←── back to feed
/topics/google-gemini-3-5-live-translate-launch

Google Gemini 3.5 Live Translate launch

3 items1 sourcesupdated 7d agotrend 0

Google released Gemini 3.5 Live Translate, a streaming speech-to-speech translation model that converts voice to voice across 70+ languages while preserving the speaker's tone, pacing, and pitch. The model is available to developers via the Gemini Live API and integrated into Google Meet and Google Translate.

  • Supports 70+ languages with continuous audio generation, running a few seconds behind the speaker
  • Preserves speaker's tone, pacing, and pitch in translated output
  • Includes SynthID watermarks for security
  • Available via Gemini Live API, Google Meet, and Google Translate app
  • Launched June 9, 2026