Google launches two Gemini 3.5 Transcribe models for offline and live use

patloeber · x · 2026-08-27

Google launched two Gemini 3.5 Transcribe models. The standard version is for transcribing recorded audio with speaker attribution and word-level timestamps, while the Live version is designed for building real-time voice applications.

Related event: Google Launches Gemini 3.5 Transcribe with 85+ Languages and Smart Post-Processing(16 posts)→

Original post →

More from Multimodal

Multimodal channel →