Moviepy

When you need to put accurate text on AI-generated video, this is the tool. LTX-2 and SadTalker can't render readable text reliably, so the pattern is: generate the visual, then overlay names, prices, or captions with moviepy in Python. It's built for sub-30s spots, lower thirds on talking heads, and anything where the text has to be pixel-perfect for legal or editorial reasons. The skill includes two runnable examples that produce real mp4s immediately, and it ships a PIL-based text renderer that sidesteps moviepy's tight-bbox bug. Use this over Remotion when you want a single build.py file and zero React overhead.

skills.sh installs: 1.3K
GitHub stars: 2.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add digitalsamba/claude-code-video-toolkit --skill moviepy --agent claude-code

Installs into .claude/skills of the current project.

Files

moviepy for Video Production

moviepy is the toolkit's go-to library for putting deterministic text on top of AI-generated video and for building short, single-file Python video projects without a Remotion toolchain.

The deeper principle is trustworthy text: any genre where text has to be readable, accurate, and consistent (legally, editorially, or commercially) is a genre where AI-rendered in-frame text is unacceptable and a moviepy overlay step is the natural fix. Names must be spelled right. Prices must be exact. Source attributions must be pixel-perfect. AI generation models cannot guarantee any of that.