Google DeepMind unveils new Gemini text-to-speech models

Google DeepMind has introduced two new text-to-speech models, Gemini 3.8 Flash-Lite TTS and Gemini 3.8 Flash TTS, as part of its Gemini model family. The company describes them as its most expressive audio models so far, suggesting improvements in tone, naturalness and vocal range compared to earlier versions.

The announcement did not include extensive technical details, but positions the new models as an upgrade for developers and businesses building voice applications, such as virtual assistants, audiobooks, customer service bots and accessibility tools.