Google announced Gemini 3.5 Live Translate, a speech-to-speech AI model providing instant voice-to-voice translation across more than 70 languages. The release expands real-time translation availability beyond previous requirements for specific Google phones or earbuds, offering lower latency than prior implementations. Google has pursued real-time translation for years as one of its pioneering machine learning experiments, previously rolling out limited real-time translation in the Translate app last year before today's broader deployment.
Gemini 3.5 Live Translate Technical Specifications and Model Family
Gemini 3.5 Live Translate is part of the version 3.5 family that launched at I/O. Before today, Google had only rolled out the Flash version, with a Pro model expected to drop in the coming weeks. The speech-to-speech model is tuned to automatically detect and translate in more than 70 languages.
According to Google, Gemini 3.5 Live Translate is fast enough to keep up with a normal conversation, following just a few seconds behind the speaker while also matching intonation, pacing, and pitch. The model produces voice output that sounds more like the original speaker than a generic robot. Google released demos recorded under controlled conditions demonstrating these capabilities.
Rollout Across Google Ecosystem and User Access
Gemini 3.5 Live Translate is rolling out across several parts of the Google ecosystem. The model is available in Google Meet for speech translation during video calls. Users can access the translation capabilities without waiting for extended verification periods.
Developer API Access and Automatic Processing Features
Developers can begin building with a public preview in the Gemini Live API or AI Studio. The model processes speech continuously and handles all multilingual inputs automatically, saving developers from manually configuring settings. It also filters out background noise in busy environments.
FAQ
What languages does Gemini 3.5 Live Translate support?
Gemini 3.5 Live Translate supports more than 70 languages with automatic detection and translation capabilities.
Where can users access Gemini 3.5 Live Translate?
The model is rolling out across several parts of the Google ecosystem, including Google Meet for speech translation, and developers can access it through the Gemini Live API or AI Studio public preview.
How does Gemini 3.5 Live Translate handle speech processing?
The model processes speech continuously, automatically handles multilingual inputs without manual configuration, and filters out background noise in busy environments while matching the speaker's intonation, pacing, and pitch.
