Voice AI icon

Voice AI

Interact with Voice.ai text-to-speech and voice management API

Actions6

Speech → Text to Speech

AI-generated

Summary

Convert the given text into speech using the selected voice and optional TTS settings.

Inputs

  • voice (required) — The voice to use for conversion; can be selected from a list or provided as an ID.
  • text (required) — The text content to be spoken.
  • additionalOptions — Optional settings including audio format, language, model, temperature, topP, and other request options.

Output shape

binary audio file (e.g., MP3 or WAV)

The operation returns the generated audio as a binary payload; response headers are preserved. No additional JSON body is emitted on success.

Examples

Example 1: Generate an MP3 spoken greeting

voice: list value "en-US-Aria", text: "Hello, welcome to Voice AI!", additionalOptions.audioFormat: "mp3"

Example 2: Batch convert multiple phrases

voice: list value "en-US-Goodman", text: "First sentence", additionalOptions.batching.batchSize: 10, additionalOptions.batching.batchInterval: 500

Example 3: Produce a WAV file with custom model and temperature

voice: list value "en-US-Aria", text: "Custom settings", additionalOptions.audioFormat: "wav", additionalOptions.temperature: 1.2, additionalOptions.model: "voiceai-tts-v1-latest"

Links

Discussion