Text To Speech

Generate speech audio from text using a Gemini TTS model.

Request body: {model, input, voice, speakers?, instructions?} instructions (delivery style, OpenAI /audio/speech name) is accepted by gemini-3.8-* models only. Response: raw PCM bytes (audio/pcm) with X-Input-Tokens / X-Output-Tokens headers.

post/audio/speech/

Request

  • Base URL: https://factchat-cloud.mindlogic.ai/v1/gateway
  • URL: https://factchat-cloud.mindlogic.ai/v1/gateway/audio/speech/
  • Auth: none declared

Response

Successful Response

unknown required

Changes

No recorded changes to this operation across all 1 revision of this API.