Universal Speech Generation

Generate speech audio from text using multiple AI providers

Universal Speech Generation

AI-generated

Summary

Convert the required text to speech using Google Generative AI or OpenAI and the selected voice. OpenAI also exposes optional audio format, speed, and language settings.

Inputs

  • Provider (required) — Choose Google Generative AI (the default) or OpenAI.
  • Text (required) — Text to convert to speech.
  • Voice (required) — Voice for the generated speech; available voices depend on the selected provider.
  • Output Format — For OpenAI, choose MP3 (default), WAV, FLAC, AAC, or OGG.
  • Speed — For OpenAI, set a speech speed multiplier from 0.25 to 4; defaults to 1.
  • Language — For OpenAI, provide a language code such as en, es, or fr, or use auto for detection.

Output shape

Generated speech audio returned by the node.

The source pack exposes the operation handler but omits its implementation body, so it does not establish the exact output item fields or whether the audio is returned as binary data or another representation.

Links

Discussion