Gemini 3.5 Transcribe generally available (GA)
GAVerifiedAdded Sep 22, 2026
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).
Topics: LLMs, Streaming, Developer tools, Performance
Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.
More Gemini API releases
Every Gemini API release| Date | Release | Type |
|---|---|---|
| Aug 27 | Gemini Omni Flash generally available (GA) GA | GA |
| Sep 1 | Agentic video understanding Update | Update |
| Sep 2 | Gemini 3.8 Flash generally available (GA) GA | GA |
| Sep 3 | Lyria 3.5 generally available (GA) GA | GA |
| Aug 13 | Gemini 3.7 Flash generally available (GA) GA | GA |
| Sep 15 | Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking are generally available GA | GA |
| Sep 17 | Antigravity Agent 09-2026 Preview | Preview |
| Sep 18 | Gemini 2.5 models access update Update | Update |
