yokel1121/muyang-handdrawn-video — explained in plain English
Analysis updated 2026-05-18
Turn a single topic idea into a narrated, subtitled explainer video without editing software.
Produce short vertical social videos in a consistent hand drawn visual style.
Generate Chinese language narrated videos using a properly matched Chinese voice.
Get an editable Remotion project to keep tweaking script, images, and animation after generation.
| yokel1121/muyang-handdrawn-video | 410979729/scope-recall | abdullahselek/reducepy | |
|---|---|---|---|
| Stars | 33 | 33 | 33 |
| Language | Python | Python | Python |
| Last pushed | — | — | 2022-04-03 |
| Maintenance | — | — | Dormant |
| Setup difficulty | — | moderate | moderate |
| Complexity | — | 3/5 | 3/5 |
| Audience | vibe coder | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
This project is a Codex skill that turns a single topic into a finished hand-drawn style explainer video. You type in one sentence describing what you want the video to be about, and the skill handles the rest: writing a script, planning the storyboard, generating AI illustrations for each scene, producing spoken narration, syncing subtitles, adding Remotion based motion effects, and rendering a final MP4 file. The default output is a 60 to 90 second vertical video with continuous narration from a single consistent voice, generated scene by scene illustrations, and synced captions. For Chinese language projects, the tool prefers Chinese or Mandarin voices instead of forcing an English voice to read Chinese text, and it will pause and ask the user to pick a usable voice rather than silently using a mismatched one. Narration can come from Fish Audio, a Chinese focused cloud text to speech service, or ElevenLabs. Both require the user to sign up separately and provide their own API key, which is stored locally in a project file rather than inside the skill itself. There is also a guided mode that walks the user through choosing a visual style, screen shape, length, and voice step by step, with an option to stop answering questions and accept the defaults at any time. The project ships ten built in visual styles, ranging from a warm editorial look to a chalkboard classroom style to a technical blueprint style, each paired with its own fonts, color palette, and layout. It also includes matching motion presets so a chosen visual style automatically gets an animation style that fits it. Generated images stay free of text, since all titles, captions, and subtitles are rendered separately by Remotion so they remain clean and readable. To run it, a user needs Codex with the skill installed, Node.js, Python 3.10 or newer, FFmpeg, and the separate imagegen skill for creating illustrations. The output is an editable Remotion project, so scripts, images, subtitles, and animations can all be adjusted afterward rather than only being a final locked video file.
A Codex skill that auto generates a full hand drawn style explainer video, script to finished MP4, from just one topic sentence.
Mainly Python. The stack also includes Python, Node.js, Remotion.
Mainly vibe coder.
This repo across BitVibe Labs
Don't trust strangers blindly. Verify against the repo.