Latest / Models & Agents for Beginners — Video Edition
Ep 147: Gemini just dropped a dictation tool that turns messy voice notes into polished text while…
Models & Agents for Beginners Gemini just dropped a dictation tool that turns messy voice notes into polished text while understanding what’s on your screen. Google released Gemini 3.5 Transcribe, a new speech-to-text model that cleans up filler words, works in over 85 languages, and uses what’s on your screen to understand commands. It already shows a 4.0 percent word error rate in streaming mode and delivers 70 percent lower latency than its predecessor Chirp 3. The model is rolling out in the Gemini app on macOS and Gboard on Android, with API access through Google AI Studio and the Gemini…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.