GoKawiilGoogle adds Gemini 3.5 Transcribe with filler-word removal and voice editing
Google has released three new Gemini Audio models: 3.5 Transcribe, 3.5 Live, and 3.5 Live Experimental. Transcribe automatically strips out filler words like 'um' and 'uh', formats text, adapts to custom vocabulary and jargon, and can identify up to three speakers with word-level timestamps. The Live models improve handling of interruptions, multilingual recognition, and real-time reasoning narration for voice chat.
GoKawiil's interpretation of the reporting above, not reported fact.
Cleaner, jargon-aware transcription reduces manual editing for professionals like journalists, researchers, and businesses relying on dictation tools. It also signals Google is prioritizing incremental audio improvements while the promised Gemini 3.5 Pro model remains delayed, keeping pressure on rivals in the voice AI space.
- Gemini 3.5 Transcribe removes filler words and adapts to custom vocabulary
- New Live models improve interruption handling and real-time reasoning narration
- Rollout begins today for macOS Gemini app users and Android's Rambler dictation
Blue Yeti USB Microphone — If you're leaning on AI transcription tools like Gemini 3.5 Transcribe, clean audio input still makes everything better. The Blue Yeti is a plug-and-play USB condenser mic with multiple pickup patterns, making it a solid pick for dictation, podcasts, and calls alike.
See Blue Yeti USB Microphone on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: theverge.com — Jess Weatherbed, 2026-08-26
Published there as: “Google’s new AI transcription edits out your ‘ums’ and ‘ahs’”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.