Google DeepMind · 2026-06-09 · major
Google DeepMind Ships Gemini 3.5 Live Translate — Audio Model Streams Near Real-Time Speech-to-Speech in 70+ Languages With Preserved Intonation, SynthID Watermarks, and Public Preview on Gemini Live API, AI Studio, Meet, and Google Translate
Continuous translation model that streams a few seconds behind the speaker, auto-detects 70+ languages, and preserves pacing and pitch. Ships across Gemini Live API, AI Studio, Google Meet, and Google Translate today.
First production speech-to-speech model that translates continuously instead of taking turns.
Key specs
| Languages | 70+ |
|---|---|
| Language combos in meet | 2000+ |
What is it?
An audio-native Gemini 3.5 variant focused on live speech translation. Where prior translation tools wait for a sentence to end, Gemini 3.5 Live Translate keeps speaking a few seconds behind the source, auto-detecting the source language from a pool of 70+ and preserving the original speaker's intonation, pacing, and pitch in the output voice.
How does it work?
Native end-to-end audio model — no separate ASR, MT, and TTS stack. Detects the source language continuously, generates target-language audio while the speaker is still talking, and watermarks the output with SynthID so the synthetic audio can be detected downstream. A new Android 'listening mode' lets the phone act as a real-time interpreter without prompting.
Why does it matter?
Removes the turn-by-turn delay that makes existing translation apps awkward for live meetings, interviews, and travel. Google is wiring it into Meet (2,000+ language combos, up from English-only), Google Translate on Android and iOS, and the Gemini Live API so third parties can build it into agents and call apps.
Who is it for?
Developers building voice agents, Google Meet users, Google Translate users, accessibility teams
Try it
Public preview via Gemini Live API and Google AI Studio; rolling out in Google Meet and Google Translate