Google Gemini
Gemini 3.1 Flash TTS Preview
Create asynchronous text-to-speech tasks with gemini-3.1-flash-tts-preview via POST /v1/predictions.
POST
Prompt (input.prompt)
Required. Text to synthesize (max 32,000 characters). Supports expressive markup tags in the text:
Style instructions (input.style_instructions)
Optional (max 1,000 characters). Natural-language directions for tone, pace, accent, and emotion. Default: Say the following.
Voice presets (input.voice)
Optional. Default Kore.
Language (input.language)
Optional BCP-47 language code. Default en-US.
Output format (input.output_format)
Optional. Default mp3.
Authorizations
Authorization: Bearer YOUR_API_KEY
Body
application/json
Model ID. Use gemini-3.1-flash-tts-preview for this endpoint.
Available options:
gemini-3.1-flash-tts-preview Example:
"gemini-3.1-flash-tts-preview"
Optional HTTPS callback URL when the task completes, fails, or is cancelled.
Response
Async task created