Google releases Gemini 3.5 Live Translate; Delivers near real-time speech-to-speech translation in over 70 languages

Recently, Google introduced its latest audio model, Gemini 3.5 Live Translate, for live speech-to-speech translation in near real time.

We’re upgrading Google Translate with Gemini 3.5 Live Translate – our latest audio model for near real-time speech-to-speech translation! This model unlocks smoother, even more natural-sounding translations, and helps preserve the speaker’s tone, pace, and pitch. pic.twitter.com/4NNa3CR9Pw

— Nick Fox (@thefox) June 11, 2026

The model is available to developers in public preview via the Gemini Live API and Google AI Studio, to enterprises in private preview starting this month in Google Meet, and to everyone via Google Translate on Android and iOS.

Gemini 3.5 Live Translate

This new audio model automatically detects 70+ languages and generates smooth, natural-sounding translated speech that preserves the speakers’ intonation, pacing and pitch. Gemini 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.

It delivers fluid audio without awkward pauses and stays just a few seconds behind the speaker throughout the session. The model handles multilingual inputs without the need to manually configure settings, while its noise robustness ensures applications can handle loud, unpredictable environments.

Users can access this model’s capabilities to help facilitate live interpretation for multilingual calls, meetings, lessons, broadcasts and more. By utilising the Gemini Live API, developer platforms like Agora, Fishjam, LiveKit, Pipecat, and Vision Agents enable developers to build and deploy voice translation apps with ease.

Google also revealed that Grab is already testing this latest model to enable multilingual communication in near real-time between drivers and travellers at pickups.

Gemini 3.5 Live Translate in Google Meet

Speech Translation in Google Meet will soon use 3.5 Live Translate, improving the experience by offering 70+ languages, enabling conversations across over 2000+ language combinations in one meeting and updating the interface to provide instant access to speech translation.

Starting this month, this update will be launched in private preview for select business Google Workspace customers, followed by a broader rollout later this year.

Gemini 3.5 Live Translate in the Google Translate app

The model is rolling out on the Google Translate app globally, on both Android and iOS. For Android users, the company has also started rolling out a new listening mode with 3.5 Live Translate that lets you hear translations directly through your phone’s earpiece.

Do note that all audio generated by Google’s models is watermarked with SynthID.