Plain-English Summary
Google’s Gemini-based speech model for creating natural spoken audio from text.
Gemini 3.1 Flash TTS Preview
Google’s Gemini-based speech model for creating natural spoken audio from text.
Gemini TTS
Audio / Speech
Preview
Open weights: No
API: Yes
Technical Notes
Text-to-speech model designed for controllable voice generation and expressive spoken output.
Best For
Narration, voice interfaces, accessibility, generated dialogue
Watch Out For
Preview; voice inventory, quotas, and supported controls may change.
Model Specs
- Maker
- Country
- Not listed
- Family
- Gemini TTS
- Type
- Audio / Speech
- Release date
- Not listed
- Date confidence
- Not publicly stated
- Status
- Preview
- Context window
- Varies
- Max output
- Not listed
- Parameters
- Not disclosed
- Active parameters
- Not disclosed
- Architecture
- Proprietary speech generation model
- Reasoning
- Not applicable
- Tool calling
- No
- Structured output
- No
- API available
- Yes
- Open weights
- No
- Self-hostable
- No
- License
- Proprietary
- Inputs
- Text
- Outputs
- Audio
- Approx. price
- See provider pricing
- How to access
- Provider website or API
- Model / API ID
- gemini-3.1-flash-tts-preview
- Knowledge cutoff
- Not publicly disclosed
- Fine-tuning
- Prompting / RAG
- Completeness
- 76 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source