Back
AI summary
Written by AI from the official notes. Check them for exact details.Google has released Gemini 3.5 Transcribe for high-accuracy speech-to-text and Gemini 3.5 Transcribe Live for streaming transcription.
- Gemini 3.5 Transcribe offers high-accuracy, low-latency speech-to-text.
- Supports utterance-based language detection in 85+ languages.
- Includes speaker diarization and word-level timestamps.
- Gemini 3.5 Transcribe Live enables bidirectional streaming transcription.
- Smart transcription mode and multiple VAD strategies available.
Why it matters: Users needing reliable speech-to-text solutions across multiple languages should consider these new models.
Full release notes2 changes
- Gemini 3.5 Transcribe generally available (GA): Released two dedicated speech-to-text models based on Gemini's audio understanding: Gemini 3.5 Transcribe (
gemini-3.5-transcribe): High-accuracy, low-latency non-streaming speech-to-text with utterance-based language detection across 85+ languages, speaker diarization, word-level timestamps, and custom vocabulary biasing (up to 1,000 terms). - Gemini 3.5 Transcribe Live (
gemini-3.5-transcribe-live): Low-latency, bidirectional streaming speech-to-text over WebSockets using the Live API, supporting interim and finalized transcription events, Smart transcription mode, and multiple Voice Activity Detection (VAD) strategies.
To get started, see the Audio transcription guide, the Live transcription guide, and the Gemini 3.5 Transcribe model page.