HTTP examples

Want to try TTS without setting up code? Open the live demo and test different models and voices in your browser.

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

Basic Request

Send text and receive a complete audio file in WAV format:

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

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

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)

It will sound like this:

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:

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.

With a Different Model

Each model has its own endpoint and may use different parameters. For example, Rime Arcana uses speaker instead of model:

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. To control how brand names, acronyms, and domain-specific terms are spoken, add a pronunciation dictionary to your TTS request. For voice catalogs with audio samples, browse the Voices section in the sidebar.

Next Steps

Live TTS demo

Try TTS in your browser, no setup needed

TTS WebSocket examples

Stream audio in real time for voice agents

Text-to-Speech models

Browse all TTS models and endpoints

Pronunciation dictionaries

Reuse pronunciation rules across TTS requests

TTS API reference

Endpoint-specific parameters

⌘I

Get started

Text-to-Speech

Speech-to-Text

Managed Agents

Integrations

SDKs & Tools

Reference

Placeholders

Basic Request

More Examples

With Voice Selection (Deepgram Aura)

With a Different Model

Next Steps

Live TTS demo

TTS WebSocket examples

Text-to-Speech models

Pronunciation dictionaries

TTS API reference

​Placeholders

​Basic Request

​More Examples

​With Voice Selection (Deepgram Aura)

​With a Different Model

​Next Steps

Live TTS demo

TTS WebSocket examples

Text-to-Speech models

Pronunciation dictionaries

TTS API reference

Placeholders

Basic Request

More Examples

With Voice Selection (Deepgram Aura)

With a Different Model

Next Steps