Gemini 3.1 Flash TTS: the next generation of expressive AI speech

Google DeepMind's Gemini 3.1 Flash TTS is a text-to-speech model delivering improved controllability, expressivity, and quality for developers, enterprises, and everyday users building AI-speech applications. The model features native multi-speaker dialogue, support for 70+ languages, and granular creative control via natural language. All audio generated is watermarked with SynthID — an imperceptible watermark woven directly into the audio output to enable reliable detection of AI-generated content and help prevent misinformation.

Guide to prompting Gemini 3.1 Flash TTS (text-to-speech)
Google’s Gemini 3.1 Flash TTS model offers unparalleled control over AI voices
What a week! Here’s everything we shipped: — Gemini 3.1 Flash TTS, our latest text-to-speech model, featuring native multi-speaker dialogue …
Google rolls out Gemini 3.1 Flash TTS, a text-to-speech model with support for over 70 languages and audio tags that give developers granular speech control (Matthias Bastian/The Decoder)
[[today-we-launched-gemini-31-flash-tts-our-most-expressive-an|Today we launched Gemini 3.1 Flash TTS, our most expressive and controllable text-to-speech model yet. This launch [excitement] includes aud…]]
Gemini 3.1 Flash TTS is rolling out in Google Vids and is available today in preview via the Gemini API and in @GoogleAIStudio. Whether you’…

Source: Google DeepMind | 2026-04-15

Related