Google Gemini 3.5 Live Translate Offers Real-Time Voice Translation

Launch of Gemini 3.5 Live Translate

Google has introduced Gemini 3.5 Live Translate, the latest update in its voice translation capabilities. This model can translate spoken language in real-time across more than 70 languages, offering users a seamless experience. The release marks a significant advancement in Google's long-standing efforts in machine learning for language translation.

Key Features of Gemini 3.5 Live Translate

Unlike traditional translation systems that operate turn by turn, Gemini 3.5 generates translations continuously, minimizing pauses and maintaining the original speaker's intonation and pacing. This feature is crucial for ensuring conversations flow naturally, particularly in scenarios like meetings and calls.

Deployment and Availability

Gemini 3.5 Live Translate is now available for developers through the Gemini Live API and in Google AI Studio. Enterprise users can access it via Google Meet in private preview starting this month, while all users can utilize it in Google Translate on Android and iOS.

Implications for Multilingual Communication

The continuous translation capability presents new opportunities for live interpretation across various platforms such as broadcasts, lessons, and meetings. Companies like Grab are already testing this technology to facilitate communication between drivers and travelers in real time.

Developer Integrations and Use Cases

Using the Gemini Live API, platforms like Agora and Fishjam enable developers to build apps for voice translation efficiently. This allows developers to focus on improving user experiences without managing the underlying real-time streaming technology.