Gemini 3.5 Live Translate: smooth and natural voice translation
Google DeepMind has released Gemini 3.5 Live Translate, a speech-to-speech translation model that detects 70+ languages and generates natural-sounding translated speech with preserved intonation. The model rolls out across Google products including the Gemini Live API, Google Meet, and Google Translate apps, with continuous streaming and noise robustness.
Google/DeepMind

