Supertone icon

Supertone

Interact with Supertone API for AI voice synthesis

Actions8

Speech → Text to Speech

AI-generated

Summary

Convert text to speech audio using a selected voice and optional voice settings via the Supertone API.

Inputs

  • voice (required) — Select the voice to use for speech generation
  • text (required) — The text to convert to speech (max 300 characters)
  • language — The language of the text
  • style — The speaking style. If not specified, the default style for the voice will be used.
  • additionalOptions — Optional voice and output settings.
  • requestOptions — HTTP request options.

Output shape

binary or JSON

Returns binary audio data (WAV/MP3) representing the generated speech. If includePhonemes is enabled, returns a JSON object with base64-encoded audio and phoneme timing data. Duration (seconds) and format (wav/mp3) are included when available, with duration derived from the x-audio-length response header.

Examples

Example 1: Basic text-to-speech generation

Provide a required voice (by list or ID) and the text to synthesize. Optional language, style, and voice settings can be omitted or adjusted.

Links

Discussion