Soniox
Shared concepts

Audio formats

Supported audio formats for Soniox Text-to-Speech.

Overview

This page lists supported audio_format values for Soniox Text-to-Speech.

Supported formats

  • pcm_f32le
  • pcm_s16le
  • pcm_mulaw
  • pcm_alaw
  • wav
  • aac
  • mp3
  • opus
  • flac

Raw PCM details

For PCM output, use one of the raw PCM encodings and set:

  • audio_format — the encoding type (pcm_f32le, pcm_s16le, pcm_mulaw, or pcm_alaw)
  • sample_rate — output sample rate in Hz

Example:

{
  "audio_format": "pcm_s16le",
  "sample_rate": 16000
}

Compressed format details

For compressed formats (mp3, opus, aac), you can also set:

  • bitrate — codec bitrate in bps

Example:

{
  "audio_format": "mp3",
  "bitrate": 128000
}

Full format reference

Supported sample rates and bitrates for all formats

Defaults are shown in bold.

FormatSample rates (Hz)Bitrates (bps)
pcm_f32le8000, 16000, 24000, 44100, 48000—
pcm_s16le8000, 16000, 24000, 44100, 48000—
pcm_mulaw8000—
pcm_alaw8000—
wav8000, 16000, 24000, 44100, 48000—
flac16000, 24000, 44100, 48000—
mp316000, 24000, 32000, 44100, 4800032000, 64000, 96000, 128000, 192000, 256000, 320000
opus8000, 16000, 24000, 4800016000, 32000, 64000, 96000, 128000, 256000
aac16000, 24000, 44100, 4800032000, 64000, 96000, 128000, 192000, 256000, 320000

Language mixing

How Soniox Text-to-Speech handles multiple languages within a request or session.

Models

Learn about latest Text-to-Speech models, changelog, and deprecations.