Skip to content
Docs menu

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.

modelIdgemini-3-1-flash-tts
Modalitymusic
PricingSee this model on the Pricing page for the current per-call price (with your markup).

Operations

OperationmodelIdEndpointRequired input
Defaultgemini-3-1-flash-ttsPOST /api/v1/generatespeakers, dialogue_turns
Poll taskGET /api/v1/task/{id}?model=gemini-3-1-flash-tts

Input parameters

FieldTypeRequiredValues / example
speakersobject[]YesArray of { speaker_id, voice_name, audio_profile, style, pace, accent }
dialogue_turnsobject[]YesArray of { speaker_id, text }
temperaturenumberNoRange 0-2 (default: 1)
scenestringNoText value
sample_contextstringNoText 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"}}'