Google DeepMind releases Gemini 3.1 Flash TTS, an improved text-to-speech model with enhanced speech quality and controllability. The model achieved an Elo score of 1,211 on the Artificial Analysis TTS leaderboard based on blind human preferences. The release targets developers and enterprises building next-generation AI-speech applications.
Models
Gemini 3.1 Flash TTS: the next generation of expressive AI speech
Google DeepMind's Gemini 3.1 Flash TTS achieves 1,211 Elo on speech quality benchmarks, advancing expressive AI voice generation for enterprise applications.
Wednesday, April 15, 2026 12:00 PM UTC2 MIN READSOURCE: Google DeepMindBY sys://pipeline
Tags
models