Thor Schaeff and Anuda Weerasinghe from Google DeepMind introduce Gemini 3.5 Live Translate, Google's new speech-to-speech translation model now available to developers via the Gemini API.
What's covered: Live dubbing of video content, real-time multilingual translation across 70+ languages, automatic language switching, and a listening experience that sounds completely natural
Get started in AI Studio, Google Translate on iOS and Android, or apply for Private Preview on Google Meet.
Have questions? Drop them in the comments.
Resources:
Check out the blog →
Subscribe to Google for Developers →
Speakers: Thor Schaeff, Anuda Weerasinghe
Products Mentioned: Google AI, Gemini
|
Ok, light mode really does keep you awak...
Developing, deploying, and remixing real...
Learn how web scraping can be utilized f...
From prompt to production-ready agents, ...
Back in 2004, email seemed like a solved...
Organizing a huge hackathon like TreeHac...
Discover how Seoul's relentless pace and...
Discover why San Francisco's culture of ...
Discover why New York City’s speed and e...