Support |
| `en-US-will`     | Will     | <AudioPlayer title="Will" />     | masculine | Adult | Conversation                           | Voice Agents, Customer Support |
| `en-US-zion`     | Zion     | <AudioPlayer title="Zion" />     | masculine | Adult | Conversation                           | Voice Agents, Customer Support |

## English (en-UK)

| Voice ID         | Name     | Sample                           | Gender    | Age   | Tone                  | Use Case                       |
| ---------------- | -------- | -------------------------------- | --------- | ----- | --------------------- | ------------------------------ |
| `en-UK-benedict` | Benedict | <AudioPlayer title="Benedict" /> | masculine | Adult | Conversational        | Voice Agents, Customer Support |
| `en-UK-freddie`  | Freddie  | <AudioPlayer title="Freddie" />  | masculine | Adult | Conversational        | Voice Agents, Customer Support |
| `en-UK-hazel`    | Hazel    | <AudioPlayer title="Hazel" />    | feminine  | Adult | Conversational        | Voice Agents, Customer Support |
| `en-UK-hugo`     | Hugo     | <AudioPlayer title="Hugo" />     | masculine | Adult | Conversational        | Voice Agents, Customer Support |
| `en-UK-juliet`   | Juliet   | <AudioPlayer title="Juliet" />   | feminine  | Adult | Conversational        | Voice Agents, Customer Support |
| `en-UK-ruby`     | Ruby     | <AudioPlayer title="Ruby" />     | feminine  | Adult | Conversational, Promo | Voice Agents, Customer Support |

## English (en-AU)

| Voice ID       | Name   | Sample                         | Gender    | Age   | Tone                  | Use Case                       |
| -------------- | ------ | ------------------------------ | --------- | ----- | --------------------- | ------------------------------ |
| `en-AU-harper` | Harper | <AudioPlayer title="Harper" /> | masculine | Adult | Conversational        | Voice Agents, Customer Support |
| `en-AU-ivy`    | Ivy    | <AudioPlayer title="Ivy" />    | feminine  | Adult | Conversational        | Voice Agents, Customer Support |
| `en-AU-jimm`   | Jimm   | <AudioPlayer title="Jimm" />   | masculine | Adult | Conversational        | Voice Agents, Customer Support |
| `en-AU-kylie`  | Kylie  | <AudioPlayer title="Kylie" />  | feminine  | Adult | Conversational        | Voice Agents, Customer Support |
| `en-AU-leyton` | Leyton | <AudioPlayer title="Leyton" /> | masculine | Adult | Conversational, Promo | Voice Agents, Customer Support |

## English (en-IN)

| Voice ID          | Name      | Sample                            | Gender    | Age   | Tone           | Use Case                       |
| ----------------- | --------- | --------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `en-IN-aarav`     | Aarav     | <AudioPlayer title="Aarav" />     | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `en-IN-anisha`    | Anisha    | <AudioPlayer title="Anisha" />    | feminine  | Adult | Conversation   | Voice Agents, Customer Support |
| `en-IN-anusha`    | Anusha    | <AudioPlayer title="Anusha" />    | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `en-IN-nikhil`    | Nikhil    | <AudioPlayer title="Nikhil" />    | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `en-IN-samar`     | Samar     | <AudioPlayer title="Samar" />     | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `en-IN-tanushree` | Tanushree | <AudioPlayer title="Tanushree" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |

## English (Scottish)

| Voice ID         | Name  | Sample                        | Gender    | Age   | Tone           | Use Case                       |
| ---------------- | ----- | ----------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `en-SCOTT-emily` | Emily | <AudioPlayer title="Emily" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `en-SCOTT-rory`  | Rory  | <AudioPlayer title="Rory" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |

## Spanish (es-ES)

| Voice ID        | Name    | Sample                          | Gender    | Age   | Tone           | Use Case                       |
| --------------- | ------- | ------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `es-ES-carla`   | Carla   | <AudioPlayer title="Carla" />   | feminine  | Adult | Conversation   | Voice Agents, Customer Support |
| `es-ES-carmen`  | Carmen  | <AudioPlayer title="Carmen" />  | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `es-ES-elvira`  | Elvira  | <AudioPlayer title="Elvira" />  | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `es-ES-enrique` | Enrique | <AudioPlayer title="Enrique" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `es-ES-javier`  | Javier  | <AudioPlayer title="Javier" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |

## Spanish (es-MX)

| Voice ID          | Name      | Sample                            | Gender    | Age   | Tone           | Use Case                       |
| ----------------- | --------- | --------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `es-MX-alejandro` | Alejandro | <AudioPlayer title="Alejandro" /> | masculine | Adult | Conversation   | Voice Agents, Customer Support |
| `es-MX-carlos`    | Carlos    | <AudioPlayer title="Carlos" />    | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `es-MX-luisa`     | Luisa     | <AudioPlayer title="Luisa" />     | feminine  | Adult | Conversation   | Voice Agents, Customer Support |
| `es-MX-valeria`   | Valeria   | <AudioPlayer title="Valeria" />   | feminine  | Adult | Conversation   | Voice Agents, Customer Support |

## French (fr-FR)

| Voice ID          | Name      | Sample                            | Gender    | Age   | Tone         | Use Case                       |
| ----------------- | --------- | --------------------------------- | --------- | ----- | ------------ | ------------------------------ |
| `fr-FR-axel`      | Axel      | <AudioPlayer title="Axel" />      | masculine | Adult | Conversation | Voice Agents, Customer Support |
| `fr-FR-guillaume` | Guillaume | <AudioPlayer title="Guillaume" /> | masculine | Adult | Conversation | Voice Agents, Customer Support |

## French (fr-CA)

| Voice ID       | Name   | Sample                         | Gender    | Age   | Tone           | Use Case                       |
| -------------- | ------ | ------------------------------ | --------- | ----- | -------------- | ------------------------------ |
| `fr-CA-alexis` | Alexis | <AudioPlayer title="Alexis" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |

## German (de-DE)

| Voice ID          | Name      | Sample                            | Gender    | Age   | Tone           | Use Case                       |
| ----------------- | --------- | --------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `de-DE-björn`     | Björn     | <AudioPlayer title="Björn" />     | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `de-DE-erna`      | Erna      | <AudioPlayer title="Erna" />      | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `de-DE-josephine` | Josephine | <AudioPlayer title="Josephine" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `de-DE-lara`      | Lara      | <AudioPlayer title="Lara" />      | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `de-DE-lia`       | Lia       | <AudioPlayer title="Lia" />       | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `de-DE-matthias`  | Matthias  | <AudioPlayer title="Matthias" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `de-DE-ralf`      | Ralf      | <AudioPlayer title="Ralf" />      | masculine | Adult | Conversational | Voice Agents, Customer Support |

## Italian (it-IT)

| Voice ID       | Name   | Sample                         | Gender    | Age   | Tone           | Use Case                       |
| -------------- | ------ | ------------------------------ | --------- | ----- | -------------- | ------------------------------ |
| `it-IT-angelo` | Angelo | <AudioPlayer title="Angelo" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `it-IT-giulia` | Giulia | <AudioPlayer title="Giulia" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |

## Portuguese (pt-BR)

| Voice ID        | Name    | Sample                          | Gender    | Age   | Tone           | Use Case                       |
| --------------- | ------- | ------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `pt-BR-benício` | Benício | <AudioPlayer title="Benício" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `pt-BR-eloa`    | Eloa    | <AudioPlayer title="Eloa" />    | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `pt-BR-gustavo` | Gustavo | <AudioPlayer title="Gustavo" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `pt-BR-heitor`  | Heitor  | <AudioPlayer title="Heitor" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `pt-BR-isadora` | Isadora | <AudioPlayer title="Isadora" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `pt-BR-silvio`  | Silvio  | <AudioPlayer title="Silvio" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `pt-BR-yago`    | Yago    | <AudioPlayer title="Yago" />    | masculine | Adult | Conversational | Voice Agents, Customer Support |

## Dutch (nl-NL)

| Voice ID      | Name  | Sample                        | Gender    | Age   | Tone           | Use Case                       |
| ------------- | ----- | ----------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `nl-NL-dirk`  | Dirk  | <AudioPlayer title="Dirk" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `nl-NL-famke` | Famke | <AudioPlayer title="Famke" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `nl-NL-merel` | Merel | <AudioPlayer title="Merel" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |

## Polish (pl-PL)

| Voice ID       | Name   | Sample                         | Gender    | Age   | Tone           | Use Case                       |
| -------------- | ------ | ------------------------------ | --------- | ----- | -------------- | ------------------------------ |
| `pl-PL-blazej` | Blazej | <AudioPlayer title="Blazej" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `pl-PL-jacek`  | Jacek  | <AudioPlayer title="Jacek" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `pl-PL-kasia`  | Kasia  | <AudioPlayer title="Kasia" />  | feminine  | Adult | Conversational | Voice Agents, Customer Support |

## Greek (el-GR)

| Voice ID        | Name    | Sample                          | Gender    | Age   | Tone      | Use Case                       |
| --------------- | ------- | ------------------------------- | --------- | ----- | --------- | ------------------------------ |
| `el-GR-stavros` | Stavros | <AudioPlayer title="Stavros" /> | masculine | Adult | Narration | Voice Agents, Customer Support |

## Croatian (hr-HR)

| Voice ID       | Name   | Sample                         | Gender   | Age   | Tone      | Use Case                       |
| -------------- | ------ | ------------------------------ | -------- | ----- | --------- | ------------------------------ |
| `hr-HR-marija` | Marija | <AudioPlayer title="Marija" /> | feminine | Adult | Narration | Voice Agents, Customer Support |

## Hindi (hi-IN)

| Voice ID        | Name    | Sample                          | Gender    | Age   | Tone           | Use Case                       |
| --------------- | ------- | ------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `hi-IN-aman`    | Aman    | <AudioPlayer title="Aman" />    | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `hi-IN-karan`   | Karan   | <AudioPlayer title="Karan" />   | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `hi-IN-khyati`  | Khyati  | <AudioPlayer title="Khyati" />  | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `hi-IN-namrita` | Namrita | <AudioPlayer title="Namrita" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `hi-IN-sunaina` | Sunaina | <AudioPlayer title="Sunaina" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |

## Tamil (ta-IN)

| Voice ID        | Name    | Sample                          | Gender    | Age   | Tone           | Use Case                       |
| --------------- | ------- | ------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `ta-IN-abirami` | Abirami | <AudioPlayer title="Abirami" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `ta-IN-dinesh`  | Dinesh  | <AudioPlayer title="Dinesh" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `ta-IN-iniya`   | Iniya   | <AudioPlayer title="Iniya" />   | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `ta-IN-murali`  | Murali  | <AudioPlayer title="Murali" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `ta-IN-sarvesh` | Sarvesh | <AudioPlayer title="Sarvesh" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |

## Telugu (te-IN)

| Voice ID          | Name      | Sample                            | Gender   | Age   | Tone           | Use Case                       |
| ----------------- | --------- | --------------------------------- | -------- | ----- | -------------- | ------------------------------ |
| `te-IN-navya`     | Navya     | <AudioPlayer title="Navya" />     | feminine | Adult | Conversational | Voice Agents, Customer Support |
| `te-IN-vaishnavi` | Vaishnavi | <AudioPlayer title="Vaishnavi" /> | feminine | Adult | Conversational | Voice Agents, Customer Support |

## Malayalam (ml-IN)

| Voice ID         | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                       |
| ---------------- | -------- | -------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `ml-IN-madhavan` | Madhavan | <AudioPlayer title="Madhavan" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `ml-IN-nimisha`  | Nimisha  | <AudioPlayer title="Nimisha" />  | feminine  | Adult | Conversational | Voice Agents, Customer Support |

## Marathi (mr-IN)

| Voice ID           | Name       | Sample                             | Gender    | Age   | Tone           | Use Case                       |
| ------------------ | ---------- | ---------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `mr-IN-prajakta`   | Prajakta   | <AudioPlayer title="Prajakta" />   | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `mr-IN-prathamesh` | Prathamesh | <AudioPlayer title="Prathamesh" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `mr-IN-vaibhav`    | Vaibhav    | <AudioPlayer title="Vaibhav" />    | masculine | Adult | Conversational | Voice Agents, Customer Support |

