Gemini 3.5 Live Translate brings near real-time voice translation

Gemini 3.5 Live Translate is an audio model that delivers near real-time speech-to-speech translation in more than 70 languages. It automatically detects languages and generates natural-sounding speech that preserves speakers' intonation, pacing and pitch, translating continuously rather than waiting for each turn and staying just a few seconds behind the speaker.

It is rolling out across products: developers can access it in public preview via the Gemini Live API and Google AI Studio, enterprises enter a private preview in Google Meet starting this month, and everyone will see it in Google Translate on Android and iOS. The model processes streamed speech, handles multilingual inputs without manual configuration and offers noise robustness for loud, unpredictable environments, useful for calls, meetings, lessons and broadcasts.

gemini 3.5, live translate, speech translation, real time, google translate, google meet, gemini api, ai studio, multilingual inputs, noise robustness