news
Gemini 3.1 Flash TTS: the next generation of expressive AI speech
April 15, 2026
Gemini 3.1 Flash TTS introduces granular audio tags for precise control over expressive AI speech generation. The notable detail is that the model is focused on fine-grained direction of speech style and delivery, which could make AI voice outputs more controllable and natural-sounding.
Our newest audio model introduces granular audio tags that give you precise control to direct AI speech for expressive audio generation.
Source: deepmind.google