Today we launched Gemini 3.1 Flash TTS, our most expressive and controllable text-to-speech model yet.

This launch [excitement] includes audio tags! 🗣🏷 Audio tags [explanatory] are a seamless way to guide vocal style, pace, and delivery using natural language commands embedded… pic.twitter.com/hNeHreY7N3

— Google AI (@GoogleAI) 15 avril 2026

Today we launched Gemini 3.1 Flash TTS, our most expressive and controllable text-to-speech model yet. This launch [excitement] includes audio tags! Audio tags [explanatory] are a seamless way to guide vocal style, pace, and delivery using natural language commands embedded

→ View original post on X — @googleai