I’ve built a dozen or more apps. This one was made nearly entirely via voice using a telegram chat with my openclaw running on a machine at home. The claw uses ACP to talk to GitHub copilot which uses Brady Gaster’s squad agent. Each squad member has a responsibility context window and appropriate model (so as to avoid being wasteful) for the tasks.
Today, we released Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation.
It supports over 70 languages and starts translating as soon as you start talking, streaming translations while listening to what you say next. No awkward pauses or choppy audio, just real connection without language barriers.
So, how does it work? 🤔
The model is able to make split-second decisions to juggle speed and translation quality so conversations actually feel fluid, human, and natural. In order to do this, the model must receive and contextualize the input while simultaneously outputting the translated speech.
Through this process, Gemini 3.5 Live Translate manages to stay mere seconds behind each speaker and can even maintain pacing, pitch, and intonation across extended sessions.
See it in action below, or try it yourself in the Google Translate app on iOS & Android.
For the record, the president of the United States is now simultaneously claiming that he has won the war, is currently winning the war, needs help to win the war, and needs no help to win the war. All to destroy the nuclear program he claims to have already destroyed last year.
Fascinating study, more fascinating how Ethan posts about this 2017 study at least once a year with a different tweet. :) I would love to get his AI system that writes these tweets !
More on how bad air pollution is for the 🧠: going from a no-pollution day to pollution (only 15 PM2.5 - green on the map!) in Ottawa drops the quality of politician's speeches an amount equivalent to them having half a year less education that day! https://t.co/N0yxhuKPxj