Gemini 3.8 Flash TTS (GA)
Gemini 3.8 Flash TTS is Google’s text-to-speech model, generally available in the Gemini API since September 22, 2026.
- Lab
- Google DeepMind
- Release date
- Status
- Generally available
- API model ID
- gemini-3.8-flash-tts
The Gemini API changelog for September 22, 2026 lists Gemini 3.8 Flash TTS (gemini-3.8-flash-tts) as generally available, released alongside Gemini 3.8 Flash-Lite TTS and the Gemini API Voices endpoint. Google describes it as its flagship creative TTS model for voice fidelity, acting, regional dialects and long-form multi-turn stability.
- Modalities
- Text input; audio output (text to speech)
- Availability
- Gemini API.
- Official source
- ai.google.dev
- Last checked
Questions
When did Gemini 3.8 Flash TTS become generally available?
The Gemini API changelog lists it as GA on September 22, 2026.
What is the API ID?
gemini-3.8-flash-tts.What else launched with it?
Gemini 3.8 Flash-Lite TTS and the Gemini API Voices endpoint, with voice design, voice replication and an extended voice library.
Source
Release dates, model IDs and limits come from each lab’s own announcement, changelog, documentation or deprecations page, linked on every model with the date it was last checked. How we pick and check sources: editorial standards.