Documentation

Available Models

SLNG provides access to best-in-class speech models through a single API. All models support consistent protocols and provide production-ready performance.

Quick Navigation: All Models · TTS Models · STT Models · Selection Guide

All Models Overview

Aura

SLNGTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2 (English)Aura 2 (Spanish)

Regions

apeu

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Kokoro

SLNGTTS

Kokoro TTS model deployed on SLNG infrastructure

API Docs

medium

HTTP

Variants

Kokoro v1

Regions

Use Cases

Voice synthesisContent creation

Melo

SLNGTTS

Melo - High-quality TTS model deployed on SLNG infrastructure

API Docs

medium

6 languages

HTTP

Variants

Melo v1

Regions

Use Cases

Voice agentsContent creationInteractive applications

Nova

SLNGSTT

Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.

API Docs

real-time

40 languages

HTTPWebSocket

Variants

Deepgram Nova 3 EnglishDeepgram Nova 3 SpanishDeepgram Nova 3 Hindi

Regions

apeume

Use Cases

Real-time transcriptionVoice agentsLive streaming

Orpheus

SLNGTTS

High-quality streaming TTS with emotion control, hosted on SLNG infrastructure

API Docs

low

HTTPWebSocket

Variants

Orpheus English

Regions

Use Cases

Voice agentsInteractive applicationsConversational AI

Rime Arcana

SLNGTTS

Rime Arcana TTS - High-quality multilingual text-to-speech with on-premises deployment support

API Docs

medium

5 languages

HTTPWebSocket

Variants

Rime Arcana 3 EnglishRime Arcana 3 FrenchRime Arcana 3 Hindi

Regions

apeume

Use Cases

Voice agentsInteractive applicationsContent localization

Speechmatics

SLNGSTT

Speech-to-Text. Real-time speech-to-text transcription using Speechmatics model hosted by SLNG via WebSocket. Supports streaming audio input with intelligent Voice Activity Detection (VAD), partial transcripts for immediate feedback. Perfect for live transcription, voice commands, and real-time captioning. Supports English and Spanish with high accuracy.

API Docs

realtime

Multi-language

WebSocket

Variants

Speechmatics ENSpeechmatics ES

Regions

Use Cases

Real-time transcriptionVoice commandsLive captioning

Whisper

SLNGSTT

Speech-to-Text using Whisper Large v3 model hosted by SLNG. Supports 99+ languages with automatic language detection. Best for general-purpose transcription with high accuracy.

API Docs

batch

Multi-language

HTTPWebSocket

Variants

Whisper Large v3

Regions

Use Cases

Batch transcriptionMeeting notesContent creation

Aura

DeepgramTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2

Regions

afcaeume

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Nova

DeepgramSTT

Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.

API Docs

real-time

40 languages

HTTPWebSocket

Variants

Nova 2Nova 3Nova 3 Medical

Regions

afcaeume

Use Cases

Real-time transcriptionVoice agentsLive streaming

Eleven Flash

ElevenLabsTTS

Ultra-low latency TTS with industry-leading speed

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven Flash v2Eleven Flash v2.5

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Eleven Multilingual

ElevenLabsTTS

Multilingual TTS with ultra-low latency

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven Multilingual v2

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Eleven v3

ElevenLabsTTS

Premium TTS with industry-leading latency and voice quality

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven v3

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Text-to-Speech Models

Aura

SLNGTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2 (English)Aura 2 (Spanish)

Regions

apeu

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Kokoro

SLNGTTS

Kokoro TTS model deployed on SLNG infrastructure

API Docs

medium

HTTP

Variants

Kokoro v1

Regions

Use Cases

Voice synthesisContent creation

Melo

SLNGTTS

Melo - High-quality TTS model deployed on SLNG infrastructure

API Docs

medium

6 languages

HTTP

Variants

Melo v1

Regions

Use Cases

Voice agentsContent creationInteractive applications

Orpheus

SLNGTTS

High-quality streaming TTS with emotion control, hosted on SLNG infrastructure

API Docs

low

HTTPWebSocket

Variants

Orpheus English

Regions

Use Cases

Voice agentsInteractive applicationsConversational AI

Rime Arcana

SLNGTTS

Rime Arcana TTS - High-quality multilingual text-to-speech with on-premises deployment support

API Docs

medium

5 languages

HTTPWebSocket

Variants

Rime Arcana 3 EnglishRime Arcana 3 FrenchRime Arcana 3 Hindi

Regions

apeume

Use Cases

Voice agentsInteractive applicationsContent localization

Aura

DeepgramTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2

Regions

afcaeume

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Eleven Flash

ElevenLabsTTS

Ultra-low latency TTS with industry-leading speed

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven Flash v2Eleven Flash v2.5

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Eleven Multilingual

ElevenLabsTTS

Multilingual TTS with ultra-low latency

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven Multilingual v2

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Eleven v3

ElevenLabsTTS

Premium TTS with industry-leading latency and voice quality

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven v3

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Speech-to-Text Models

Nova

SLNGSTT

Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.

