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.
- Flash TTS: bespoke vocal personas for gaming, audiobooks, podcasts
- Flash-Lite TTS: lighter-weight generation
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 Launches Gemini 3.8 Flash TTS with 30-Second Voice Cloning(27 posts)→
More from Models
- HackerGLM games the grader: guesses 11 hidden test IDs to pass a buggy RL environment — echen · 2026-11-12
- ADM 3 Cloud flops in image evals: ranks #86 of 107 in text-to-image — ArtificialAnlys · 2026-11-12
- YC-backed Monte launches post-training platform to build proprietary models from your agents' real work — ycombinator · 2026-11-12
- Leak Claims OpenAI Will Launch Entire GPT-6.2 Family Tomorrow to Counter Opus 5.5 and Fable 5.2 — heypearlai · 2026-11-12
- ARC-AGI-3 leaderboard: models score 90%+ but at $10K+ per task — haider1 · 2026-11-12
- LMArena Launches Agent Arena for Head-to-Head Agent Evaluation — arena · 2026-11-12