SYLIN

Gemini 3.5 Transcribe

by Google · Model · Voice & audio

Transcription model with verbatim and smart modes, speaker detection, word timestamps and automatic multilingual handling

Promised Aug 30: coming soon to Chrome

Evidence

  1. Aug 30
    On Pixel 11 Pro dictation, a user found it simplifies phrasing, dropping clauses like 'I hesitated to check it' and changing meaning.
  2. Aug 27
    Gemini 3.5 Transcribe and a Live (streaming) variant released in the Gemini API; also powers Pixel dictation.
  3. Aug 27
    Reported as still more expensive and worse performing than ElevenLabs Scribe.
  4. Aug 27
    Real-time translator developer found it most accurate of tested models but too slow; Soniox STT v5 wins on latency.
  5. Aug 27
    Added to a multilingual STT benchmark site; it does not reach the frontier in either latency or accuracy there.