API Docs

real-time

40 languages

HTTPWebSocket

Variants

Deepgram Nova 3 EnglishDeepgram Nova 3 SpanishDeepgram Nova 3 Hindi

Regions

apeume

Use Cases

Real-time transcriptionVoice agentsLive streaming

Speechmatics

SLNGSTT

API Docs

realtime

Multi-language

WebSocket

Variants

Speechmatics ENSpeechmatics ES

Regions

Use Cases

Real-time transcriptionVoice commandsLive captioning

Whisper

SLNGSTT

Speech-to-Text using Whisper Large v3 model hosted by SLNG. Supports 99+ languages with automatic language detection. Best for general-purpose transcription with high accuracy.

API Docs

batch

Multi-language

HTTPWebSocket

Variants

Whisper Large v3

Regions

Use Cases

Batch transcriptionMeeting notesContent creation

Nova

DeepgramSTT

Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.

API Docs

real-time

40 languages

HTTPWebSocket

Variants

Nova 2Nova 3Nova 3 Medical

Regions

afcaeume

Use Cases

Real-time transcriptionVoice agentsLive streaming

Model Selection Guide

With the variety of models available, choosing the right one depends on your specific use case and requirements. Here are some recommendations to help you decide based on our internal benchmarks.

Filter models by: Use Case · Performance · Language · Region

By Use Case

Different applications have different requirements. Voice agents need low latency, while audiobooks prioritize quality over speed.

Real-time Voice Agents

Models optimized for low-latency conversational applications:

Aura

SLNGTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2 (English)Aura 2 (Spanish)

Regions

apeu

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Aura

DeepgramTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2

Regions

afcaeume

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Eleven Flash

ElevenLabsTTS

Ultra-low latency TTS with industry-leading speed

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven Flash v2Eleven Flash v2.5

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Eleven Multilingual

ElevenLabsTTS

Multilingual TTS with ultra-low latency

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven Multilingual v2

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Eleven v3

ElevenLabsTTS

Premium TTS with industry-leading latency and voice quality

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven v3

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Voice Assistants

Models ideal for voice assistant applications:

Aura

SLNGTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2 (English)Aura 2 (Spanish)

Regions

apeu

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Aura

DeepgramTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2

Regions

afcaeume

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Content Creation & Audiobooks

Models with premium quality for long-form content:

Kokoro

SLNGTTS

Kokoro TTS model deployed on SLNG infrastructure

API Docs

medium

HTTP

Variants

Kokoro v1

Regions

Use Cases

Voice synthesisContent creation

Melo

SLNGTTS

Melo - High-quality TTS model deployed on SLNG infrastructure

API Docs

medium

6 languages

HTTP

Variants

Melo v1

Regions

Use Cases

Voice agentsContent creationInteractive applications

Whisper

SLNGSTT

Speech-to-Text using Whisper Large v3 model hosted by SLNG. Supports 99+ languages with automatic language detection. Best for general-purpose transcription with high accuracy.

API Docs

batch

Multi-language

HTTPWebSocket

Variants

Whisper Large v3

Regions

Use Cases

Batch transcriptionMeeting notesContent creation

Batch Transcription

Models optimized for accuracy in offline processing:

Whisper

SLNGSTT

Speech-to-Text using Whisper Large v3 model hosted by SLNG. Supports 99+ languages with automatic language detection. Best for general-purpose transcription with high accuracy.

API Docs

batch

Multi-language

HTTPWebSocket

Variants

Whisper Large v3

Regions

Use Cases

Batch transcriptionMeeting notesContent creation

IVR & Phone Systems

Models suited for telephony and IVR applications:

Aura

SLNGTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2 (English)Aura 2 (Spanish)

Regions

apeu

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Aura

DeepgramTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2

Regions

afcaeume

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Multilingual Applications

Models with broad language support:

No models found for use case "Multilingual content".

By Performance Requirement

Performance trade-offs matter. Ultra-low latency models sacrifice some quality, while high-accuracy models may have longer processing times.

