Google releases Gemini 3.5 Live Translate, a speech-to-speech model for instant voice translation across more than 70 languages

Google rolled out Gemini 3.5 Live Translate across several parts of the Google ecosystem, including Google Meet. Developers can begin building with a public preview in the Gemini Live API or AI Studio.

The model is a speech-to-speech translator tuned to automatically detect and translate in more than 70 languages. It processes speech continuously, filters background noise, and matches intonation, pacing, and pitch of the original speaker.

Google says Gemini 3.5 Live Translate is fast enough to keep up with a normal conversation, following just a few seconds behind the speaker, delivering lower latency than the real-time translation Google brought to the Translate app last year.