## Bengali (bn-IN)

| Voice ID          | Name      | Sample                            | Gender    | Age   | Tone           | Use Case                       |
| ----------------- | --------- | --------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `bn-IN-debarati`  | Debarati  | <AudioPlayer title="Debarati" />  | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `bn-IN-sourav`    | Sourav    | <AudioPlayer title="Sourav" />    | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `bn-IN-subhankar` | Subhankar | <AudioPlayer title="Subhankar" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |

## Gujarati (gu-IN)

| Voice ID       | Name   | Sample                         | Gender    | Age   | Tone           | Use Case                       |
| -------------- | ------ | ------------------------------ | --------- | ----- | -------------- | ------------------------------ |
| `gu-IN-diya`   | Diya   | <AudioPlayer title="Diya" />   | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `gu-IN-hardik` | Hardik | <AudioPlayer title="Hardik" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |

## Kannada (kn-IN)

| Voice ID          | Name      | Sample                            | Gender    | Age   | Tone           | Use Case                       |
| ----------------- | --------- | --------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `kn-IN-rajesh`    | Rajesh    | <AudioPlayer title="Rajesh" />    | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `kn-IN-rakshitha` | Rakshitha | <AudioPlayer title="Rakshitha" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |

## Punjabi (pa-IN)

| Voice ID       | Name   | Sample                         | Gender    | Age   | Tone           | Use Case                       |
| -------------- | ------ | ------------------------------ | --------- | ----- | -------------- | ------------------------------ |
| `pa-IN-harman` | Harman | <AudioPlayer title="Harman" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |

## Japanese (ja-JP)

| Voice ID      | Name  | Sample                        | Gender    | Age   | Tone           | Use Case                       |
| ------------- | ----- | ----------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `ja-JP-denki` | Denki | <AudioPlayer title="Denki" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `ja-JP-kenji` | Kenji | <AudioPlayer title="Kenji" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `ja-JP-kimi`  | Kimi  | <AudioPlayer title="Kimi" />  | feminine  | Adult | Conversational | Voice Agents, Customer Support |

## Korean (ko-KR)

| Voice ID         | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                       |
| ---------------- | -------- | -------------------------------- | --------- | ----- | -------------- | ------------------------------ |
| `ko-KR-jangmi`   | Jangmi   | <AudioPlayer title="Jangmi" />   | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `ko-KR-jong-su`  | Jong-su  | <AudioPlayer title="Jong-su" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `ko-KR-sanghoon` | SangHoon | <AudioPlayer title="SangHoon" /> | masculine | Adult | Conversational | Voice Agents, Customer Support |

## Chinese (zh-CN)

| Voice ID       | Name   | Sample                         | Gender    | Age   | Tone           | Use Case                       |
| -------------- | ------ | ------------------------------ | --------- | ----- | -------------- | ------------------------------ |
| `zh-CN-baolin` | Baolin | <AudioPlayer title="Baolin" /> | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `zh-CN-jiao`   | Jiao   | <AudioPlayer title="Jiao" />   | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `zh-CN-tao`    | Tao    | <AudioPlayer title="Tao" />    | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `zh-CN-wei`    | Wei    | <AudioPlayer title="Wei" />    | feminine  | Adult | Conversational | Voice Agents, Customer Support |
| `zh-CN-yuxan`  | Yuxan  | <AudioPlayer title="Yuxan" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |
| `zh-CN-zhang`  | Zhang  | <AudioPlayer title="Zhang" />  | masculine | Adult | Conversational | Voice Agents, Customer Support |


# Orpheus
Source: https://docs.slng.ai/voices/orpheus

Browse Orpheus English voices on SLNG with audio samples, emotion-control tags, and recommended use cases for natural conversational speech synthesis.

Orpheus by CanopyLabs is a low-latency text-to-speech model hosted on SLNG infrastructure. It supports 8 English voices and built-in emotion control, letting you shape how the voice sounds without post-processing.

Select a voice by passing its `voice` ID in your request body. Optionally set an `emotion` to change the delivery style.

```json theme={null}
{
  "voice": "tara",
  "prompt": "Hello from SLNG and Orpheus.",
  "emotion": "happy"
}
```

## Emotion control

Orpheus supports an `emotion` parameter that changes the delivery style of any voice. When omitted, the voice uses its default neutral tone.

| Emotion     | Description                | Sample                                   |
| ----------- | -------------------------- | ---------------------------------------- |
| `neutral`   | Default, balanced delivery | <AudioPlayer title="Tara - neutral" />   |
| `happy`     | Upbeat, warm, and positive | <AudioPlayer title="Tara - happy" />     |
| `sad`       | Subdued, empathetic tone   | <AudioPlayer title="Tara - sad" />       |
| `angry`     | Firm, intense delivery     | <AudioPlayer title="Tara - angry" />     |
| `surprised` | Excited, astonished tone   | <AudioPlayer title="Tara - surprised" /> |

## Voices

| Voice ID | Name | Sample                       | Gender    | Age         | Tone                     | Use Case                                      |
| -------- | ---- | ---------------------------- | --------- | ----------- | ------------------------ | --------------------------------------------- |
| `dan`    | Dan  | <AudioPlayer title="Dan" />  | masculine | Adult       | Friendly, Casual         | Tutorials, Explainer Videos, Chatbots         |
| `jess`   | Jess | <AudioPlayer title="Jess" /> | feminine  | Young Adult | Energetic, Youthful      | Social Content, Ads, Upbeat Narration         |
| `leah`   | Leah | <AudioPlayer title="Leah" /> | feminine  | Adult       | Warm, Gentle             | Wellness Apps, Audiobooks, Meditation         |
| `leo`    | Leo  | <AudioPlayer title="Leo" />  | masculine | Adult       | Authoritative, Deep      | News, Corporate Narration, Documentaries      |
| `mia`    | Mia  | <AudioPlayer title="Mia" />  | feminine  | Adult       | Professional, Articulate | E-learning, Corporate Training, Presentations |
| `tara`   | Tara | <AudioPlayer title="Tara" /> | feminine  | Adult       | Conversational, Clear    | Podcasts, AI Assistants, Interviews           |
| `zac`    | Zac  | <AudioPlayer title="Zac" />  | masculine | Adult       | Enthusiastic, Dynamic    | Sports, Gaming, Promos                        |
| `zoe`    | Zoe  | <AudioPlayer title="Zoe" />  | feminine  | Adult       | Calm, Soothing           | Relaxation Apps, Gentle Narration             |


# Rime Arcana voices
Source: https://docs.slng.ai/voices/rime-arcana

Browse Rime Arcana v2 and v3 voices on SLNG with audio samples and characteristics — supports English, Spanish, French, German, Arabic, and Hindi.

Rime builds the Arcana model and voice collection, and we host it on our own infrastructure for optimal performance.

Select a voice by passing its `speaker` ID in your request body

Check a curated selection of available voices below.

```json theme={null}
{
  "text": "Hello from SLNG and Rime Arcana.",
  "speaker": "astra",
}
```

SLNG exposes two Arcana versions:

* **Arcana v3 (recommended)** - multilingual speaker pool shared across `:3-en`, `:3-fr`, and `:3-hi` endpoints.
* **Arcana v1** - language-specific voice sets on `:en`, `:es`, `:fr`, `:de`, and `:ar` endpoints.

## Arcana v3 (Multilingual)

Arcana v3 is the recommended version for new builds. It uses a shared multilingual speaker pool across English, French, and Hindi endpoints.

### English voices

Endpoint documentation: [Rime Arcana 3 EN](/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws)

<table>
  <thead>
    <tr>
      <th>Model</th>
      <th>Name</th>
      <th>Sample</th>
      <th>Gender</th>
      <th>Age</th>
      <th>Language</th>
      <th>Characteristics</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        <code>astra</code>
      </td>

      <td>Astra</td>

      <td>
        <AudioPlayer title="Astra" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>English (v3 multilingual)</td>
      <td>American accent (US), White profile</td>
    </tr>

    <tr>
      <td>
        <code>arcade</code>
      </td>

      <td>Arcade</td>

      <td>
        <AudioPlayer title="Arcade" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>English (v3 multilingual)</td>
      <td>American accent (US), Asian American profile</td>
    </tr>

    <tr>
      <td>
        <code>albion</code>
      </td>

      <td>Albion</td>

      <td>
        <AudioPlayer title="Albion" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>English (v3 multilingual)</td>
      <td>English accent (England), White profile</td>
    </tr>

    <tr>
      <td>
        <code>luna</code>
      </td>

      <td>Luna</td>

      <td>
        <AudioPlayer title="Luna" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>English (v3 multilingual)</td>
      <td>American accent (US), White profile</td>
    </tr>

    <tr>
      <td>
        <code>lyra</code>
      </td>

      <td>Lyra</td>

      <td>
        <AudioPlayer title="Lyra" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>English (v3 multilingual)</td>
      <td>American accent (US), White profile</td>
    </tr>

    <tr>
      <td>
        <code>sirius</code>
      </td>

      <td>Sirius</td>

      <td>
        <AudioPlayer title="Sirius" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>English (v3 multilingual)</td>
      <td>American accent (US), Latino profile</td>
    </tr>

    <tr>
      <td>
        <code>celeste</code>
      </td>

      <td>Celeste</td>

      <td>
        <AudioPlayer title="Celeste" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>English (v3 multilingual)</td>
      <td>American accent (US), Asian American profile</td>
    </tr>

    <tr>
      <td>
        <code>bond</code>
      </td>

      <td>Bond</td>

      <td>
        <AudioPlayer title="Bond" />
      </td>

      <td>Male</td>
      <td>Adult</td>
      <td>English (v3 multilingual)</td>
      <td>American accent (US), Black profile</td>
    </tr>

    <tr>
      <td>
        <code>eliphas</code>
      </td>

      <td>Eliphas</td>

      <td>
        <AudioPlayer title="Eliphas" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>English (v3 multilingual)</td>
      <td>American accent (US), Asian American profile</td>
    </tr>

    <tr>
      <td>
        <code>estelle</code>
      </td>

      <td>Estelle</td>

      <td>
        <AudioPlayer title="Estelle" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>English (v3 multilingual)</td>
      <td>American accent (US), Black profile</td>
    </tr>

    <tr>
      <td>
        <code>vashti</code>
      </td>

      <td>Vashti</td>

      <td>
        <AudioPlayer title="Vashti" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>English (v3 multilingual)</td>
      <td>English accent (England), White profile</td>
    </tr>
  </tbody>
</table>

### French voices

Endpoint documentation: [Rime Arcana 3 EN](/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws)

<table>
  <thead>
    <tr>
      <th>Model</th>
      <th>Name</th>
      <th>Sample</th>
      <th>Gender</th>
      <th>Age</th>
      <th>Language</th>
      <th>Characteristics</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        <code>amarante</code>
      </td>

      <td>Amarante</td>

      <td>
        <AudioPlayer title="Amarante" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>French (v3 multilingual)</td>
      <td>Montreal accent (Canada), White profile</td>
    </tr>

    <tr>
      <td>
        <code>aurelie</code>
      </td>

      <td>Aurelie</td>

      <td>
        <AudioPlayer title="Aurelie" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>French (v3 multilingual)</td>
      <td>French accent, White profile</td>
    </tr>

    <tr>
      <td>
        <code>destin</code>
      </td>

      <td>Destin</td>

      <td>
        <AudioPlayer title="Destin" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>French (v3 multilingual)</td>
      <td>French accent, White profile</td>
    </tr>

    <tr>
      <td>
        <code>morel\_marianne</code>
      </td>

      <td>Morel Marianne</td>

      <td>
        <AudioPlayer title="Morel Marianne" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>French (v3 multilingual)</td>
      <td>French accent, White profile</td>
    </tr>

    <tr>
      <td>
        <code>solstice</code>
      </td>

      <td>Solstice</td>

      <td>
        <AudioPlayer title="Solstice" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>French (v3 multilingual)</td>
      <td>French accent, White profile</td>
    </tr>

    <tr>
      <td>
        <code>astra</code>
      </td>

      <td>Astra</td>

      <td>
        <AudioPlayer title="Astra" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>French (v3 multilingual)</td>
      <td>American accent (US), White profile</td>
    </tr>

