Cut dead air from videos automatically with auto-editor
Added New⧉ Copyable prompt below
Our verdict
A big time saver for talking-head videos, tutorials, podcasts and screen recordings: the boring first pass becomes a single command. No generative model, so results are predictable, and it's released under the Unlicense. Tune --margin so cuts don't feel abrupt, and review the result before publishing.
- Who it's for
- Creators and builders who record tutorials, demos, podcasts or streams
- Leverage
- Removes the most tedious editing pass
- Effort
- Low
- Date added
What it does
Auto-Editor is a command-line application that edits video and audio automatically by analysing audio loudness, motion or both. --edit chooses the method and threshold (including dB values), --margin adds padding around kept sections, and it can handle multiple audio tracks. It also ships an agent skill via npx skills add WyattBlue/auto-editor.
How builders use it
- Run auto-editor recording.mp4 for a default silence cut.
- Loosen the pacing with --margin 0.3s,1.5sec.
- For screen recordings, cut on motion: --edit motion:threshold=0.02.
- Add the agent skill so Claude Code or Cursor can run edits for you.
What to expect
A tightened rough cut in minutes, ready for your normal editor.
Copy this: Commands
auto-editor talk.mp4 # default: cut silence
auto-editor talk.mp4 --margin 0.3s,1.5sec # gentler pacing
auto-editor screen.mp4 --edit motion:threshold=0.02
auto-editor podcast.mp4 --edit "(or audio:0.03 motion:0.06)"
npx skills add WyattBlue/auto-editor # agent skillRelated discoveries
- ToolCreative & Media
ComfyUI
Open-source node-graph engine for image, video and audio generation that runs locally and exposes an API.
NewEffort: High#Image#Video
- WorkflowCreative & Media
Prompt videos in code with Remotion and a coding agent
Scaffold a Remotion project, add its agent skills, and describe the video to Claude Code, Codex or OpenCode.
NewEffort: Medium⧉ Prompt#Video#Open source
- ToolCreative & Media
Chatterbox TTS
Open-source text-to-speech models from Resemble AI with voice cloning, installable with pip.
NewEffort: Medium⧉ Prompt#Audio#GitHub repo
- ToolCreative & Media
LTX-2: open audio and video generation
Lightricks' open-weights model for video with synchronized audio, runnable locally or inside ComfyUI.
NewEffort: High#Video#Audio
Want more like this?
Practical discoveries, without the noise.