Google launches Gemini 3.8 Flash TTS with 2,000+ voices across 100+ languages

Arindam_1729 · x · 2026-09-24

Google launches Gemini 3.8 Flash TTS and Flash-Lite TTS: expressive audio models with custom voices in 100+ languages or 2,000+ presets, line-by-line delivery direction, natural cues like <laughs> and listening interjections like |mhm|, and hours of consistent output.

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

Original post →

More from Multimodal

Multimodal channel →