tech
Google's New AI Transcription Edits Out Your ‘Ums’ and ‘Ahs’
Posts from this topic will be added to your daily email digest and your homepage feed.
TL;DR
- Google's Gemini Audio now includes 3.5 Transcribe, an advanced transcription model.
- 3.5 Transcribe automatically detects specialized jargon and supports over 85 languages.
- It can format text, remove filler words like 'um' and 'uh', and adapt to custom vocabularies.
- The model can attribute speech for up to three speakers and provide word-level timestamps.
- Updates for Gemini 3.5 Live and 3.5 Live Experimental were also noted but are not launching today.
- 3.5 Transcribe is rolling out for macOS Gemini app users, Android users in select regions, and developers via the Gemini API.