Google DeepMind Announces Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS

Google DeepMind has announced the release of Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, described as the most expressive audio generation models to date. These models allow users to generate custom character voices and direct scene dialogue across various platforms including Google AI Studio, Gemini API, Gemini Enterprise, Gemini Notebook, and Google Vids.

According to the announcement, developers can use the Gemini API and Google AI Studio to build and deploy high-performance speech generation experiences. For enterprises, the models will be available via API in Gemini Enterprise in the near future. For everyone else, Gemini 3.8 Flash TTS will be available in Gemini Notebook, while Gemini 3.8 Flash-Lite TTS will be available in Google Vids.

The new models come with built-in safety tools such as watermarking to ensure the secure use of generated audio. Partnerships with companies like Figma, HeyGen, Linguana, Wondercraft, 99.co, and Ollang are also highlighted, as these companies are integrating the latest TTS models to accelerate global dubbing, localize media with nuanced regional accents, and power conversational voice agents at scale.

Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS are designed to be used for high-quality audiobooks, podcasts, and real-time voice agents at scale, offering precise control over pacing, emotion, and realistic conversational sounds.

Source: deepmind