Model Release

Google's Gemini 3.5 Live Translate Offers Real-Time Voice Translation Across 70+ Languages

Google released Gemini 3.5 Live Translate, a real-time audio translation model supporting 70+ languages and over 2,000 language combinations.

High-detail close-up image of a white robot with glowing eyes in studio lighting. Modern tech innovation.

Photo: Pavel Danilyuk / Pexels

Google has launched Gemini 3.5 Live Translate, a real-time audio translation model that supports over 70 languages. The model automatically detects languages and preserves the speaker's tone, pace, and pitch during translation. It also allows for continuous translation without waiting for a sentence to end. According to Google, this model is now available for developers through the Gemini Live API and Google AI Studio, as a preview for businesses in Google Meet, and for all users in the Google Translate app on Android and iOS. In Google Meet, the language support has expanded from five to more than 70 languages with over 2,000 language combinations.

Ride-hailing service Grab is reportedly testing the model for driver-passenger communication. All generated audio is tagged with an inaudible SynthID watermark. Source: thedecoder

Key points

Google released Gemini 3.5 Live Translate, a real-time audio translation model for 70+ languages.
The model detects languages automatically and preserves the speaker's tone, pace, and pitch.
Gemini 3.5 Live Translate is available now for developers through the Gemini Live API and Google AI Studio.
In Google Meet, language support jumps from five to over 70 languages with more than 2,000 language combinations.
All generated audio is tagged with an inaudible SynthID watermark.

Source: The Decoder Read the original →

WRITTEN BY

Alex Lindgren

LLMs & Frontier Models

Alex covers the large language models and their impact on society.