ModelsAug 27, 2026 · 02:046 sources

Google Ships Gemini 3.5 Transcribe to Cut Transcription Time 70% Over Chirp 3

From huggingnews.com

Image: huggingnews.com
AI;DR

Google released Gemini 3.5 Transcribe, a speech-to-text model that supports more than 85 languages and automatically removes filler words. The model reduces final transcription time by 70% compared to Chirp 3 and achieves a 2.6% word error rate on non-streaming audio. It is integrated into the Gemini app for macOS and the Rambler feature on Android, with developer access available via Google AI Studio and the Gemini API.

Read the sourceSign in to suggest

Sources

+ 4 more
  1. SUPPORT@officiallogank“new speech to text model with smart transcription, function calling, more precise transcription (lower WER)”x.com
  2. SUPPORT@_philschmid“70% reduction time for the final transcription compared to Chirp 3”x.com
  3. SUPPORT@google“Developers can start building in @GoogleAIStudio and Google @Antigravity”x.com
  4. SUPPORT@google“help turn spoken thoughts into polished text”x.com

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today