Google’s new AI transcription edits out your ‘ums’ and ‘ahs’

Google has announced a new update for its Gemini Audio model that includes advanced transcription features. The new model, Gemini 3.5 Transcribe, automatically detects specialized jargon and supports over 85 languages, enhancing transcription accuracy. This update follows the launch of the 3.5 Live Translate model and represents a significant advancement over the previous Chirp 3 model, particularly in multilingual performance and wording error rates.