Overview
The flagship creative text-to-speech model in Gemini 3.8, emphasizing studio-grade fidelity, expressive acting, regional accents, and long-form multi-turn stability.
Gemini 3.8 Flash TTS
The flagship creative text-to-speech model in Gemini 3.8, emphasizing studio-grade fidelity, expressive acting, regional accents, and long-form multi-turn stability.
Google announced Gemini 3.8 Flash TTS GA in the Gemini API on 2026-09-22; model ID `gemini-3.8-flash-tts`, targeting high-fidelity creative TTS with Voices, Voice Design, and Voice Replication.
MODEL NUMBER086
- First public date
- 2026-09-22
- Organization
- Google DeepMind
- Family
- Gemini
01
Specifications
Only published specifications are shown.
02
Overview
Why it mattered
It extends Gemini 3.8 audio from live conversation into controllable, high-quality speech generation.
03
Architecture & capabilities
Model capabilities
Audio generationVoice cloningMultilingual
04
Release history
Gemini 3.8 Flash TTS reached GA in the Gemini API for high-fidelity creative text-to-speech, alongside Voices, Voice Design, and Voice Replication.
View source05
Related models
Select a card to view the related model.
06
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.