    <tr>
      <td>
        <code>luna</code>
      </td>

      <td>Luna</td>

      <td>
        <AudioPlayer title="Luna" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>French (v3 multilingual)</td>
      <td>American accent (US), White profile</td>
    </tr>

    <tr>
      <td>
        <code>sirius</code>
      </td>

      <td>Sirius</td>

      <td>
        <AudioPlayer title="Sirius" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>French (v3 multilingual)</td>
      <td>American accent (US), Latino profile</td>
    </tr>

    <tr>
      <td>
        <code>celeste</code>
      </td>

      <td>Celeste</td>

      <td>
        <AudioPlayer title="Celeste" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>French (v3 multilingual)</td>
      <td>American accent (US), Asian American profile</td>
    </tr>
  </tbody>
</table>

### Hindi voices

Endpoint documentation: [Rime Arcana 3 HI](/api-reference/tts/rime-arcana-v3/arcana-v3-hindi-ws)

<table>
  <thead>
    <tr>
      <th>Model</th>
      <th>Name</th>
      <th>Sample</th>
      <th>Gender</th>
      <th>Age</th>
      <th>Language</th>
      <th>Characteristics</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        <code>anaya</code>
      </td>

      <td>Anaya</td>

      <td>
        <AudioPlayer title="Anaya" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>Hindi (v3 multilingual)</td>
      <td>India accent</td>
    </tr>

    <tr>
      <td>
        <code>anil</code>
      </td>

      <td>Anil</td>

      <td>
        <AudioPlayer title="Anil" />
      </td>

      <td>Male</td>
      <td>Adult</td>
      <td>Hindi (v3 multilingual)</td>
      <td>India accent</td>
    </tr>

    <tr>
      <td>
        <code>arya</code>
      </td>

      <td>Arya</td>

      <td>
        <AudioPlayer title="Arya" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>Hindi (v3 multilingual)</td>
      <td>India accent</td>
    </tr>

    <tr>
      <td>
        <code>astra</code>
      </td>

      <td>Astra</td>

      <td>
        <AudioPlayer title="Astra" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>Hindi (v3 multilingual)</td>
      <td>American accent (US), White profile</td>
    </tr>

    <tr>
      <td>
        <code>arcade</code>
      </td>

      <td>Arcade</td>

      <td>
        <AudioPlayer title="Arcade" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>Hindi (v3 multilingual)</td>
      <td>American accent (US), Asian American profile</td>
    </tr>

    <tr>
      <td>
        <code>luna</code>
      </td>

      <td>Luna</td>

      <td>
        <AudioPlayer title="Luna" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>Hindi (v3 multilingual)</td>
      <td>American accent (US), White profile</td>
    </tr>

    <tr>
      <td>
        <code>bond</code>
      </td>

      <td>Bond</td>

      <td>
        <AudioPlayer title="Bond" />
      </td>

      <td>Male</td>
      <td>Adult</td>
      <td>Hindi (v3 multilingual)</td>
      <td>American accent (US), Black profile</td>
    </tr>

    <tr>
      <td>
        <code>sirius</code>
      </td>

      <td>Sirius</td>

      <td>
        <AudioPlayer title="Sirius" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>Hindi (v3 multilingual)</td>
      <td>American accent (US), Latino profile</td>
    </tr>

    <tr>
      <td>
        <code>lyra</code>
      </td>

      <td>Lyra</td>

      <td>
        <AudioPlayer title="Lyra" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>Hindi (v3 multilingual)</td>
      <td>American accent (US), White profile</td>
    </tr>
  </tbody>
</table>

## Arcana v1 (Language-specific)

Arcana v1 uses language-specific speaker sets. Pick speakers from the endpoint that matches your target language.

### English voices

Endpoint documentation: [Rime Arcana EN](/api-reference/tts/rime-arcana-v2/arcana-v2-english-ws)

<table>
  <thead>
    <tr>
      <th>Model</th>
      <th>Name</th>
      <th>Sample</th>
      <th>Gender</th>
      <th>Age</th>
      <th>Language</th>
      <th>Characteristics</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        <code>astra</code>
      </td>

      <td>Astra</td>

      <td>
        <AudioPlayer title="Astra" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>English (v1 language-specific)</td>
      <td>American accent (US), White profile</td>
    </tr>

    <tr>
      <td>
        <code>arcade</code>
      </td>

      <td>Arcade</td>

      <td>
        <AudioPlayer title="Arcade" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>English (v1 language-specific)</td>
      <td>American accent (US), Asian American profile</td>
    </tr>

    <tr>
      <td>
        <code>albion</code>
      </td>

      <td>Albion</td>

      <td>
        <AudioPlayer title="Albion" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>English (v1 language-specific)</td>
      <td>English accent (England), White profile</td>
    </tr>

    <tr>
      <td>
        <code>atrium</code>
      </td>

      <td>Atrium</td>

      <td>
        <AudioPlayer title="Atrium" />
      </td>

      <td>Male</td>
      <td>Adult</td>
      <td>English (v1 language-specific)</td>
      <td>American accent (US), Mixed Race profile</td>
    </tr>

    <tr>
      <td>
        <code>bond</code>
      </td>

      <td>Bond</td>

      <td>
        <AudioPlayer title="Bond" />
      </td>

      <td>Male</td>
      <td>Adult</td>
      <td>English (v1 language-specific)</td>
      <td>American accent (US), Black profile</td>
    </tr>

    <tr>
      <td>
        <code>celeste</code>
      </td>

      <td>Celeste</td>

      <td>
        <AudioPlayer title="Celeste" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>English (v1 language-specific)</td>
      <td>American accent (US), Asian American profile</td>
    </tr>

    <tr>
      <td>
        <code>eliphas</code>
      </td>

      <td>Eliphas</td>

      <td>
        <AudioPlayer title="Eliphas" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>English (v1 language-specific)</td>
      <td>American accent (US), Asian American profile</td>
    </tr>

    <tr>
      <td>
        <code>estelle</code>
      </td>

      <td>Estelle</td>

      <td>
        <AudioPlayer title="Estelle" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>English (v1 language-specific)</td>
      <td>American accent (US), Black profile</td>
    </tr>

    <tr>
      <td>
        <code>luna</code>
      </td>

      <td>Luna</td>

      <td>
        <AudioPlayer title="Luna" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>English (v1 language-specific)</td>
      <td>American accent (US), White profile</td>
    </tr>

    <tr>
      <td>
        <code>lyra</code>
      </td>

      <td>Lyra</td>

      <td>
        <AudioPlayer title="Lyra" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>English (v1 language-specific)</td>
      <td>American accent (US), White profile</td>
    </tr>

    <tr>
      <td>
        <code>sirius</code>
      </td>

      <td>Sirius</td>

      <td>
        <AudioPlayer title="Sirius" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>English (v1 language-specific)</td>
      <td>American accent (US), Latino profile</td>
    </tr>

    <tr>
      <td>
        <code>vashti</code>
      </td>

      <td>Vashti</td>

      <td>
        <AudioPlayer title="Vashti" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>English (v1 language-specific)</td>
      <td>English accent (England), White profile</td>
    </tr>
  </tbody>
</table>

### Spanish voices

Endpoint documentation: [Rime Arcana ES](/api-reference/tts/rime-arcana-v2/arcana-v2-spanish-ws)

<table>
  <thead>
    <tr>
      <th>Model</th>
      <th>Name</th>
      <th>Sample</th>
      <th>Gender</th>
      <th>Age</th>
      <th>Language</th>
      <th>Characteristics</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        <code>aurelio</code>
      </td>

      <td>Aurelio</td>

      <td>
        <AudioPlayer title="Aurelio" />
      </td>

      <td>Male</td>
      <td>Adult</td>
      <td>Spanish (v1 language-specific)</td>
      <td>Heritage accent (US), Latin profile</td>
    </tr>

    <tr>
      <td>
        <code>celestino</code>
      </td>

      <td>Celestino</td>

      <td>
        <AudioPlayer title="Celestino" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>Spanish (v1 language-specific)</td>
      <td>Mexican accent, Latino profile</td>
    </tr>

    <tr>
      <td>
        <code>lark</code>
      </td>

      <td>Lark</td>

      <td>
        <AudioPlayer title="Lark" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>Spanish (v1 language-specific)</td>
      <td>Spanish accent (Spain), White profile</td>
    </tr>

    <tr>
      <td>
        <code>luz</code>
      </td>

      <td>Luz</td>

      <td>
        <AudioPlayer title="Luz" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>Spanish (v1 language-specific)</td>
      <td>Equadorian accent, Latina profile</td>
    </tr>

    <tr>
      <td>
        <code>mar</code>
      </td>

      <td>Mar</td>

      <td>
        <AudioPlayer title="Mar" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>Spanish (v1 language-specific)</td>
      <td>Mexican accent, Latino profile</td>
    </tr>

    <tr>
      <td>
        <code>nova</code>
      </td>

      <td>Nova</td>

      <td>
        <AudioPlayer title="Nova" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>Spanish (v1 language-specific)</td>
      <td>Columbian accent, Latina profile</td>
    </tr>

    <tr>
      <td>
        <code>pola</code>
      </td>

      <td>Pola</td>

      <td>
        <AudioPlayer title="Pola" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>Spanish (v1 language-specific)</td>
      <td>Dominican accent (US), Latina profile</td>
    </tr>

    <tr>
      <td>
        <code>seraphina</code>
      </td>

      <td>Seraphina</td>

      <td>
        <AudioPlayer title="Seraphina" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>Spanish (v1 language-specific)</td>
      <td>Columbian accent, Latina profile</td>
    </tr>
  </tbody>
</table>

### French voices

Endpoint documentation: [Rime Arcana FR](/api-reference/tts/rime-arcana-v2/arcana-v2-french-ws)

<table>
  <thead>
    <tr>
      <th>Model</th>
      <th>Name</th>
      <th>Sample</th>
      <th>Gender</th>
      <th>Age</th>
      <th>Language</th>
      <th>Characteristics</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        <code>amarante</code>
      </td>

      <td>Amarante</td>

      <td>
        <AudioPlayer title="Amarante" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>French (v1 language-specific)</td>
      <td>Montreal accent (Canada), White profile</td>
    </tr>

    <tr>
      <td>
        <code>aurelie</code>
      </td>

      <td>Aurelie</td>

      <td>
        <AudioPlayer title="Aurelie" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>French (v1 language-specific)</td>
      <td>French accent, White profile</td>
    </tr>

    <tr>
      <td>
        <code>destin</code>
      </td>

      <td>Destin</td>

      <td>
        <AudioPlayer title="Destin" />
      </td>

      <td>Male</td>
      <td>Young Adult</td>
      <td>French (v1 language-specific)</td>
      <td>French accent, White profile</td>
    </tr>

    <tr>
      <td>
        <code>morel\_marianne</code>
      </td>

      <td>Morel Marianne</td>

      <td>
        <AudioPlayer title="Morel Marianne" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>French (v1 language-specific)</td>
      <td>French accent, White profile</td>
    </tr>

    <tr>
      <td>
        <code>solstice</code>
      </td>

      <td>Solstice</td>

      <td>
        <AudioPlayer title="Solstice" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>French (v1 language-specific)</td>
      <td>French accent, White profile</td>
    </tr>
  </tbody>
</table>

### German voices

Endpoint documentation: [Rime Arcana DE](/api-reference/tts/rime-arcana-v2/arcana-v2-german-ws)

<table>
  <thead>
    <tr>
      <th>Model</th>
      <th>Name</th>
      <th>Sample</th>
      <th>Gender</th>
      <th>Age</th>
      <th>Language</th>
      <th>Characteristics</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        <code>alfhild</code>
      </td>

      <td>Alfhild</td>

      <td>
        <AudioPlayer title="Alfhild" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>German (v1 language-specific)</td>
      <td>German accent, White profile</td>
    </tr>

    <tr>
      <td>
        <code>baldur</code>
      </td>

      <td>Baldur</td>

      <td>
        <AudioPlayer title="Baldur" />
      </td>

      <td>Male</td>
      <td>Adult</td>
      <td>German (v1 language-specific)</td>
      <td>German accent, White profile</td>
    </tr>

    <tr>
      <td>
        <code>kumara</code>
      </td>

      <td>Kumara</td>

      <td>
        <AudioPlayer title="Kumara" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>German (v1 language-specific)</td>
      <td>German accent, White profile</td>
    </tr>

