Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

video-assemble (Final Video Assembly)

Final-stage skill that lays TTS narration over a source video, ducks the original audio, burns SRT/ASS subtitles, and loudness-normalizes the delivered recap.

Image & VideoAdvanced★ 559⑂ 105AI score 7/10Last updated: Oct 4, 2026

What it does

  • Places per-segment narration audio on the video timeline, ducks the original sound only inside narration windows, and restores it at a verified sentence-end anchor (with bounded 3s hold rules).
  • Generates subtitles.srt / subtitles.ass from narration positions and burns them in by default; if ffmpeg lacks libass it degrades to a sidecar .srt and logs a subtitle_burn_degraded warning.
  • Normalizes loudness with two-pass loudnorm plus a 4x-oversampled true-peak limiter, then re-measures the delivered AAC and re-encodes audio only (stream-copying video) if it exceeds -1 dBTP.
  • Emits auditable artifacts — timeline.json, assembly_manifest.json, assembly_qc.json, binding receipts — and optionally a Jianying/CapCut editable draft.

Who it's for

  • Creators mass-producing "source footage + AI narration" recap or summary videos.
  • Engineers building ffmpeg-based automated editing pipelines who want mixing, subtitle and loudness policy encoded as hard rules.
  • Post-production folks who need automated delivery gates (QC reports, true-peak ceilings, color tagging).

Usage examples

  1. python3 scripts/assemble.py source.mp4 --work-dir work/ — default narration mode: placement, ducking, subtitle burn, loudnorm.
  2. For a cut edit, add --source-video orig.mp4 --export-jianying to produce an editable draft that references real source ranges.
  3. Ship soft subtitles instead: pass --no-burn-subtitles and the run writes recap_<stem>.srt next to the final file.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/zenstory-ai/video-recap-skills/HEAD/skills/video-assemble/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/video-assemble folder from the GitHub repo zenstory-ai/video-recap-skills into my ~/.claude/skills/zenstory-ai-video-assemble/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/zenstory-ai/video-recap-skills.git /tmp/video-recap-skills && mkdir -p ~/.claude/skills && cp -r /tmp/video-recap-skills/skills/video-assemble ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal in your working directory.
  2. Clone the repo: git clone https://github.com/zenstory-ai/video-recap-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r video-recap-skills/skills/video-assemble ~/.claude/skills/
    • Copy the sibling skills in skills/ too if you want the full recap pipeline.
  5. Verify prerequisites: run ffmpeg -version and check for --enable-libass and --enable-libfreetype, and confirm python3 --version works.
  6. Restart Claude Code and ask it to "assemble the recap video, mix the narration and burn subtitles". Note this stage is not user-invocable on its own: it expects tts_meta.json produced by the earlier voiceover stage.
View source on GitHub ↗License: MIT