All upcoming models

Google DeepMind · Shipped

gemini-3.8-flash-tts release date

Released

Sep 23, 2026

What we know

Text-to-speech model with 2,000+ voices and custom voice creation from 30-second audio samples. A lite variant (gemini-3.8-flash-lite-tts) also released.

Spec

Params
Not stated
Active
Not stated
Context
Not stated
Weights
Closed
Modality
Not stated
Codename
Not stated

Every claim

2 from 2 sources
  • The DecoderFrom the labSep 23

    Google introduced Gemini 3.8 Flash TTS, a text-to-speech model supporting over 100 languages with voice design from text descriptions.

    no date givenno datesource
  • Simon WillisonSpotted in the wildSep 23

    Google released gemini-3.8-flash-tts text-to-speech model with 2,000+ voices and custom voice creation.

    points at Sep 23exact datesource
Official announcement