    <tr>
      <td>
        <code>liesel</code>
      </td>

      <td>Liesel</td>

      <td>
        <AudioPlayer title="Liesel" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>German (v1 language-specific)</td>
      <td>Austrian accent, White profile</td>
    </tr>

    <tr>
      <td>
        <code>lorelei</code>
      </td>

      <td>Lorelei</td>

      <td>
        <AudioPlayer title="Lorelei" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>German (v1 language-specific)</td>
      <td>German accent, White profile</td>
    </tr>

    <tr>
      <td>
        <code>runa</code>
      </td>

      <td>Runa</td>

      <td>
        <AudioPlayer title="Runa" />
      </td>

      <td>Female</td>
      <td>Young Adult</td>
      <td>German (v1 language-specific)</td>
      <td>German accent, White profile</td>
    </tr>
  </tbody>
</table>

### Arabic voices

Endpoint documentation: [Rime Arcana AR](/api-reference/tts/rime-arcana-v2/arcana-v2-arabic-ws)

<table>
  <thead>
    <tr>
      <th>Model</th>
      <th>Name</th>
      <th>Sample</th>
      <th>Gender</th>
      <th>Age</th>
      <th>Language</th>
      <th>Characteristics</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        <code>batin</code>
      </td>

      <td>Batin</td>

      <td>
        <AudioPlayer title="Batin" />
      </td>

      <td>Male</td>
      <td>Adult</td>
      <td>Arabic (v1 language-specific)</td>
      <td>Palestinian accent</td>
    </tr>

    <tr>
      <td>
        <code>layla</code>
      </td>

      <td>Layla</td>

      <td>
        <AudioPlayer title="Layla" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>Arabic (v1 language-specific)</td>
      <td>Egyptian accent</td>
    </tr>

    <tr>
      <td>
        <code>qadir</code>
      </td>

      <td>Qadir</td>

      <td>
        <AudioPlayer title="Qadir" />
      </td>

      <td>Male</td>
      <td>Adult</td>
      <td>Arabic (v1 language-specific)</td>
      <td>Egyptian accent</td>
    </tr>

    <tr>
      <td>
        <code>sakina</code>
      </td>

      <td>Sakina</td>

      <td>
        <AudioPlayer title="Sakina" />
      </td>

      <td>Female</td>
      <td>Adult</td>
      <td>Arabic (v1 language-specific)</td>
      <td>Egyptian accent</td>
    </tr>
  </tbody>
</table>

## Next steps

* [TTS HTTP examples](/examples/tts-http) - code samples for calling the TTS API
* [TTS WebSocket examples](/examples/tts-websocket) - real-time streaming with WebSockets
* [Rime Arcana API reference](/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws) - endpoint details and request parameters
* [Voice Agents guide](/voice-agents) - configure voices in agent setups


# Sarvam Bulbul v3
Source: https://docs.slng.ai/voices/sarvam-bulbul

Browse Sarvam Bulbul v3 voices on SLNG — multilingual TTS for 11 Indian languages including Hindi, Tamil, Telugu, Marathi, and Indian English.

Sarvam Bulbul v3 is a multilingual TTS model focused on Indian languages. Unlike other providers on SLNG, Sarvam is **proxied**: your requests go straight to the Sarvam API, and you get back their response unchanged.

To pick a voice, set the `speaker` and `target_language_code` fields in your request body. All voices work across every supported language regardless of which language the audio sample below uses.

```json theme={null}
{
  "text": "Hello, how are you today?",
  "target_language_code": "en-IN",
  "speaker": "shubh"
}
```

Supported language codes: `bn-IN` (Bengali), `en-IN` (English), `gu-IN` (Gujarati), `hi-IN` (Hindi), `kn-IN` (Kannada), `ml-IN` (Malayalam), `mr-IN` (Marathi), `od-IN` (Odia), `pa-IN` (Punjabi), `ta-IN` (Tamil), `te-IN` (Telugu). To try other languages and settings, use the [Sarvam Voice Playground](https://dashboard.sarvam.ai/text-to-speech).

## Supported languages

| Language                              | Code    | Voices |
| ------------------------------------- | ------- | ------ |
| [English (en-IN)](#english-en-in)     | `en-IN` | 37     |
| [Hindi (hi-IN)](#hindi-hi-in)         | `hi-IN` | 37     |
| [Bengali (bn-IN)](#bengali-bn-in)     | `bn-IN` | 36     |
| [Gujarati (gu-IN)](#gujarati-gu-in)   | `gu-IN` | 36     |
| [Kannada (kn-IN)](#kannada-kn-in)     | `kn-IN` | 37     |
| [Malayalam (ml-IN)](#malayalam-ml-in) | `ml-IN` | 37     |
| [Marathi (mr-IN)](#marathi-mr-in)     | `mr-IN` | 37     |
| [Odia (od-IN)](#odia-od-in)           | `od-IN` | 37     |
| [Punjabi (pa-IN)](#punjabi-pa-in)     | `pa-IN` | 37     |
| [Tamil (ta-IN)](#tamil-ta-in)         | `ta-IN` | 37     |
| [Telugu (te-IN)](#telugu-te-in)       | `te-IN` | 37     |
| [HI](#hi)                             | `hi`    | 1      |

## English (en-IN)

| Voice ID   | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                         |
| ---------- | -------- | -------------------------------- | --------- | ----- | -------------- | -------------------------------- |
| `aayan`    | Aayan    | <AudioPlayer title="Aayan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `aditya`   | Aditya   | <AudioPlayer title="Aditya" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `advait`   | Advait   | <AudioPlayer title="Advait" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `amit`     | Amit     | <AudioPlayer title="Amit" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `anand`    | Anand    | <AudioPlayer title="Anand" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ashutosh` | Ashutosh | <AudioPlayer title="Ashutosh" /> | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `dev`      | Dev      | <AudioPlayer title="Dev" />      | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `gokul`    | Gokul    | <AudioPlayer title="Gokul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ishita`   | Ishita   | <AudioPlayer title="Ishita" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kabir`    | Kabir    | <AudioPlayer title="Kabir" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `kavitha`  | Kavitha  | <AudioPlayer title="Kavitha" />  | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kavya`    | Kavya    | <AudioPlayer title="Kavya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `manan`    | Manan    | <AudioPlayer title="Manan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mani`     | Mani     | <AudioPlayer title="Mani" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mohit`    | Mohit    | <AudioPlayer title="Mohit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `neha`     | Neha     | <AudioPlayer title="Neha" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `pooja`    | Pooja    | <AudioPlayer title="Pooja" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `priya`    | Priya    | <AudioPlayer title="Priya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rahul`    | Rahul    | <AudioPlayer title="Rahul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ratan`    | Ratan    | <AudioPlayer title="Ratan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `rehan`    | Rehan    | <AudioPlayer title="Rehan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ritu`     | Ritu     | <AudioPlayer title="Ritu" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rohan`    | Rohan    | <AudioPlayer title="Rohan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `roopa`    | Roopa    | <AudioPlayer title="Roopa" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rupali`   | Rupali   | <AudioPlayer title="Rupali" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shreya`   | Shreya   | <AudioPlayer title="Shreya" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shruti`   | Shruti   | <AudioPlayer title="Shruti" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shubh`    | Shubh    | <AudioPlayer title="Shubh" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `simran`   | Simran   | <AudioPlayer title="Simran" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `soham`    | Soham    | <AudioPlayer title="Soham" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `suhani`   | Suhani   | <AudioPlayer title="Suhani" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `sumit`    | Sumit    | <AudioPlayer title="Sumit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `sunny`    | Sunny    | <AudioPlayer title="Sunny" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `tanya`    | Tanya    | <AudioPlayer title="Tanya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `tarun`    | Tarun    | <AudioPlayer title="Tarun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `varun`    | Varun    | <AudioPlayer title="Varun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `vijay`    | Vijay    | <AudioPlayer title="Vijay" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |

## Hindi (hi-IN)

| Voice ID   | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                         |
| ---------- | -------- | -------------------------------- | --------- | ----- | -------------- | -------------------------------- |
| `aayan`    | Aayan    | <AudioPlayer title="Aayan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `aditya`   | Aditya   | <AudioPlayer title="Aditya" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `advait`   | Advait   | <AudioPlayer title="Advait" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `amit`     | Amit     | <AudioPlayer title="Amit" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `anand`    | Anand    | <AudioPlayer title="Anand" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ashutosh` | Ashutosh | <AudioPlayer title="Ashutosh" /> | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `dev`      | Dev      | <AudioPlayer title="Dev" />      | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `gokul`    | Gokul    | <AudioPlayer title="Gokul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ishita`   | Ishita   | <AudioPlayer title="Ishita" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kabir`    | Kabir    | <AudioPlayer title="Kabir" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `kavitha`  | Kavitha  | <AudioPlayer title="Kavitha" />  | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kavya`    | Kavya    | <AudioPlayer title="Kavya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `manan`    | Manan    | <AudioPlayer title="Manan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mani`     | Mani     | <AudioPlayer title="Mani" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mohit`    | Mohit    | <AudioPlayer title="Mohit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `neha`     | Neha     | <AudioPlayer title="Neha" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `pooja`    | Pooja    | <AudioPlayer title="Pooja" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `priya`    | Priya    | <AudioPlayer title="Priya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rahul`    | Rahul    | <AudioPlayer title="Rahul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ratan`    | Ratan    | <AudioPlayer title="Ratan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `rehan`    | Rehan    | <AudioPlayer title="Rehan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ritu`     | Ritu     | <AudioPlayer title="Ritu" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rohan`    | Rohan    | <AudioPlayer title="Rohan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `roopa`    | Roopa    | <AudioPlayer title="Roopa" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rupali`   | Rupali   | <AudioPlayer title="Rupali" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shreya`   | Shreya   | <AudioPlayer title="Shreya" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shruti`   | Shruti   | <AudioPlayer title="Shruti" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shubh`    | Shubh    | <AudioPlayer title="Shubh" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `simran`   | Simran   | <AudioPlayer title="Simran" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `soham`    | Soham    | <AudioPlayer title="Soham" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `suhani`   | Suhani   | <AudioPlayer title="Suhani" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `sumit`    | Sumit    | <AudioPlayer title="Sumit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `sunny`    | Sunny    | <AudioPlayer title="Sunny" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `tanya`    | Tanya    | <AudioPlayer title="Tanya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `tarun`    | Tarun    | <AudioPlayer title="Tarun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `varun`    | Varun    | <AudioPlayer title="Varun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `vijay`    | Vijay    | <AudioPlayer title="Vijay" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |

## Bengali (bn-IN)

| Voice ID   | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                         |
| ---------- | -------- | -------------------------------- | --------- | ----- | -------------- | -------------------------------- |
| `aayan`    | Aayan    | <AudioPlayer title="Aayan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `aditya`   | Aditya   | <AudioPlayer title="Aditya" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `advait`   | Advait   | <AudioPlayer title="Advait" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `amit`     | Amit     | <AudioPlayer title="Amit" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `anand`    | Anand    | <AudioPlayer title="Anand" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ashutosh` | Ashutosh | <AudioPlayer title="Ashutosh" /> | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `dev`      | Dev      | <AudioPlayer title="Dev" />      | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `gokul`    | Gokul    | <AudioPlayer title="Gokul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ishita`   | Ishita   | <AudioPlayer title="Ishita" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kavitha`  | Kavitha  | <AudioPlayer title="Kavitha" />  | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kavya`    | Kavya    | <AudioPlayer title="Kavya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `manan`    | Manan    | <AudioPlayer title="Manan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mani`     | Mani     | <AudioPlayer title="Mani" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mohit`    | Mohit    | <AudioPlayer title="Mohit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `neha`     | Neha     | <AudioPlayer title="Neha" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `pooja`    | Pooja    | <AudioPlayer title="Pooja" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `priya`    | Priya    | <AudioPlayer title="Priya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rahul`    | Rahul    | <AudioPlayer title="Rahul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ratan`    | Ratan    | <AudioPlayer title="Ratan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `rehan`    | Rehan    | <AudioPlayer title="Rehan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ritu`     | Ritu     | <AudioPlayer title="Ritu" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rohan`    | Rohan    | <AudioPlayer title="Rohan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `roopa`    | Roopa    | <AudioPlayer title="Roopa" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rupali`   | Rupali   | <AudioPlayer title="Rupali" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shreya`   | Shreya   | <AudioPlayer title="Shreya" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shruti`   | Shruti   | <AudioPlayer title="Shruti" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shubh`    | Shubh    | <AudioPlayer title="Shubh" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `simran`   | Simran   | <AudioPlayer title="Simran" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `soham`    | Soham    | <AudioPlayer title="Soham" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `suhani`   | Suhani   | <AudioPlayer title="Suhani" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `sumit`    | Sumit    | <AudioPlayer title="Sumit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `sunny`    | Sunny    | <AudioPlayer title="Sunny" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `tanya`    | Tanya    | <AudioPlayer title="Tanya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `tarun`    | Tarun    | <AudioPlayer title="Tarun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `varun`    | Varun    | <AudioPlayer title="Varun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `vijay`    | Vijay    | <AudioPlayer title="Vijay" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |

