New Gemini 3.5 Live Translate Model Provides Near Real-time Translation in Over 70 Languages

Google has released today a new Gemini 3.5 Live Translate audio model that supports near real-time speech-to-speech translation in over 70 languages. It’s available across the Google Translate app for iOS and Android, but it’s also coming to Google Meet.

“The model automatically detects 70+ languages and generates smooth, natural-sounding translated speech that preserves the speakers’ intonation, pacing and pitch. Unlike turn by turn systems that wait for the speaker to finish speaking before responding, 3.5 Live Translate generates speech continuously, balancing the trade-off between waiting for context to improve quality and translating immediately to stay in sync with the speaker,” Google said today.

In the Google Translate mobile app, the Live Translate feature, which can be used with or without headphones, can provide even faster and more accurate real-time translations in your language. On Android, the new Listening mode can also stream the translation through the phone’s earpiece instead of using the built-in speakers.

Live Translation with Google’s Gemini 3.5 Live model is now available in private preview in Google Meet for select Google Workspace customers. It will expand the list of supported languages from 5 to over 70, and the app will automatically identify the speaker’s language that needs to be translated in near real-time.

Google’s Gemini 3.5 Live Translate is also available for app developers in public preview via the Gemini Live API and Google AI Studio. The latest translation model can be used to enable live dubbing of video content, real-time multilingual translation, and more.