video-use

Introducing video-use — edit videos with Claude Code. 100% open source.

Drop raw footage in a folder, chat with Claude Code, get final.mp4 back. Works for any content — talking heads, montages, tutorials, travel, interviews — without presets or menus.

Try video-use in Browser Use Cloud.

What it does

• Cuts out filler words (umm, uh, false starts) and dead space between takes
• Auto color grades every segment (warm cinematic, neutral punch, or any custom ffmpeg chain)
• 30ms audio fades at every cut so you never hear a pop
• Burns subtitles in your style — 2-word UPPERCASE chunks by default, fully customizable
• Generates animation overlays via HyperFrames, Remotion, Manim, or PIL — spawned in parallel sub-agents, one per animation
• Self-evaluates the rendered output at every cut boundary before showing you anything
• Persists session memory in project.md so next week's session picks up where you left off

Install

uv tool install video-use
mkdir -p ~/.claude/skills/video-use
video-use skill > ~/.claude/skills/video-use/SKILL.md
video-use doctor

doctor tells you if anything is missing (ffmpeg, API key). Store your ElevenLabs key with video-use key (grab one at elevenlabs.io/app/settings/api-keys).

Or let your agent do it — paste into Claude Code, Codex, Hermes, Openclaw, or any agent with shell access:

Set up video-use for me.

Read https://raw.githubusercontent.com/browser-use/video-use/main/install.md and follow it: install the video-use tool, wire up ffmpeg, register the skill with whichever agent you're running under, and set up the ElevenLabs API key — ask me to paste it when you need it. After install, don't transcribe anything on your own — just tell me it's ready and wait for me to drop footage into a folder.

Then point your agent at a folder of raw takes:

cd /path/to/your/videos
claude    # or codex, hermes, etc.

For always-on editing from your own VPS or Telegram, run the agent through Browser Use Box. Watch the 15-second demo.

And in the session:

edit these into a launch video

It inventories the sources, proposes a strategy, waits for your OK, then produces edit/final.mp4 next to your sources. All outputs live in <videos_dir>/edit/ — the skill directory stays clean.

Install from source

If you'd rather hack on it:

git clone https://github.com/browser-use/video-use ~/Developer/video-use
cd ~/Developer/video-use
pip install -e .                # same `video-use` command, editable
video-use skill > ~/.claude/skills/video-use/SKILL.md
brew install ffmpeg             # required
brew install yt-dlp             # optional, for downloading online sources
video-use key                   # paste your ElevenLabs API key

How it works

The LLM never watches the video. It reads it — through two layers that together give it everything it needs to cut with word-boundary precision.

Layer 1 — Audio transcript (always loaded). One ElevenLabs Scribe call per source gives word-level timestamps, speaker diarization, and audio events ((laughter), (applause), (sigh)). All takes pack into a single ~12KB takes_packed.md — the LLM's primary reading view.

## C0103  (duration: 43.0s, 8 phrases)
  [002.52-005.36] S0 Ninety percent of what a web agent does is completely wasted.
  [006.08-006.74] S0 We fixed this.

Layer 2 — Visual composite (on demand). timeline_view produces a filmstrip + waveform + word labels PNG for any time range. Called only at decision points — ambiguous pauses, retake comparisons, cut-point sanity checks.

Naive approach: 30,000 frames × 1,500 tokens = 45M tokens of noise. Video Use: 12KB text + a handful of PNGs.

Same idea as browser-use giving an LLM a structured DOM instead of a screenshot — but for video.

Pipeline

Transcribe ──> Pack ──> LLM Reasons ──> EDL ──> Render ──> Self-Eval
                                                              │
                                                              └─ issue? fix + re-render (max 3)

The self-eval loop runs timeline_view on the rendered output at every cut boundary — catches visual jumps, audio pops, hidden subtitles. You see the preview only after it passes.

Design principles

1. Text + on-demand visuals. No frame-dumping. The transcript is the surface.
2. Audio is primary, visuals follow. Cuts come from speech boundaries and silence gaps.
3. Ask → confirm → execute → self-eval → persist. Never touch the cut without strategy approval.
4. Zero assumptions about content type. Look, ask, then edit.
5. 12 hard rules, artistic freedom elsewhere. Production-correctness is non-negotiable. Taste isn't.

See SKILL.md for the full production rules and editing craft.