## Gujarati (gu-IN)

| Voice ID   | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                         |
| ---------- | -------- | -------------------------------- | --------- | ----- | -------------- | -------------------------------- |
| `aayan`    | Aayan    | <AudioPlayer title="Aayan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `aditya`   | Aditya   | <AudioPlayer title="Aditya" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `advait`   | Advait   | <AudioPlayer title="Advait" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `amit`     | Amit     | <AudioPlayer title="Amit" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `anand`    | Anand    | <AudioPlayer title="Anand" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ashutosh` | Ashutosh | <AudioPlayer title="Ashutosh" /> | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `dev`      | Dev      | <AudioPlayer title="Dev" />      | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `gokul`    | Gokul    | <AudioPlayer title="Gokul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ishita`   | Ishita   | <AudioPlayer title="Ishita" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kabir`    | Kabir    | <AudioPlayer title="Kabir" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `kavitha`  | Kavitha  | <AudioPlayer title="Kavitha" />  | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kavya`    | Kavya    | <AudioPlayer title="Kavya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `manan`    | Manan    | <AudioPlayer title="Manan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mani`     | Mani     | <AudioPlayer title="Mani" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mohit`    | Mohit    | <AudioPlayer title="Mohit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `neha`     | Neha     | <AudioPlayer title="Neha" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `pooja`    | Pooja    | <AudioPlayer title="Pooja" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `priya`    | Priya    | <AudioPlayer title="Priya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `ratan`    | Ratan    | <AudioPlayer title="Ratan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `rehan`    | Rehan    | <AudioPlayer title="Rehan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ritu`     | Ritu     | <AudioPlayer title="Ritu" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rohan`    | Rohan    | <AudioPlayer title="Rohan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `roopa`    | Roopa    | <AudioPlayer title="Roopa" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rupali`   | Rupali   | <AudioPlayer title="Rupali" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shreya`   | Shreya   | <AudioPlayer title="Shreya" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shruti`   | Shruti   | <AudioPlayer title="Shruti" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shubh`    | Shubh    | <AudioPlayer title="Shubh" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `simran`   | Simran   | <AudioPlayer title="Simran" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `soham`    | Soham    | <AudioPlayer title="Soham" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `suhani`   | Suhani   | <AudioPlayer title="Suhani" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `sumit`    | Sumit    | <AudioPlayer title="Sumit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `sunny`    | Sunny    | <AudioPlayer title="Sunny" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `tanya`    | Tanya    | <AudioPlayer title="Tanya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `tarun`    | Tarun    | <AudioPlayer title="Tarun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `varun`    | Varun    | <AudioPlayer title="Varun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `vijay`    | Vijay    | <AudioPlayer title="Vijay" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |

## Kannada (kn-IN)

| Voice ID   | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                         |
| ---------- | -------- | -------------------------------- | --------- | ----- | -------------- | -------------------------------- |
| `aayan`    | Aayan    | <AudioPlayer title="Aayan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `aditya`   | Aditya   | <AudioPlayer title="Aditya" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `advait`   | Advait   | <AudioPlayer title="Advait" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `amit`     | Amit     | <AudioPlayer title="Amit" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `anand`    | Anand    | <AudioPlayer title="Anand" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ashutosh` | Ashutosh | <AudioPlayer title="Ashutosh" /> | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `dev`      | Dev      | <AudioPlayer title="Dev" />      | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `gokul`    | Gokul    | <AudioPlayer title="Gokul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ishita`   | Ishita   | <AudioPlayer title="Ishita" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kabir`    | Kabir    | <AudioPlayer title="Kabir" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `kavitha`  | Kavitha  | <AudioPlayer title="Kavitha" />  | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kavya`    | Kavya    | <AudioPlayer title="Kavya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `manan`    | Manan    | <AudioPlayer title="Manan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mani`     | Mani     | <AudioPlayer title="Mani" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mohit`    | Mohit    | <AudioPlayer title="Mohit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `neha`     | Neha     | <AudioPlayer title="Neha" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `pooja`    | Pooja    | <AudioPlayer title="Pooja" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `priya`    | Priya    | <AudioPlayer title="Priya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rahul`    | Rahul    | <AudioPlayer title="Rahul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ratan`    | Ratan    | <AudioPlayer title="Ratan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `rehan`    | Rehan    | <AudioPlayer title="Rehan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ritu`     | Ritu     | <AudioPlayer title="Ritu" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rohan`    | Rohan    | <AudioPlayer title="Rohan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `roopa`    | Roopa    | <AudioPlayer title="Roopa" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rupali`   | Rupali   | <AudioPlayer title="Rupali" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shreya`   | Shreya   | <AudioPlayer title="Shreya" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shruti`   | Shruti   | <AudioPlayer title="Shruti" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shubh`    | Shubh    | <AudioPlayer title="Shubh" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `simran`   | Simran   | <AudioPlayer title="Simran" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `soham`    | Soham    | <AudioPlayer title="Soham" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `suhani`   | Suhani   | <AudioPlayer title="Suhani" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `sumit`    | Sumit    | <AudioPlayer title="Sumit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `sunny`    | Sunny    | <AudioPlayer title="Sunny" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `tanya`    | Tanya    | <AudioPlayer title="Tanya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `tarun`    | Tarun    | <AudioPlayer title="Tarun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `varun`    | Varun    | <AudioPlayer title="Varun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `vijay`    | Vijay    | <AudioPlayer title="Vijay" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |

## Malayalam (ml-IN)

| Voice ID   | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                         |
| ---------- | -------- | -------------------------------- | --------- | ----- | -------------- | -------------------------------- |
| `aayan`    | Aayan    | <AudioPlayer title="Aayan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `aditya`   | Aditya   | <AudioPlayer title="Aditya" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `advait`   | Advait   | <AudioPlayer title="Advait" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `amit`     | Amit     | <AudioPlayer title="Amit" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `anand`    | Anand    | <AudioPlayer title="Anand" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ashutosh` | Ashutosh | <AudioPlayer title="Ashutosh" /> | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `dev`      | Dev      | <AudioPlayer title="Dev" />      | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `gokul`    | Gokul    | <AudioPlayer title="Gokul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ishita`   | Ishita   | <AudioPlayer title="Ishita" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kabir`    | Kabir    | <AudioPlayer title="Kabir" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `kavitha`  | Kavitha  | <AudioPlayer title="Kavitha" />  | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kavya`    | Kavya    | <AudioPlayer title="Kavya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `manan`    | Manan    | <AudioPlayer title="Manan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mani`     | Mani     | <AudioPlayer title="Mani" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mohit`    | Mohit    | <AudioPlayer title="Mohit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `neha`     | Neha     | <AudioPlayer title="Neha" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `pooja`    | Pooja    | <AudioPlayer title="Pooja" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `priya`    | Priya    | <AudioPlayer title="Priya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rahul`    | Rahul    | <AudioPlayer title="Rahul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ratan`    | Ratan    | <AudioPlayer title="Ratan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `rehan`    | Rehan    | <AudioPlayer title="Rehan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ritu`     | Ritu     | <AudioPlayer title="Ritu" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rohan`    | Rohan    | <AudioPlayer title="Rohan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `roopa`    | Roopa    | <AudioPlayer title="Roopa" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rupali`   | Rupali   | <AudioPlayer title="Rupali" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shreya`   | Shreya   | <AudioPlayer title="Shreya" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shruti`   | Shruti   | <AudioPlayer title="Shruti" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shubh`    | Shubh    | <AudioPlayer title="Shubh" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `simran`   | Simran   | <AudioPlayer title="Simran" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `soham`    | Soham    | <AudioPlayer title="Soham" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `suhani`   | Suhani   | <AudioPlayer title="Suhani" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `sumit`    | Sumit    | <AudioPlayer title="Sumit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `sunny`    | Sunny    | <AudioPlayer title="Sunny" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `tanya`    | Tanya    | <AudioPlayer title="Tanya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `tarun`    | Tarun    | <AudioPlayer title="Tarun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `varun`    | Varun    | <AudioPlayer title="Varun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `vijay`    | Vijay    | <AudioPlayer title="Vijay" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |

## Marathi (mr-IN)

| Voice ID   | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                         |
| ---------- | -------- | -------------------------------- | --------- | ----- | -------------- | -------------------------------- |
| `aayan`    | Aayan    | <AudioPlayer title="Aayan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `aditya`   | Aditya   | <AudioPlayer title="Aditya" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `advait`   | Advait   | <AudioPlayer title="Advait" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `amit`     | Amit     | <AudioPlayer title="Amit" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `anand`    | Anand    | <AudioPlayer title="Anand" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ashutosh` | Ashutosh | <AudioPlayer title="Ashutosh" /> | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `dev`      | Dev      | <AudioPlayer title="Dev" />      | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `gokul`    | Gokul    | <AudioPlayer title="Gokul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ishita`   | Ishita   | <AudioPlayer title="Ishita" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kabir`    | Kabir    | <AudioPlayer title="Kabir" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `kavitha`  | Kavitha  | <AudioPlayer title="Kavitha" />  | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kavya`    | Kavya    | <AudioPlayer title="Kavya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `manan`    | Manan    | <AudioPlayer title="Manan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mani`     | Mani     | <AudioPlayer title="Mani" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mohit`    | Mohit    | <AudioPlayer title="Mohit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `neha`     | Neha     | <AudioPlayer title="Neha" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `pooja`    | Pooja    | <AudioPlayer title="Pooja" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `priya`    | Priya    | <AudioPlayer title="Priya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rahul`    | Rahul    | <AudioPlayer title="Rahul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ratan`    | Ratan    | <AudioPlayer title="Ratan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `rehan`    | Rehan    | <AudioPlayer title="Rehan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ritu`     | Ritu     | <AudioPlayer title="Ritu" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rohan`    | Rohan    | <AudioPlayer title="Rohan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `roopa`    | Roopa    | <AudioPlayer title="Roopa" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rupali`   | Rupali   | <AudioPlayer title="Rupali" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shreya`   | Shreya   | <AudioPlayer title="Shreya" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shruti`   | Shruti   | <AudioPlayer title="Shruti" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shubh`    | Shubh    | <AudioPlayer title="Shubh" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `simran`   | Simran   | <AudioPlayer title="Simran" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `soham`    | Soham    | <AudioPlayer title="Soham" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `suhani`   | Suhani   | <AudioPlayer title="Suhani" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `sumit`    | Sumit    | <AudioPlayer title="Sumit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `sunny`    | Sunny    | <AudioPlayer title="Sunny" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `tanya`    | Tanya    | <AudioPlayer title="Tanya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `tarun`    | Tarun    | <AudioPlayer title="Tarun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `varun`    | Varun    | <AudioPlayer title="Varun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `vijay`    | Vijay    | <AudioPlayer title="Vijay" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |

