Google launches Gemini 3.5 Transcribe with support for 85+ languages and streaming

osanseviero · x · 2026-08-27

Google announced Gemini 3.5 Transcribe, a new speech-to-text model featuring smart transcription, function calling, custom vocabulary, and multi-speaker identification. It supports over 85 languages, offers both batch and real-time streaming audio support, and is now integrated across Google's products.

Related event: Google Launches Gemini 3.5 Transcribe with 85+ Languages and Smart Post-Processing(17 posts)→

Original post →

More from Multimodal

Multimodal channel →