Google’s new Gemini TTS models can clone a voice from 30 seconds of audio
Covered by 8 sources
Read the full articleGoogle launched Gemini 3.8 Flash TTS and Flash-Lite TTS models that generate customizable voices from text and can clone voices from 30-second audio samples with consent. These models support multi-language, long-form audio, and include features like voice remixing and delivery direction.