## Odia (od-IN)

| Voice ID   | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                         |
| ---------- | -------- | -------------------------------- | --------- | ----- | -------------- | -------------------------------- |
| `aayan`    | Aayan    | <AudioPlayer title="Aayan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `aditya`   | Aditya   | <AudioPlayer title="Aditya" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `advait`   | Advait   | <AudioPlayer title="Advait" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `amit`     | Amit     | <AudioPlayer title="Amit" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `anand`    | Anand    | <AudioPlayer title="Anand" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ashutosh` | Ashutosh | <AudioPlayer title="Ashutosh" /> | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `dev`      | Dev      | <AudioPlayer title="Dev" />      | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `gokul`    | Gokul    | <AudioPlayer title="Gokul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ishita`   | Ishita   | <AudioPlayer title="Ishita" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kabir`    | Kabir    | <AudioPlayer title="Kabir" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `kavitha`  | Kavitha  | <AudioPlayer title="Kavitha" />  | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kavya`    | Kavya    | <AudioPlayer title="Kavya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `manan`    | Manan    | <AudioPlayer title="Manan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mani`     | Mani     | <AudioPlayer title="Mani" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mohit`    | Mohit    | <AudioPlayer title="Mohit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `neha`     | Neha     | <AudioPlayer title="Neha" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `pooja`    | Pooja    | <AudioPlayer title="Pooja" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `priya`    | Priya    | <AudioPlayer title="Priya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rahul`    | Rahul    | <AudioPlayer title="Rahul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ratan`    | Ratan    | <AudioPlayer title="Ratan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `rehan`    | Rehan    | <AudioPlayer title="Rehan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ritu`     | Ritu     | <AudioPlayer title="Ritu" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rohan`    | Rohan    | <AudioPlayer title="Rohan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `roopa`    | Roopa    | <AudioPlayer title="Roopa" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rupali`   | Rupali   | <AudioPlayer title="Rupali" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shreya`   | Shreya   | <AudioPlayer title="Shreya" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shruti`   | Shruti   | <AudioPlayer title="Shruti" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shubh`    | Shubh    | <AudioPlayer title="Shubh" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `simran`   | Simran   | <AudioPlayer title="Simran" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `soham`    | Soham    | <AudioPlayer title="Soham" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `suhani`   | Suhani   | <AudioPlayer title="Suhani" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `sumit`    | Sumit    | <AudioPlayer title="Sumit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `sunny`    | Sunny    | <AudioPlayer title="Sunny" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `tanya`    | Tanya    | <AudioPlayer title="Tanya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `tarun`    | Tarun    | <AudioPlayer title="Tarun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `varun`    | Varun    | <AudioPlayer title="Varun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `vijay`    | Vijay    | <AudioPlayer title="Vijay" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |

## Punjabi (pa-IN)

| Voice ID   | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                         |
| ---------- | -------- | -------------------------------- | --------- | ----- | -------------- | -------------------------------- |
| `aayan`    | Aayan    | <AudioPlayer title="Aayan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `aditya`   | Aditya   | <AudioPlayer title="Aditya" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `advait`   | Advait   | <AudioPlayer title="Advait" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `amit`     | Amit     | <AudioPlayer title="Amit" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `anand`    | Anand    | <AudioPlayer title="Anand" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ashutosh` | Ashutosh | <AudioPlayer title="Ashutosh" /> | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `dev`      | Dev      | <AudioPlayer title="Dev" />      | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `gokul`    | Gokul    | <AudioPlayer title="Gokul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ishita`   | Ishita   | <AudioPlayer title="Ishita" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kabir`    | Kabir    | <AudioPlayer title="Kabir" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `kavitha`  | Kavitha  | <AudioPlayer title="Kavitha" />  | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kavya`    | Kavya    | <AudioPlayer title="Kavya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `manan`    | Manan    | <AudioPlayer title="Manan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mani`     | Mani     | <AudioPlayer title="Mani" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mohit`    | Mohit    | <AudioPlayer title="Mohit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `neha`     | Neha     | <AudioPlayer title="Neha" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `pooja`    | Pooja    | <AudioPlayer title="Pooja" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `priya`    | Priya    | <AudioPlayer title="Priya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rahul`    | Rahul    | <AudioPlayer title="Rahul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ratan`    | Ratan    | <AudioPlayer title="Ratan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `rehan`    | Rehan    | <AudioPlayer title="Rehan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ritu`     | Ritu     | <AudioPlayer title="Ritu" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rohan`    | Rohan    | <AudioPlayer title="Rohan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `roopa`    | Roopa    | <AudioPlayer title="Roopa" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rupali`   | Rupali   | <AudioPlayer title="Rupali" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shreya`   | Shreya   | <AudioPlayer title="Shreya" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shruti`   | Shruti   | <AudioPlayer title="Shruti" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shubh`    | Shubh    | <AudioPlayer title="Shubh" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `simran`   | Simran   | <AudioPlayer title="Simran" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `soham`    | Soham    | <AudioPlayer title="Soham" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `suhani`   | Suhani   | <AudioPlayer title="Suhani" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `sumit`    | Sumit    | <AudioPlayer title="Sumit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `sunny`    | Sunny    | <AudioPlayer title="Sunny" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `tanya`    | Tanya    | <AudioPlayer title="Tanya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `tarun`    | Tarun    | <AudioPlayer title="Tarun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `varun`    | Varun    | <AudioPlayer title="Varun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `vijay`    | Vijay    | <AudioPlayer title="Vijay" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |

## Tamil (ta-IN)

| Voice ID   | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                         |
| ---------- | -------- | -------------------------------- | --------- | ----- | -------------- | -------------------------------- |
| `aayan`    | Aayan    | <AudioPlayer title="Aayan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `aditya`   | Aditya   | <AudioPlayer title="Aditya" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `advait`   | Advait   | <AudioPlayer title="Advait" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `amit`     | Amit     | <AudioPlayer title="Amit" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `anand`    | Anand    | <AudioPlayer title="Anand" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ashutosh` | Ashutosh | <AudioPlayer title="Ashutosh" /> | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `dev`      | Dev      | <AudioPlayer title="Dev" />      | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `gokul`    | Gokul    | <AudioPlayer title="Gokul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ishita`   | Ishita   | <AudioPlayer title="Ishita" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kabir`    | Kabir    | <AudioPlayer title="Kabir" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `kavitha`  | Kavitha  | <AudioPlayer title="Kavitha" />  | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kavya`    | Kavya    | <AudioPlayer title="Kavya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `manan`    | Manan    | <AudioPlayer title="Manan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mani`     | Mani     | <AudioPlayer title="Mani" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mohit`    | Mohit    | <AudioPlayer title="Mohit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `neha`     | Neha     | <AudioPlayer title="Neha" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `pooja`    | Pooja    | <AudioPlayer title="Pooja" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `priya`    | Priya    | <AudioPlayer title="Priya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rahul`    | Rahul    | <AudioPlayer title="Rahul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ratan`    | Ratan    | <AudioPlayer title="Ratan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `rehan`    | Rehan    | <AudioPlayer title="Rehan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ritu`     | Ritu     | <AudioPlayer title="Ritu" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rohan`    | Rohan    | <AudioPlayer title="Rohan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `roopa`    | Roopa    | <AudioPlayer title="Roopa" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rupali`   | Rupali   | <AudioPlayer title="Rupali" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shreya`   | Shreya   | <AudioPlayer title="Shreya" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shruti`   | Shruti   | <AudioPlayer title="Shruti" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shubh`    | Shubh    | <AudioPlayer title="Shubh" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `simran`   | Simran   | <AudioPlayer title="Simran" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `soham`    | Soham    | <AudioPlayer title="Soham" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `suhani`   | Suhani   | <AudioPlayer title="Suhani" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `sumit`    | Sumit    | <AudioPlayer title="Sumit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `sunny`    | Sunny    | <AudioPlayer title="Sunny" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `tanya`    | Tanya    | <AudioPlayer title="Tanya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `tarun`    | Tarun    | <AudioPlayer title="Tarun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `varun`    | Varun    | <AudioPlayer title="Varun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `vijay`    | Vijay    | <AudioPlayer title="Vijay" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |

## Telugu (te-IN)

| Voice ID   | Name     | Sample                           | Gender    | Age   | Tone           | Use Case                         |
| ---------- | -------- | -------------------------------- | --------- | ----- | -------------- | -------------------------------- |
| `aayan`    | Aayan    | <AudioPlayer title="Aayan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `aditya`   | Aditya   | <AudioPlayer title="Aditya" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `advait`   | Advait   | <AudioPlayer title="Advait" />   | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `amit`     | Amit     | <AudioPlayer title="Amit" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `anand`    | Anand    | <AudioPlayer title="Anand" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ashutosh` | Ashutosh | <AudioPlayer title="Ashutosh" /> | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `dev`      | Dev      | <AudioPlayer title="Dev" />      | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `gokul`    | Gokul    | <AudioPlayer title="Gokul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ishita`   | Ishita   | <AudioPlayer title="Ishita" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kabir`    | Kabir    | <AudioPlayer title="Kabir" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `kavitha`  | Kavitha  | <AudioPlayer title="Kavitha" />  | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `kavya`    | Kavya    | <AudioPlayer title="Kavya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `manan`    | Manan    | <AudioPlayer title="Manan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mani`     | Mani     | <AudioPlayer title="Mani" />     | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `mohit`    | Mohit    | <AudioPlayer title="Mohit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `neha`     | Neha     | <AudioPlayer title="Neha" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `pooja`    | Pooja    | <AudioPlayer title="Pooja" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `priya`    | Priya    | <AudioPlayer title="Priya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rahul`    | Rahul    | <AudioPlayer title="Rahul" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ratan`    | Ratan    | <AudioPlayer title="Ratan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `rehan`    | Rehan    | <AudioPlayer title="Rehan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `ritu`     | Ritu     | <AudioPlayer title="Ritu" />     | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rohan`    | Rohan    | <AudioPlayer title="Rohan" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `roopa`    | Roopa    | <AudioPlayer title="Roopa" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `rupali`   | Rupali   | <AudioPlayer title="Rupali" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shreya`   | Shreya   | <AudioPlayer title="Shreya" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shruti`   | Shruti   | <AudioPlayer title="Shruti" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `shubh`    | Shubh    | <AudioPlayer title="Shubh" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `simran`   | Simran   | <AudioPlayer title="Simran" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `soham`    | Soham    | <AudioPlayer title="Soham" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `suhani`   | Suhani   | <AudioPlayer title="Suhani" />   | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `sumit`    | Sumit    | <AudioPlayer title="Sumit" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `sunny`    | Sunny    | <AudioPlayer title="Sunny" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `tanya`    | Tanya    | <AudioPlayer title="Tanya" />    | feminine  | Adult | Conversational | Voice Agents, Content Generation |
| `tarun`    | Tarun    | <AudioPlayer title="Tarun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `varun`    | Varun    | <AudioPlayer title="Varun" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |
| `vijay`    | Vijay    | <AudioPlayer title="Vijay" />    | masculine | Adult | Conversational | Voice Agents, Content Generation |

## HI

<Note>
  Audio samples for these voices are coming soon.
</Note>

| Voice ID | Name  | Sample |
| -------- | ----- | ------ |
| `shubh`  | Shubh | —      |


# Soniox TTS v1
Source: https://docs.slng.ai/voices/soniox

Browse Soniox TTS v1 voices on SLNG with audio samples — real-time low-latency text-to-speech with 60+ supported languages and streaming WebSocket synthesis.

Soniox TTS v1 is a real-time, low-latency text-to-speech model with 60 supported languages. Voices are referenced by name. Pass the `voice_id` from the tables below as the `voice` field in your request.

```json theme={null}
{
  "text": "Hello from Sunny Barcelona",
  "voice": "Maya",
  "language": "es"
}
```

Set the optional `language` field to the matching ISO code for the language you want to synthesize. Default voice is `Adrian`, default language is `en`.

