Google has introduced Gemini 3.5 Transcribe, an advanced AI audio model designed for improved speech recognition and transcription. This new model can convert unstructured speech into formatted text, automatically detect over 85 languages, and accurately attribute speech to up to three speakers with word-level timestamps. Gemini 3.5 Transcribe also learns custom vocabulary and unique spellings, and will soon be integrated into Chrome for use in any web field, allowing users to dictate replies and prompt Gemini with voice commands. AI
IMPACT Enhances speech-to-text capabilities, potentially improving productivity and accessibility across various applications.
RANK_REASON New model release from a frontier lab (Google Gemini Audio family). [lever_c_demoted from frontier_release: ic=2 ai=1.0]
- Gemini
- Gemini 3.5 Live
- Gemini 3.5 Live Experimental
- Gemini 3.5 Transcribe
- Gemini app
- Gemini Audio
- Gmail
- Google Antigravity
- Chrome
- Docs
- Keep
- macOS
- Pixel 11-series phones
- Search Live
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →