Google Launches Gemini 3.8 Flash TTS and Flash-Lite TTS Audio Generation Models

Google has announced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two new text-to-speech models described as its most expressive audio generation models yet. The company says the models help creators, developers, and enterprises create richer, more expressive audio experiences. They are available to try via the Gemini API and in AI Studio.

Gemini 3.8 Flash TTS is part of Google's Gemini model family, with TTS standing for text-to-speech. The Flash-Lite version is released alongside the Flash version, offering another option within the same product line. Google has opened a speech generation entry point in AI Studio, allowing developers to test the model's voice synthesis capabilities online.