## Supported languages

| Language                    | Code | Voices |
| --------------------------- | ---- | ------ |
| [Slovenian](#slovenian)     | `sl` | 15     |
| [Afrikaans](#afrikaans)     | `af` | 12     |
| [Albanian](#albanian)       | `sq` | 12     |
| [Azerbaijani](#azerbaijani) | `az` | 12     |
| [Basque](#basque)           | `eu` | 12     |
| [Belarusian](#belarusian)   | `be` | 12     |
| [Bengali](#bengali)         | `bn` | 12     |
| [Bosnian](#bosnian)         | `bs` | 12     |
| [Bulgarian](#bulgarian)     | `bg` | 12     |
| [Catalan](#catalan)         | `ca` | 12     |
| [Chinese](#chinese)         | `zh` | 12     |
| [Czech](#czech)             | `cs` | 12     |
| [Dutch](#dutch)             | `nl` | 12     |
| [English](#english)         | `en` | 12     |
| [Estonian](#estonian)       | `et` | 12     |
| [French](#french)           | `fr` | 12     |
| [German](#german)           | `de` | 12     |
| [Greek](#greek)             | `el` | 12     |
| [Gujarati](#gujarati)       | `gu` | 12     |
| [Hebrew](#hebrew)           | `he` | 12     |
| [Hindi](#hindi)             | `hi` | 12     |
| [Indonesian](#indonesian)   | `id` | 12     |
| [Italian](#italian)         | `it` | 12     |
| [Kannada](#kannada)         | `kn` | 12     |
| [Korean](#korean)           | `ko` | 12     |
| [Latvian](#latvian)         | `lv` | 12     |
| [Lithuanian](#lithuanian)   | `lt` | 12     |
| [Macedonian](#macedonian)   | `mk` | 12     |
| [Malay](#malay)             | `ms` | 12     |
| [Marathi](#marathi)         | `mr` | 12     |
| [Norwegian](#norwegian)     | `no` | 12     |
| [Persian](#persian)         | `fa` | 12     |
| [Polish](#polish)           | `pl` | 12     |
| [Portuguese](#portuguese)   | `pt` | 12     |
| [Punjabi](#punjabi)         | `pa` | 12     |
| [Romanian](#romanian)       | `ro` | 12     |
| [Russian](#russian)         | `ru` | 12     |
| [Serbian](#serbian)         | `sr` | 12     |
| [Slovak](#slovak)           | `sk` | 12     |
| [Spanish](#spanish)         | `es` | 12     |
| [Swedish](#swedish)         | `sv` | 12     |
| [Tagalog](#tagalog)         | `tl` | 12     |
| [Telugu](#telugu)           | `te` | 12     |
| [Arabic](#arabic)           | `ar` | 11     |
| [Croatian](#croatian)       | `hr` | 11     |
| [Danish](#danish)           | `da` | 11     |
| [Finnish](#finnish)         | `fi` | 11     |
| [Galician](#galician)       | `gl` | 11     |
| [Hungarian](#hungarian)     | `hu` | 11     |
| [Japanese](#japanese)       | `ja` | 11     |
| [Kazakh](#kazakh)           | `kk` | 11     |
| [Malayalam](#malayalam)     | `ml` | 11     |
| [Swahili](#swahili)         | `sw` | 11     |
| [Tamil](#tamil)             | `ta` | 11     |
| [Thai](#thai)               | `th` | 11     |
| [Ukrainian](#ukrainian)     | `uk` | 11     |
| [Urdu](#urdu)               | `ur` | 11     |
| [Turkish](#turkish)         | `tr` | 10     |
| [Vietnamese](#vietnamese)   | `vi` | 10     |
| [Welsh](#welsh)             | `cy` | 10     |

## Slovenian

| Voice ID | Name          | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------------- | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian        | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire        | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel        | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace         | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack          | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji         | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya          | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `Maya`   | Maya (Female) | —                              | —         | —     | —                            | —                             |
| `mina`   | Mina          | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina          | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah          | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen          | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `Daniel` | Daniel (Male) | —                              | —         | —     | —                            | —                             |
| `Noah`   | Noah (Male)   | —                              | —         | —     | —                            | —                             |
| `Nina`   | Nina (Female) | —                              | —         | —     | —                            | —                             |

## Afrikaans

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Albanian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Azerbaijani

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Basque

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Belarusian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Bengali

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Bosnian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Bulgarian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Catalan

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Chinese

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Czech

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Dutch

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## English

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Estonian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## French

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## German

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Greek

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Gujarati

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Hebrew

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Hindi

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Indonesian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Italian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Kannada

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Korean

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Latvian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Lithuanian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Macedonian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Malay

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Marathi

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Norwegian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Persian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Polish

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Portuguese

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Punjabi

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Romanian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Russian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Serbian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Slovak

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Spanish

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Swedish

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Tagalog

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Telugu

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Arabic

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Croatian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Danish

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Finnish

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Galician

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Hungarian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Japanese

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Kazakh

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Malayalam

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Swahili

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Tamil

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Thai

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `emma`   | Emma   | <AudioPlayer title="Emma" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Ukrainian

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Urdu

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `claire` | Claire | <AudioPlayer title="Claire" /> | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Turkish

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Vietnamese

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |

## Welsh

| Voice ID | Name   | Sample                         | Gender    | Age   | Tone                         | Use Case                      |
| -------- | ------ | ------------------------------ | --------- | ----- | ---------------------------- | ----------------------------- |
| `adrian` | Adrian | <AudioPlayer title="Adrian" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `daniel` | Daniel | <AudioPlayer title="Daniel" /> | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `grace`  | Grace  | <AudioPlayer title="Grace" />  | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `jack`   | Jack   | <AudioPlayer title="Jack" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `kenji`  | Kenji  | <AudioPlayer title="Kenji" />  | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `maya`   | Maya   | <AudioPlayer title="Maya" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `mina`   | Mina   | <AudioPlayer title="Mina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `nina`   | Nina   | <AudioPlayer title="Nina" />   | feminine  | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `noah`   | Noah   | <AudioPlayer title="Noah" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |
| `owen`   | Owen   | <AudioPlayer title="Owen" />   | masculine | Adult | Studio quality, multilingual | Voice Agents, General Purpose |


# WebSocket integration guide
Source: https://docs.slng.ai/websocket-guide

Production patterns for SLNG WebSocket integrations. Reconnection, backpressure, audio buffering, error handling, and troubleshooting common issues.

This guide covers what you need to build a production-ready WebSocket integration. For message types and parameters, see the [WebSocket protocol reference](/websockets).

**Prerequisites:**

* Familiarity with the [SLNG WebSocket protocol](/websockets)
* A working WebSocket connection (see the [TTS](/examples/tts-websocket) or [STT](/examples/stt-websocket) quick starts)

***

## Best Practices

Items 1 and 2 are required for any production integration. Items 3-6 improve quality and resilience.

### 1. Connection Management

**Implement Reconnection Logic:**

```javascript theme={null}
class ResilientWebSocket {
  constructor(url) {
    this.url = url;
    this.backoff = 1000;
    this.maxBackoff = 30000;
    this.connect();
  }

  connect() {
    this.ws = new WebSocket(this.url);

    this.ws.onclose = () => {
      console.log(`Reconnecting in ${this.backoff}ms`);
      setTimeout(() => this.connect(), this.backoff);
      this.backoff = Math.min(this.backoff * 2, this.maxBackoff);
    };

    this.ws.onopen = () => {
      console.log("Connected");
      this.backoff = 1000; // Reset backoff on successful connection
    };
  }
}
```

### 2. Error Handling

Always handle errors gracefully:

```javascript theme={null}
ws.onerror = (error) => {
  console.error("WebSocket error:", error);
  // Notify user, attempt recovery
};

ws.onmessage = (event) => {
  if (typeof event.data === "string") {
    const message = JSON.parse(event.data);
    if (message.type === "error") {
      handleServerError(message.code, message.message);
    }
  }
};
```

### 3. Buffer Management (TTS)

Use flush strategically to control latency vs. quality:

```javascript theme={null}
// For low latency: flush after each sentence
ws.send(JSON.stringify({ type: "text", text: sentence }));
ws.send(JSON.stringify({ type: "flush" }));

// For better quality: batch multiple sentences
ws.send(JSON.stringify({ type: "text", text: paragraph }));
// ... send more text ...
ws.send(JSON.stringify({ type: "flush" })); // Flush at the end
```

### 4. Audio Format Consistency

Ensure your audio format matches configuration:

```javascript theme={null}
// Configuration
{
  encoding: 'linear16',    // 16-bit PCM
  sample_rate: 16000       // 16kHz
}

// Audio capture must match:
// - 16-bit samples
// - 16000 Hz sample rate
// - Single channel (mono)
```

### 5. Heartbeat/Keep-Alive

Send keep-alive messages to prevent idle disconnection. For STT sessions, use the built-in `keepalive` message type. For TTS, use a WebSocket ping frame:

```javascript theme={null}
// STT: use the protocol-level keepalive message
let keepaliveInterval = setInterval(() => {
  if (ws.readyState === WebSocket.OPEN) {
    ws.send(JSON.stringify({ type: "keepalive" }));
  }
}, 10000); // Every 10 seconds

ws.onclose = () => {
  clearInterval(keepaliveInterval);
};
```

### 6. Interruption Handling (TTS)

<Note>[SLNG Voice Agents](/voice-agents) handle interruptions automatically via `enable_interruptions`. This only applies if you manage TTS WebSocket connections yourself.</Note>

When building your own voice agent, stop TTS output as soon as the user starts speaking:

* Send `{ "type": "close" }` to stop server-side generation and end the session
* Send `{ "type": "clear" }` to discard queued audio (keeps the session open)
* Clear your local audio buffer and stop playback

For complete patterns (immediate interrupt, clear-and-restart, fade-out, voice agent loop), see [TTS WebSocket examples](/examples/tts-websocket#interruption--cancellation-patterns).

***

## Troubleshooting

For WebSocket error codes and fixes for connection drops, choppy audio, delayed transcriptions, and authentication failures, see [Error Codes & Troubleshooting](/reference/errors).

***

## Next Steps

<CardGroup>
  <Card title="WebSocket protocol" icon="plug" href="/websockets">
    Message types, parameters, and connection URLs
  </Card>

  <Card title="Protocol comparison" icon="arrow-left-right" href="/protocols">
    HTTP vs. WebSocket: when to use each
  </Card>

  <Card title="TTS examples" icon="bolt" href="/examples/tts-websocket">
    JavaScript and Python code for real-time TTS
  </Card>

  <Card title="STT examples" icon="waveform" href="/examples/stt-websocket">
    JavaScript and Python code for real-time STT
  </Card>
</CardGroup>


# WebSocket API reference
Source: https://docs.slng.ai/websockets

Stream text-to-speech and speech-to-text in real time over WebSocket. Message format, init handshake, sub-100ms streaming, and reconnection patterns.

WebSocket connections give you sub-100ms latency and bidirectional streaming, ideal for voice agents, live transcription, and any use case where audio flows continuously. If you don't need real-time streaming, see [HTTP vs. WebSocket](/protocols) instead.

**Prerequisites:**

* An [SLNG key](/getting-started)
* Basic familiarity with WebSockets (open, send, receive, close)

## Protocol overview

This page documents the WebSocket protocol used by SLNG-hosted models and [bridges](/execution-layer/unified-api). Third-party providers (Deepgram, KugelAudio, Sarvam) may expose their own native WebSocket formats. Check the per-model API reference in the sidebar for provider-specific details.

<Note>Supported encodings, sample rates, and optional fields vary by model. For model-specific parameters, see the Text-to-Speech and Speech-to-Text tabs in the sidebar.</Note>

***

## TTS WebSocket Protocol

For the full per-model parameter list and response schema, see the model's page in the **Text-to-Speech** sidebar.

### Connection

```
WSS wss://api.slng.ai/v1/tts/{provider}/{model}:{variant}
```

Use the direct provider path for proxied models and add the `slng/` prefix for
SLNG-hosted models:

| Hosting                | URL pattern                                                  | Example                                            |
| ---------------------- | ------------------------------------------------------------ | -------------------------------------------------- |
| Proxied provider model | `wss://api.slng.ai/v1/tts/{provider}/{model}:{variant}`      | `wss://api.slng.ai/v1/tts/deepgram/aura:2`         |
| SLNG-hosted model      | `wss://api.slng.ai/v1/tts/slng/{provider}/{model}:{variant}` | `wss://api.slng.ai/v1/tts/slng/deepgram/aura:2-en` |

### Message Flow

```mermaid theme={null}
sequenceDiagram
    participant Client
    participant SLNG
    Client->>SLNG: Connect
    SLNG-->>Client: Connection open
    Client->>SLNG: { type: "init", model, voice, config }
    SLNG-->>Client: { type: "ready", session_id }
    Client->>SLNG: { type: "text", text: "..." }
    SLNG-->>Client: { type: "audio_chunk", data }
    SLNG-->>Client: { type: "audio_chunk", data }
    Client->>SLNG: { type: "flush" }
    SLNG-->>Client: { type: "flushed" }
    Client->>SLNG: { type: "text", text: "..." }
    SLNG-->>Client: { type: "audio_chunk", data }
    Client->>SLNG: { type: "clear" }
    SLNG-->>Client: { type: "cleared" }
    SLNG-->>Client: { type: "audio_end" }
    Client->>SLNG: { type: "close" }
```

Browse all available TTS models and endpoints on the [Text-to-Speech models](/models/tts) page.