Lowest Latency (sub-100ms)

ElevenLabs Eleven Flash v2.5

Most Voices (50+)

Deepgram Aura

Best Transcription Accuracy

SLNG Whisper Large v3

Real-time Streaming

Deepgram Nova 2 (STT)
Deepgram Aura (TTS)

Emotion Control

SLNG Orpheus

By Language Support

Language support varies by model. Some excel at English only, while others support dozens of languages with varying quality.

English

All models support English - here are the available options:

Aura

SLNGTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2 (English)Aura 2 (Spanish)

Regions

apeu

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Kokoro

SLNGTTS

Kokoro TTS model deployed on SLNG infrastructure

API Docs

medium

HTTP

Variants

Kokoro v1

Regions

Use Cases

Voice synthesisContent creation

Melo

SLNGTTS

Melo - High-quality TTS model deployed on SLNG infrastructure

API Docs

medium

6 languages

HTTP

Variants

Melo v1

Regions

Use Cases

Voice agentsContent creationInteractive applications

Nova

SLNGSTT

Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.

API Docs

real-time

40 languages

HTTPWebSocket

Variants

Deepgram Nova 3 EnglishDeepgram Nova 3 SpanishDeepgram Nova 3 Hindi

Regions

apeume

Use Cases

Real-time transcriptionVoice agentsLive streaming

Orpheus

SLNGTTS

High-quality streaming TTS with emotion control, hosted on SLNG infrastructure

API Docs

low

HTTPWebSocket

Variants

Orpheus English

Regions

Use Cases

Voice agentsInteractive applicationsConversational AI

Rime Arcana

SLNGTTS

Rime Arcana TTS - High-quality multilingual text-to-speech with on-premises deployment support

API Docs

medium

5 languages

HTTPWebSocket

Variants

Rime Arcana 3 EnglishRime Arcana 3 FrenchRime Arcana 3 Hindi

Regions

apeume

Use Cases

Voice agentsInteractive applicationsContent localization

Aura

DeepgramTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2

Regions

afcaeume

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Nova

DeepgramSTT

Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.

API Docs

real-time

40 languages

HTTPWebSocket

Variants

Nova 2Nova 3Nova 3 Medical

Regions

afcaeume

Use Cases

Real-time transcriptionVoice agentsLive streaming

Spanish

Models with Spanish language support:

Aura

SLNGTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2 (English)Aura 2 (Spanish)

Regions

apeu

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Melo

SLNGTTS

Melo - High-quality TTS model deployed on SLNG infrastructure

API Docs

medium

6 languages

HTTP

Variants

Melo v1

Regions

Use Cases

Voice agentsContent creationInteractive applications

Nova

SLNGSTT

Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.

API Docs

real-time

40 languages

HTTPWebSocket

Variants

Deepgram Nova 3 EnglishDeepgram Nova 3 SpanishDeepgram Nova 3 Hindi

Regions

apeume

Use Cases

Real-time transcriptionVoice agentsLive streaming

Rime Arcana

SLNGTTS

Rime Arcana TTS - High-quality multilingual text-to-speech with on-premises deployment support

API Docs

medium

5 languages

HTTPWebSocket

Variants

Rime Arcana 3 EnglishRime Arcana 3 FrenchRime Arcana 3 Hindi

Regions

apeume

Use Cases

Voice agentsInteractive applicationsContent localization

Aura

DeepgramTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2

Regions

afcaeume

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Nova

DeepgramSTT

Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.

API Docs

real-time

40 languages

HTTPWebSocket

Variants

Nova 2Nova 3Nova 3 Medical

Regions

afcaeume

Use Cases

Real-time transcriptionVoice agentsLive streaming

Multilingual

Models with broad language coverage:

Speechmatics

SLNGSTT

API Docs

realtime

Multi-language

WebSocket

Variants

Speechmatics ENSpeechmatics ES

Regions

Use Cases

Real-time transcriptionVoice commandsLive captioning

Whisper

SLNGSTT

Speech-to-Text using Whisper Large v3 model hosted by SLNG. Supports 99+ languages with automatic language detection. Best for general-purpose transcription with high accuracy.

API Docs

batch

Multi-language

HTTPWebSocket

Variants

Whisper Large v3

Regions

Use Cases

Batch transcriptionMeeting notesContent creation

Eleven Flash

ElevenLabsTTS

Ultra-low latency TTS with industry-leading speed

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven Flash v2Eleven Flash v2.5

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Eleven Multilingual

ElevenLabsTTS

Multilingual TTS with ultra-low latency

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven Multilingual v2

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Eleven v3

ElevenLabsTTS

Premium TTS with industry-leading latency and voice quality

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven v3

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

By Region

Geographic proximity reduces latency. Choose models deployed in regions closest to your users for the best real-time experience.

