By Anuda Weerasinghe
Publication Date: 2026-06-09 00:00:00
Twenty years ago, translation began at Google as one of our groundbreaking machine learning experiments to transform the science of language into the magic of human connection. This experiment has come a long way: over a trillion words are translated every month for billions of users in our products.
Today we’re taking the next step with the release of Gemini 3.5 Live Translate, our latest audio model for live language translation.
The model automatically recognizes over 70 languages and generates smooth, natural-sounding translated speech that maintains the speaker’s intonation, tempo and pitch. Unlike turn-by-turn systems that wait for the speaker to finish speaking before responding, 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 sound without awkward pauses and stays behind the speaker for only a few seconds throughout the process…
