Soniox
Text-to-SpeechShared concepts

Speech speed

Control the speaking rate of Soniox Text-to-Speech output with the speed parameter.

Overview

The speed parameter controls how fast the generated speech is spoken.

  • 1.0 is the normal speaking rate, and the default when speed is omitted.
  • Values below 1.0 slow speech down.
  • Values above 1.0 speed speech up.

The supported range is 0.7 to 1.3. A value outside this range is rejected with an invalid_request error.

Set the speed field in your Text-to-Speech request.

speed rescales the whole output, so it can flatten the natural rhythm of a voice. Start by picking a voice whose default pacing and energy already fit your use case, then shape individual moments with audio tags and punctuation such as [slowly], [rushed], or .... Use speed only when the delivery is still globally too fast or too slow, and keep the adjustment small.

Usage

speed is supported by both the real-time WebSocket API and the REST API.

In the WebSocket configuration message:

{
  "api_key": "<SONIOX_API_KEY|SONIOX_TEMPORARY_API_KEY>",
  "model": "tts-rt-v2",
  "language": "en",
  "voice": "Adrian",
  "audio_format": "wav",
  "speed": 1.2,
  "stream_id": "stream-001"
}

In the REST request body:

{
  "model": "tts-rt-v2",
  "language": "en",
  "voice": "Adrian",
  "audio_format": "wav",
  "text": "Hello from Soniox Text-to-Speech.",
  "speed": 1.2
}

Audio formats

Supported audio formats for Soniox Text-to-Speech.

Reduce silence

Shorten the pauses between words in Soniox Text-to-Speech output with the reduce_silence parameter.

On this page

Overview
Usage