ModelClock
Released on Aug 26, 2026
Google announced this model on 2026-08-26. Live API.
- Hosting route
- First-party API
- Affected scope
- Live API
- Announced
- Aug 26, 2026
- First seen by ModelClock
- Oct 4, 2026
What the provider published
ai.google.dev ↗August 26, 2026
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.
Read from the provider's text; the quote is the provider's exact lines.