Google launches Gemini 3.8 Flash TTS with custom voices in 100+ languages

kastnerkyle · x · 2026-09-24

Google AI launched Gemini 3.8 Flash TTS and Flash-Lite TTS, its most expressive audio models yet: custom voices across 100+ languages, 2,000+ presets, line-by-line delivery control, natural cues like <laughs> and |mhm|, and hours of consistent audio.

Hume AI CEO Alan Cowen called it the most natural speech model he's used, arguing TTS is no longer a "small model" problem — frontier models sound more expressive because they better understand what they're saying.

Related event: Google DeepMind Launches Gemini 3.8 TTS Models with 30-Second Voice Cloning(16 posts)→

Original post →

More from Models

Models channel →