Video Remove Audio
Removes all audio and music tracks from a single video file using FFmpeg, keeping the video stream (stream copy by default). Use when the user wants to mute a video, strip audio, remove soundtrack/BGM/music from MP4/MKV/MOV/WebM, export silent video, or remove audio from a cutscene clip.
Get the complete skill folder, including its scripts and reference files.
When to use this skill
Use Video Remove Audio when an AI agent needs a reusable SKILL.md workflow for this job: Removes all audio and music tracks from a single video file using FFmpeg, keeping the video stream (stream copy by default). Use when the user wants to mute a video, strip audio, remove soundtrack/BGM/music from MP4/MKV/MOV/WebM, export silent video, or remove audio from a cutscene clip.
When not to use it
Skip Video Remove Audio when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.
How to install
Where will you use it?
mkdir -p ~/.claude/skills/video-remove-audio # Save SKILL.md to ~/.claude/skills/video-remove-audio/SKILL.md
- Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/video-remove-audio/SKILL.md. For a shared project, commit the folder at .claude/skills/video-remove-audio/ instead.
- Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
- For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.
Full install guide for Claude, Cursor, and Codex →
Try a starter prompt
After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.
Use the Video Remove Audio skill for this task: Use Video Remove Audio when this documented workflow matches the task. Confirm any required inputs or files before making changes.
What supports this recommendation?
70/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.
- Documentation
- 77/100
- Practical detail
- 68/100
- Source evidence
- 61/100
- Source signals
- 72/100
Model compatibility evidence
- claudeuntested
No model-specific signal or recorded compatibility test was found.
- chatgptuntested
No model-specific signal or recorded compatibility test was found.
- geminiuntested
No model-specific signal or recorded compatibility test was found.
- copilotuntested
No model-specific signal or recorded compatibility test was found.
- llamauntested
No model-specific signal or recorded compatibility test was found.
- perplexityuntested
No model-specific signal or recorded compatibility test was found.
- mistraluntested
No model-specific signal or recorded compatibility test was found.
- grokuntested
No model-specific signal or recorded compatibility test was found.
Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.
What this skill does
# Video Remove Audio
Strip **all audio tracks** (music, voice, SFX) from a supported video file via FFmpeg. **Defaults preserve the video bitstream** — stream-copy video (`-c:v copy`), drop audio (`-an`), no re-encode.
## Rules
When this skill applies, read and follow [skill-dependency-manager](../skill-dependency-manager.md) — run scripts as documented, install missing tools into `.dependency/`.
- Run `remove_audio.py` through **`.dependency/python/python.exe`**. Never use host `python` / `ffmpeg`. - **Never overwrite sources.** Outputs go under `video-remove-audio/`. - Use the bundled script — do not hand-write equivalent FFmpeg commands. - **One file per run** — pass `--video` with a single file; repeat for each clip in a batch.
## Quick Start
```bash .dependency/python/python .ai/video-remove-audio/remove_audio.py --video path/to/clip.mp4 ```
Example:
``` assets/intro.mp4 → assets/video-remove-audio/intro.mp4 ```
Same video codec/container, no audio.
## Format Defaults
| Setting | Default | Notes | |---------|---------|-------| | Video | Stream copy | No quality loss; same codec/resolution/fps | | Audio | Removed (`-an`) | Drops every audio stream | | Container | Same as source | Extension preserved | | Already silent | Skipped | Reports `[skip]` when no audio streams |
## Common Flags
`--video` · `-o` / `--output`
```bash .dependency/python/python .ai/video-remove-audio/remove_audio.py --video clip.mp4 .dependency/python/python .ai/video-remove-audio/remove_audio.py --video clip.mp4 -o out/silent.mp4 ```
**Never overwrite source files.** Input must be a single video file (`--video`), not a directory. Supported inputs: `.mp4`, `.mkv`, `.mov`, `.avi`, `.webm`, `.wmv`, `.flv`, `.m4v`, `.mpeg`, `.mpg`, `.ts`, `.mts`, `.m2ts`, `.3gp`, `.ogv`.
## Agent Notes
1. Use the bundled script, not hand-written `ffmpeg -i … -an` commands. 2. Always uses **stream copy** for video (`-c:v copy -an`). 3. This removes **all** audio; it does **not** isolate or mute music while keeping dialogue (no stem separation). 4. Missing Python/FFmpeg → populate `.dependency/` per skill-dependency-manager, retry same command. 5. **Do not copy, move, or replace the source with muted output** — tell the user where `video-remove-audio/` files are; they swap assets manually when ready. 6. Need audio extracted instead of removed → use **video-to-wav**. 7. FFmpeg details: [reference.md](reference.md)
## Tests
From repo root:
```bash .dependency/python/python .ai/video-remove-audio/test_remove_audio.py ```
Manual CLI examples: [cli/video-remove-audio.md](../../../cli/video-remove-audio.md)
Intended uses
- Use Video Remove Audio when this documented workflow matches the task.
Implementation notes
- Review the source instructions and adapt inputs before running the workflow.
Try it, then tell us how it went
A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.