Soniox WebSocket TTS provider

This page applies when provider=soniox — either via the voice compound parameter or by setting provider=soniox explicitly. See Configuration.

Voice Format

Soniox.tts-rt-v2.<VoiceId>

Example: Soniox.tts-rt-v2.Emma

Models

Model	Description
`tts-rt-v2`	Real-time model. Default and the only model accepted.

Voices

Around 200 voices under tts-rt-v2; every voice speaks all supported languages. Browse the full catalog via the Voices API; samples are on the Soniox provider page.

Language

Set voice_settings.language on the init frame, or the language query parameter, to the two-letter ISO 639-1 code of the text, for example en, it, or pt. The default is en. The Soniox provider page lists the supported languages.

Voice Settings

Field	Type	Default	Description
`language`	string	`en`	Two-letter ISO 639-1 code of the text.
`speed`	float	`1.0`	Speaking rate, `0.7` to `1.3`.
`reduce_silence`	boolean	`false`	Shortens the pauses between words.

{
  "text": " ",
  "voice_settings": {
    "language": "it",
    "speed": 1.1,
    "reduce_silence": true
  }
}

SSML is not supported. Send plain text.

Audio Output

Streamed delivery. Default: MP3 at 24 kHz. Use the audio_format and sample_rate query parameters to change the output:

`audio_format`	Accepted Sample Rates (Hz)	Default
`mp3`	16000, 24000, 44100, 48000	24000
`wav`	8000, 16000, 24000, 44100, 48000	24000
`linear16`	8000, 16000, 24000, 44100, 48000	24000
`mulaw`	8000	8000
`alaw`	8000	8000

wss://api.telnyx.com/v2/text-to-speech/speech?voice=Soniox.tts-rt-v2.Emma&audio_format=mulaw

Limits

A request produces up to two minutes of audio. Split longer text into several requests.

WebSocket Streaming

REST API

Providers

Other

API Reference

For AI Agents

Soniox WebSocket TTS provider

Voice Format

Models

Voices

Language

Voice Settings

Audio Output

Limits

​Voice Format

​Models

​Voices

​Language

​Voice Settings

​Audio Output

​Limits

Voice Format

Models

Voices

Language

Voice Settings

Audio Output

Limits