Google launches Gemini 3.8 Flash TTS, tops Hume's Voice Design Benchmark

_philschmid · x · 2026-09-23

Google released Gemini 3.8 Flash TTS and Flash-Lite TTS: clone a voice from 30s of audio or create one from a text description, with 2,000+ ready voices across 100+ languages, line-by-line direction of style and natural cues like <laughs>, and hours of consistent generation. The models rank #1 on Hume's Voice Design Benchmark and top Voice Arena in 6 languages. Blog, prompt guide, and migration guide from 3.1 are available.

Related event: Google Launches Gemini 3.8 Flash and Flash-Lite TTS with 30-Second Voice Cloning Across 100+ Languages(14 posts)→

Original post →

More from Multimodal

Multimodal channel →