### Client → Server Messages

#### Initialize Session

Initialize a session with model and voice configuration before sending text.

```json theme={null}
{
  "type": "init",
  "model": "aura:2",
  "voice": "aura-2-thalia-en",
  "config": {
    "sample_rate": 24000,
    "encoding": "linear16",  // 16-bit signed PCM — the most common raw audio format
    "language": "en",
    "speed": 1.0,
    "pronunciation": {
      "mode": "rewrite",
      "name": "brand-pronunciations"
    }
  }
}
```

Use `config.pronunciation` to set a default [pronunciation dictionary](/pronunciation-dictionaries) for the session.

**Parameters:**

| Field                  | Type                                | Required | Description                                    |
| ---------------------- | ----------------------------------- | -------- | ---------------------------------------------- |
| `type`                 | `"init"`                            | Yes      | Message type                                   |
| `model`                | `string`                            | Yes      | Model identifier                               |
| `voice`                | `string`                            | No       | Voice identifier                               |
| `config`               | `object`                            | No       | Session configuration                          |
| `config.sample_rate`   | `number`                            | No       | Audio sample rate in Hz                        |
| `config.encoding`      | `"linear16"` \| `"mp3"` \| `"opus"` | No       | Audio encoding format                          |
| `config.language`      | `string`                            | No       | Language code                                  |
| `config.speed`         | `number`                            | No       | Speech speed multiplier                        |
| `config.pronunciation` | `object`                            | No       | Default pronunciation dictionary for TTS turns |

#### Send Text for Synthesis

Send text to synthesize into audio. Set `flush: true` to finalize the current segment immediately instead of waiting for more text.

```json theme={null}
{
  "type": "text",
  "text": "Hello from SLNG.",
  "flush": false,
  "pronunciation": {
    "mode": "rewrite",
    "name": "support-pronunciations"
  }
}
```

Use `pronunciation` on a text message to override the active dictionary for that turn. Later turns reuse the most recent active dictionary.

| Field           | Type      | Required | Description                                     |
| --------------- | --------- | -------- | ----------------------------------------------- |
| `type`          | `"text"`  | Yes      | Message type                                    |
| `text`          | `string`  | Yes      | Text to synthesize                              |
| `flush`         | `boolean` | No       | Whether to flush remaining audio immediately    |
| `pronunciation` | `object`  | No       | Pronunciation dictionary override for this turn |

#### Flush Buffer

Force any buffered text/audio to be finalized and delivered.

```json theme={null}
{
  "type": "flush"
}
```

#### Clear Buffer

Clear any queued text/audio from the current session.

```json theme={null}
{
  "type": "clear"
}
```

#### Close Session

Close the current session and stop any further audio generation.

```json theme={null}
{
  "type": "close"
}
```

### Server → Client Messages

#### Session Ready

Indicates the session is ready to receive messages.

```json theme={null}
{
  "type": "ready",
  "session_id": "session_123"
}
```

#### Audio Chunk

Chunk of base64-encoded audio data.

```json theme={null}
{
  "type": "audio_chunk",
  "data": "SGVsbG8gV29ybGQ=",
  "sequence": 1
}
```

| Field      | Type            | Required | Description                  |
| ---------- | --------------- | -------- | ---------------------------- |
| `type`     | `"audio_chunk"` | Yes      | Message type                 |
| `data`     | `string`        | Yes      | Base64-encoded audio data    |
| `sequence` | `integer`       | No       | Sequence number for ordering |

<Tip>Audio may also arrive as raw binary WebSocket frames instead of base64 JSON. Binary frames have lower overhead.</Tip>

#### Segment Start

Signals the start of a synthesized segment.

```json theme={null}
{
  "type": "segment_start",
  "segment_id": "seg_1"
}
```

#### Segment End

Signals the end of a synthesized segment.

```json theme={null}
{
  "type": "segment_end",
  "segment_id": "seg_1"
}
```

#### Flushed

Acknowledges that buffered output was flushed.

```json theme={null}
{
  "type": "flushed"
}
```

#### Cleared

Acknowledges that queued output was cleared.

```json theme={null}
{
  "type": "cleared"
}
```

#### Audio End

Signals the end of audio generation.

```json theme={null}
{
  "type": "audio_end",
  "duration": 0.12
}
```

| Field      | Type          | Required | Description    |
| ---------- | ------------- | -------- | -------------- |
| `type`     | `"audio_end"` | Yes      | Message type   |
| `duration` | `number`      | No       | Audio duration |

#### Error

Indicates an error occurred during synthesis.

```json theme={null}
{
  "type": "error",
  "code": "provider_error",
  "message": "Upstream error"
}
```

| Field     | Type      | Required | Description                      |
| --------- | --------- | -------- | -------------------------------- |
| `type`    | `"error"` | Yes      | Message type                     |
| `code`    | `string`  | Yes      | Error code                       |
| `message` | `string`  | Yes      | Human-readable error description |

**Common Error Codes:**

* `auth_error`: Invalid or missing SLNG key
* `config_error`: Invalid configuration
* `rate_limit`: Too many requests
* `provider_error`: Upstream provider error

***

## STT WebSocket Protocol

For the full per-model parameter list and response schema, see the model's page in the **Speech-to-Text** sidebar.

### Connection

```
WSS wss://api.slng.ai/v1/stt/{provider}/{model}:{variant}
```

Use the direct provider path for proxied models and add the `slng/` prefix for
SLNG-hosted models:

| Hosting                | URL pattern                                                  | Example                                                 |
| ---------------------- | ------------------------------------------------------------ | ------------------------------------------------------- |
| Proxied provider model | `wss://api.slng.ai/v1/stt/{provider}/{model}:{variant}`      | `wss://api.slng.ai/v1/stt/deepgram/nova:3`              |
| SLNG-hosted model      | `wss://api.slng.ai/v1/stt/slng/{provider}/{model}:{variant}` | `wss://api.slng.ai/v1/stt/slng/openai/whisper:large-v3` |

### Message Flow

```mermaid theme={null}
sequenceDiagram
    participant Client
    participant SLNG
    Client->>SLNG: Connect
    SLNG-->>Client: Connection open
    Client->>SLNG: { type: "init", config }
    SLNG-->>Client: { type: "ready", session_id }
    Client->>SLNG: binary audio data
    SLNG-->>Client: { type: "partial_transcript" }
    Client->>SLNG: binary audio data
    SLNG-->>Client: { type: "final_transcript" }
    Note over Client: Silence — send keepalive
    Client->>SLNG: { type: "keepalive" }
    Client->>SLNG: binary audio data
    SLNG-->>Client: { type: "final_transcript" }
    Client->>SLNG: { type: "finalize" }
    SLNG-->>Client: { type: "final_transcript" }
    Client->>SLNG: { type: "close" }
```

Browse all available STT models and endpoints on the [Speech-to-Text models](/models/stt) page.

### Client → Server Messages

#### Initialize Session

Initialize a session with recognition configuration before streaming audio.

```json theme={null}
{
  "type": "init",
  "config": {
    "language": "en",
    "sample_rate": 16000,
    "encoding": "linear16",
    "enable_vad": true,
    "enable_diarization": false,
    "enable_word_timestamps": true,
    "enable_partials": true
  }
}
```

**Parameters:**

| Field                           | Type                                | Required | Description                        |
| ------------------------------- | ----------------------------------- | -------- | ---------------------------------- |
| `type`                          | `"init"`                            | Yes      | Message type                       |
| `config`                        | `object`                            | No       | Recognition configuration          |
| `config.language`               | `string`                            | No       | Language code for recognition      |
| `config.sample_rate`            | `number`                            | No       | Audio sample rate in Hz            |
| `config.encoding`               | `"linear16"` \| `"mp3"` \| `"opus"` | No       | Audio encoding format              |
| `config.enable_vad`             | `boolean`                           | No       | Enable voice activity detection    |
| `config.enable_diarization`     | `boolean`                           | No       | Enable speaker diarization         |
| `config.enable_word_timestamps` | `boolean`                           | No       | Include word-level timestamps      |
| `config.enable_partials`        | `boolean`                           | No       | Enable partial/interim transcripts |

#### Send Audio Data

Stream an audio frame to be transcribed. After initialization, send audio in one of two formats:

<Tip>Binary frames are recommended over base64-encoded JSON for lower overhead.</Tip>

**Binary frames**: send raw PCM audio samples directly as binary WebSocket frames:

```javascript theme={null}
ws.send(audioBuffer); // ArrayBuffer or Uint8Array
```

**JSON messages** with base64-encoded data:

```json theme={null}
{
  "type": "audio",
  "data": "SGVsbG8gV29ybGQ="
}
```

| Field  | Type      | Required | Description               |
| ------ | --------- | -------- | ------------------------- |
| `type` | `"audio"` | Yes      | Message type              |
| `data` | `string`  | Yes      | Base64-encoded audio data |

#### Finalize Transcription

Force the server to finalize any buffered audio and return results. The connection stays open so you can continue streaming.

```json theme={null}
{
  "type": "finalize"
}
```

#### Close Stream

Signal that no more audio will be sent. The server processes any remaining audio, sends final results, then closes the connection.

```json theme={null}
{
  "type": "close"
}
```

<Tip>Use `finalize` when you want to flush results mid-session (e.g., between utterances). Use `close` when you are done and want to end the session.</Tip>

#### Keep-Alive

Send periodically during silence to prevent idle disconnection.

```json theme={null}
{
  "type": "keepalive"
}
```

### Server → Client Messages

#### Session Ready

Indicates the session is ready to receive audio.

```json theme={null}
{
  "type": "ready",
  "session_id": "session_123"
}
```

#### Partial Transcript

Interim transcription result.

```json theme={null}
{
  "type": "partial_transcript",
  "transcript": "Hello",
  "confidence": 0.91
}
```

| Field        | Type                   | Required | Description             |
| ------------ | ---------------------- | -------- | ----------------------- |
| `type`       | `"partial_transcript"` | Yes      | Message type            |
| `transcript` | `string`               | Yes      | Transcribed text so far |
| `confidence` | `number`               | No       | Confidence score (0-1)  |

#### Final Transcript

Final transcription result with optional metadata.

```json theme={null}
{
  "type": "final_transcript",
  "transcript": "Hello world",
  "confidence": 0.97,
  "language": "en",
  "duration": 2.5
}
```

| Field        | Type                 | Required | Description                         |
| ------------ | -------------------- | -------- | ----------------------------------- |
| `type`       | `"final_transcript"` | Yes      | Message type                        |
| `transcript` | `string`             | Yes      | Complete transcribed text           |
| `confidence` | `number`             | No       | Overall confidence score (0-1)      |
| `language`   | `string`             | No       | Detected or specified language code |
| `duration`   | `number`             | No       | Audio duration                      |

#### Error

Indicates an error occurred during recognition.

```json theme={null}
{
  "type": "error",
  "code": "provider_error",
  "message": "Upstream error"
}
```

| Field     | Type      | Required | Description                      |
| --------- | --------- | -------- | -------------------------------- |
| `type`    | `"error"` | Yes      | Message type                     |
| `code`    | `string`  | Yes      | Error code                       |
| `message` | `string`  | Yes      | Human-readable error description |

***

## Next Steps

<CardGroup>
  <Card title="Integration guide" icon="wrench" href="/websocket-guide">
    Best practices and troubleshooting
  </Card>

  <Card title="TTS examples" icon="audio-lines" href="/examples/tts-websocket">
    JavaScript and Python code for real-time TTS
  </Card>

  <Card title="STT examples" icon="ear" href="/examples/stt-websocket">
    JavaScript and Python code for real-time STT
  </Card>

  <Card title="Protocol comparison" icon="arrow-left-right" href="/protocols">
    HTTP vs. WebSocket: when to use each
  </Card>
</CardGroup>