Google launches Gemini 3.8 Flash TTS models with voice cloning
Google just dropped two new text-to-speech models (Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS) that can turn written text into impressively real-sounding voices.
They can even copy a voice from a 30-second audio sample when the user has permission to use it, and a consent recording from the voice owner is required, support more than 100 languages and dialects, and handle conversations with multiple speakers.
You can try them now through the Gemini API or Google AI Studio, with more access options coming soon.
Gemini Flash TTS offers deep customization
With Gemini 3.8 Flash TTS, you get detailed control: change accents, roles, or vocal styles to fit your vibe.
Voice cloning is available from a 30-second audio sample when the user has permission to use it, and Google requires a consent recording from the voice owner before replication.
There are more than 2,000 ready-made voices to pick from. Google's also working on a remix feature so you can tweak voice attributes even further.
If you need something for higher-volume tasks such as dubbing, audio generation, and voice agents, Flash-Lite TTS has you covered too.