Google DeepMind
Google DeepMind releases Gemini 3.8 Flash TTS and Flash-Lite TTS
Announced 23 September 2026
Google DeepMind introduced two text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, which generate speech from natural language prompts and let a script direct pacing, emotion and conversational sounds line by line. Flash TTS is aimed at character design and creative direction, while Flash-Lite TTS is aimed at high-volume work such as dubbing and voice agents. Both are offered through Google AI Studio, the Gemini API, Gemini Enterprise, Gemini Notebook and Google Vids, and the page says voice remixing is coming soon.
What this means
Google DeepMind reports Flash TTS builds voices from scratch across more than 100 languages and dialects, replicates a voice from a 30-second sample with consent verification, and that a library of 2,000+ voices is available, with SynthID watermarking on generated audio. It adds another hosted speech option rather than anything you can run yourself.
On this site
Source
“Gemini 3.8 text-to-speech says hello”
Announced by Google DeepMind on 23 September 2026 · we wrote this on 28 September 2026.
read the original at blog.google ↗