North America (US)

Models with US-based deployments for lowest latency from US/CA:

Aura

DeepgramTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2

Regions

afcaeume

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Nova

DeepgramSTT

Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.

API Docs

real-time

40 languages

HTTPWebSocket

Variants

Nova 2Nova 3Nova 3 Medical

Regions

afcaeume

Use Cases

Real-time transcriptionVoice agentsLive streaming

Europe (EU)

Models with EU-based deployments to reduce cross-Atlantic latency:

Aura

SLNGTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2 (English)Aura 2 (Spanish)

Regions

apeu

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Nova

SLNGSTT

Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.

API Docs

real-time

40 languages

HTTPWebSocket

Variants

Deepgram Nova 3 EnglishDeepgram Nova 3 SpanishDeepgram Nova 3 Hindi

Regions

apeume

Use Cases

Real-time transcriptionVoice agentsLive streaming

Orpheus

SLNGTTS

High-quality streaming TTS with emotion control, hosted on SLNG infrastructure

API Docs

low

HTTPWebSocket

Variants

Orpheus English

Regions

Use Cases

Voice agentsInteractive applicationsConversational AI

Rime Arcana

SLNGTTS

Rime Arcana TTS - High-quality multilingual text-to-speech with on-premises deployment support

API Docs

medium

5 languages

HTTPWebSocket

Variants

Rime Arcana 3 EnglishRime Arcana 3 FrenchRime Arcana 3 Hindi

Regions

apeume

Use Cases

Voice agentsInteractive applicationsContent localization

Whisper

SLNGSTT

Speech-to-Text using Whisper Large v3 model hosted by SLNG. Supports 99+ languages with automatic language detection. Best for general-purpose transcription with high accuracy.

API Docs

batch

Multi-language

HTTPWebSocket

Variants

Whisper Large v3

Regions

Use Cases

Batch transcriptionMeeting notesContent creation

Aura

DeepgramTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2

Regions

afcaeume

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Nova

DeepgramSTT

Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.

API Docs

real-time

40 languages

HTTPWebSocket

Variants

Nova 2Nova 3Nova 3 Medical

Regions

afcaeume

Use Cases

Real-time transcriptionVoice agentsLive streaming

Eleven Flash

ElevenLabsTTS

Ultra-low latency TTS with industry-leading speed

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven Flash v2Eleven Flash v2.5

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Eleven Multilingual

ElevenLabsTTS

Multilingual TTS with ultra-low latency

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven Multilingual v2

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Eleven v3

ElevenLabsTTS

Premium TTS with industry-leading latency and voice quality

API Docs

<100ms

Multi-language

HTTPWebSocket

Variants

Eleven v3

Regions

Use Cases

Real-time voice agentsLive streamingInstant messaging

Asia Pacific (AP)

Models with APAC deployments for lower latency in the region:

Aura

SLNGTTS

Real-time conversational TTS designed for voice agents with ultra-low latency

API Docs

<200ms

7 languages

HTTPWebSocket

Variants

Aura 2 (English)Aura 2 (Spanish)

Regions

apeu

Use Cases

Real-time voice agentsIVR systemsVoice assistants

Nova

SLNGSTT

Real-time speech-to-text transcription with ultra-low latency using Deepgram's Nova model. Optimized for streaming audio with intelligent Voice Activity Detection (VAD) and speaker diarization.

API Docs

real-time

40 languages

HTTPWebSocket

Variants

Deepgram Nova 3 EnglishDeepgram Nova 3 SpanishDeepgram Nova 3 Hindi

Regions

apeume

Use Cases

Real-time transcriptionVoice agentsLive streaming

Rime Arcana

SLNGTTS

Rime Arcana TTS - High-quality multilingual text-to-speech with on-premises deployment support

API Docs

medium

5 languages

HTTPWebSocket

Variants

Rime Arcana 3 EnglishRime Arcana 3 FrenchRime Arcana 3 Hindi

Regions

apeume

Use Cases

Voice agentsInteractive applicationsContent localization

Protocol Support

All models support:

HTTP - Simple request/response for batch processing
WebSocket - Real-time bidirectional streaming

See Protocol Comparison for detailed information.

Pricing Overview

Pricing varies by model and provider:

TTS Models: Typically charged per 1,000 characters
STT Models: Typically charged per minute of audio

For exact pricing, contact [email protected] or check your dashboard.

Adding New Models

We continuously adds new models and providers. Check back regularly for updates, or subscribe to our newsletter for announcements. And let us know if there is a specific model or provider you'd like to see supported!

Coming Soon:

Additional language variants
More voice options
Enhanced real-time features

Last modified on February 12, 2026

Getting Started HTTP vs. WebSocket