Audio
Gemini 3.8 Flash TTS
Prepare narration or a two-person conversation from a written script.
- Text to speech
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Gemini 3.8 Flash TTS. Review your own result before publishing.
A starting point.
Prepare narration or a two-person conversation from a written script. Keep delivery directions separate from the words you want spoken.
Before you publish.
Listen for pronunciation, speaker changes and unwanted spoken instructions. Check names and numbers against the script before attaching the audio to a video.
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
For narration, send prompt and choose voice. Put pacing and tone in style_instructions.
For dialogue, omit prompt. Configure exactly two speakers with distinct speaker_id values and voices, then supply ordered turns using those aliases and text.
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 google/gemini-3.8-flash-tts. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Optional | — |
speakers | List | Optional | Min. items: 2 · Max. items: 2 |
style_instructions | Text | Optional | — |
turns | List | Optional | Min. items: 1 |
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 3.8 Flash TTS through the API.
Start with this model ID for the endpoint featured on this page:
google/gemini-3.8-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.