Audio models
Gemini 3.1 Flash TTS
On this page
Google's expressive text-to-speech — natural AI voice with control over tone and emotion.
| modelId | gemini-3-1-flash-tts |
| Modality | music |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | modelId | Endpoint | Required input |
|---|---|---|---|
| Default | gemini-3-1-flash-tts | POST /api/v1/generate | speakers, dialogue_turns |
| Poll task | — | GET /api/v1/task/{id}?model=gemini-3-1-flash-tts | — |
Input parameters
| Field | Type | Required | Values / example |
|---|---|---|---|
| speakers | object[] | Yes | Array of { speaker_id, voice_name, audio_profile, style, pace, accent } |
| dialogue_turns | object[] | Yes | Array of { speaker_id, text } |
| temperature | number | No | Range 0-2 (default: 1) |
| scene | string | No | Text value |
| sample_context | string | No | Text value |
Example request
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"gemini-3-1-flash-tts","input":{"speakers":[{"speaker_id":"Speaker 1","voice_name":"Zephyr","audio_profile":"example","style":"Deadpan","pace":"Natural","accent":"Neutral"}],"dialogue_turns":[{"speaker_id":"Speaker 1","text":"example"}],"temperature":1,"scene":"example","sample_context":"example"}}'