Google introduced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two expressive text-to-speech models for generating custom character voices.

The models allow for detailed control over voice characteristics, including accent and emotional tone, across platforms like Google AI Studio and Gemini API. Users can create a vast library of unique voices, expanding beyond the original 30 voices. These models enhance audio experiences in applications such as Gemini Notebook and Google Vids, joining existing Gemini Audio offerings like 3.5 Live Translate and 3.8 Live.

Source: blog.google