Skip to content
Models

Gemini 3.8 TTS Playground.

Simon Willison's WeblogAnalysis or commentary··Updated just now
Corroborated event · 3 outlets

Google released two text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, through its cloud platform, with Flash TTS able to generate new voices from text descriptions.

AI brief

Google released two Gemini text-to-speech models, gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, which include a library of over 2,000 voices and the ability to create a custom voice from a 30-second audio sample.

Why it matters: The models expand Google's text-to-speech options with a large voice library and custom voice creation from a short audio clip.

Written by AI from Simon Willison's Weblog's published text. Read the original for full details.

More coverage of this story (2)

Google releases Gemini 3.8 Flash text-to-speech models

Google's new Flash TTS models let you design AI voices from scratch using text descriptions
The Decoder · 23 Sept 2026, 17:39
Gemini 3.8 text-to-speech says hello
Google DeepMind · 23 Sept 2026, 15:25

Primary source

Interpretation or community commentary rather than straight reporting.

Read original story ↗