Audio
Gemini 3.1 Flash Tts
Convert written text to expressive speech with Gemini 3.1 Flash TTS.
- Text to speech
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Gemini 3.1 Flash Tts. Review your own result before publishing.
A starting point.
Draft narration or spoken messages with separate instructions for tone and pace.
Before you publish.
Listen for pronunciation, unintended spoken instructions, pauses and clipped endings.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Put the spoken text in prompt and delivery direction in style_instructions. Choose voice and language_code for the intended reading.
Select WAV, MP3 or Ogg Opus output. Compare temperature cautiously; this Raywake operation has no speakers configuration for assigning multiple voices.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for gemini-3.1-flash-tts. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | Min. characters: 1 · Max. characters: 50000 |
language_code | Text | Optional | — |
output_format | Text | Optional | wav, mp3, ogg_opus |
style_instructions | Text | Optional | Max. characters: 4000 |
temperature | Number | Optional | ≥ 0 · ≤ 2 |
voice | Text | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Gemini 3.1 Flash Tts through the API.
Start with this model ID for the endpoint featured on this page:
gemini-3.1-flash-tts
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.