Google's Gemini 3.5 Transcribe edits out filler words in audio
google updates gemini audio with new transcription capabilities that detect specialized jargon and 85+ languages, allowing users to edit naturally with voice. this affects users of google's voice-controlled ai features.
google has updated its gemini audio models with new transcription capabilities, introducing gemini 3.5 transcribe, which represents a major advancement from its previous transcription model, chirp 3. gemini 3.5 transcribe can automatically format text, remove filler words like 'um' and 'uh', and adapt to unique spelling requirements and specialized jargon. it can also attribute speech for up to three speakers in pre-recorded audio and provide word-level timestamps. this update is rolling out starting today in english for all macos gemini app users and the rambler dictation feature on android in select countries and languages. developers can access it in public preview via the gemini api.