Automatically trim dead air from a talking head video before manual fine editing
Remove filler words like um and uh using local Whisper transcription
Mute profanity in place without shifting the rest of the timeline
Export an SRT caption file that matches the timeline after cuts are applied
| eonurk/cutty | 00kaku/gallery-slider-block | 3rd-eden/ircb.io | |
|---|---|---|---|
| Stars | 0 | — | — |
| Language | JavaScript | JavaScript | JavaScript |
| Last pushed | — | 2021-05-19 | 2016-11-16 |
| Maintenance | — | Dormant | Dormant |
| Setup difficulty | moderate | easy | easy |
| Complexity | — | 2/5 | 2/5 |
| Audience | general | general | developer |
Figures from each repo's GitHub metadata at analysis time.
macOS and Premiere Pro 2020+ only, needs ffmpeg via Homebrew, and a Whisper model download for filler word or profanity muting.
Cutty is a panel that adds itself to Adobe Premiere Pro to automatically cut out silence and filler words from talking head video, while keeping you in control of every edit before it happens. All of the analysis runs on your own computer using ffmpeg, so no footage is ever uploaded anywhere. The workflow is straightforward: select one or more talking clips on your timeline, click analyze, and Cutty shows a waveform with every proposed cut marked. You can click any cut to toggle it off, use All or None to toggle everything at once, and preview a cut by parking the playhead just before it. Five presets, from calm and podcast style to jumpy and fast paced, adjust how aggressively pauses get trimmed, and you can fine tune settings like how quiet counts as silence and how much padding to leave around speech. By default, edits apply to a duplicate of your sequence rather than the original, so nothing you already built gets overwritten. Beyond plain silence removal, Cutty can optionally transcribe your clip locally with Whisper to also cut filler words like um and uh, shown separately on the waveform in a different color so you can review each one. A similar local transcription feature can mute profanity in place without shifting the timing of your video. There is also a feature to export a caption file in SRT format matching your edited timeline, meant to be run after cutting is finished. Cutty only works on macOS with Premiere Pro 2020 or newer, and requires ffmpeg installed through Homebrew, with an optional Whisper model download for the filler word and profanity features. It does not yet support speed changed clips, nested sequences, or multicam clips.
A local Premiere Pro panel that finds silences and filler words in talking clips and lets you review and remove them on a waveform.
Mainly JavaScript. The stack also includes JavaScript, ExtendScript, ffmpeg.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly general.
This repo across BitVibe Labs
double-check against the repo, no cap.