Live music in frame: one continuous audio span, picture cuts on top
When a band or a busker is in the shot, keep one unbroken stretch of that clip's audio under the whole scene and cut only the picture; cut the audio per shot and the beat restarts.
Edit instruction for a live-music scene: - Pick the one clip with the cleanest, longest take of the music. Its audio from {span_start} to {span_end} seconds is the ONLY sound under the scene. - Lay the other angles as picture cuts on top of that span. Never cut the audio with the picture. - Give the music its own time: if this music is what the trip was for, 20-30 seconds of it, not one line of the MC. - The score has a hole here (silence), not a duck. - If a speaker is drowned by the band, raise the speaker from the vocals stem of that clip and sit it over the same continuous span. ffmpeg, picture from the cut, sound from the span, video not re-encoded: ffmpeg -i cut_video_only.mp4 -ss {span_start} -t {span_length} -i master_clip.mp4 -map 0:v -map 1:a -c:v copy -c:a aac -shortest scene.mp4
In Claude Code, paste the prompt as a message, or run /video-edit which does this end to end.
Steps
- Export the picture cut of the scene without audio first (add -an to the render).
- Trim the master clip's audio span and marry it to the picture with the command.
- Check with ffprobe that the output duration equals the picture duration; a span shorter than the cut leaves silence at the tail.
Tips
- The beat restarting at every cut is the most common tell of an amateur concert edit.
- `demucs -d mps --two-stems=vocals -o out clip.wav` gives the vocals stem for a speaker drowned by the band (the stem-split skill).
- In Claude Code, `/video-edit` holds this rule: live music is one continuous span, a hole in the score, no ducking.
| works with | ffmpeg: A terminal command you run yourself. · CapCut / any editor: A manual recipe for any editor. · Claude Code: Runs as a skill or a prompt in the terminal; can read your files and write the result. · By hand: No tool needed: a checklist or a technique. |
| skill | npx skills add fortunto2/solo-factory/video-edit · source |
| cost | Free. No API, no key. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-01 |
| for agents | live-music-one-continuous-audio-span.md |
Related
Score with a hole, not ducking, where something plays live
Cut the score to silence under live music, a laugh or a knock instead of ducking it; ducking is audible, a hole is not. The rule, the measured levels and the ffmpeg line.
Strip other people's music before upload with Demucs and ffmpeg
Car radio, shop speakers and festival stages trigger Content ID. Split the soundtrack into stems, find the music on drums plus bass, keep the voice, replace the music, rebuild audio only.
Level every chapter to -16 LUFS with ffmpeg loudnorm
One ffmpeg line that brings a file to -16 LUFS integrated and -1.5 dBTP true peak without touching the video, the two-pass version for exact results, and the timestamp trap on upload.
Voice cleanup checklist: room tone, de-ess, noise gate, in that order
Six passes that turn a phone or lav recording into a usable voice track, each with the ffmpeg filter and a starting parameter to adjust by ear, in the order that keeps the gate off word endings.
Beat-sync cutting: cut on the beat, not on every beat
A rule and an agent prompt for cutting to music from a list of beat timestamps: cuts land on beats, phrases get room to breathe, and the best shot is held through the hook.
A contact sheet of every cutaway with its line under it
The one-page check that catches off-topic cutaways before anyone watches: every cutaway frame in a grid, its sentence under it. Measured once: 12 of 54 automatic cutaways were off topic.