#3737th of 50 in Data and scraping for AIFor image, video and design, video and animation
ai-youtube-shorts-generator
CLI that cuts long YouTube videos into ranked vertical shorts
- Stars
- 6k
- License
- MIT
- Last commit
- Nov 2026
- Language
- Python
3,201 on 21 Apr 20265,951 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Python CLI and library that downloads a YouTube video or local file, transcribes it with Whisper, and has an LLM score highlight candidates for virality. The top N are cropped to 9:16 or another ratio. API mode runs everything through the MuAPI hosted service; local mode uses yt-dlp, faster-whisper, ffmpeg and OpenCV face tracking, with OpenAI or Gemini for ranking.
Who it is for: Creators and developers clipping long videos into shorts from scripts
Strengths
- Local mode runs download, Whisper, and cropping on your machine; only the LLM call is remote
- Each clip returns a score, hook line, and reason; --output-json dumps full results
- Highlight prompt and virality criteria are editable in shorts_generator/highlights.py
- Chunks videos over 30 minutes and dedupes overlapping candidates by score
Weaknesses
- Default API mode depends on a paid MuAPI key for download, transcription, and cropping
- Local mode still needs an OpenAI or Gemini API key for highlight ranking
- README promotes a hosted clipping API as giving better quality than this repo
- No Dockerfile, web UI, or tagged release; CLI and Python library only
What it needs
- GPU optional
- Needs MuAPI (API mode), ffmpeg (local mode), yt-dlp, faster-whisper, OpenCV, OpenAI or Gemini API key (local mode)
- Models: OpenAI gpt-4o-mini, Gemini gemini-2.5-flash, faster-whisper tiny to large-v3, MuAPI gpt-5-mini
Quick answers
Is ai-youtube-shorts-generator open source?
Yes. Its code is on GitHub under the MIT license.
Does ai-youtube-shorts-generator need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Data and scraping for AI
See all 50| Rank | Project | Score |
|---|---|---|
| 1 | doclingPython library that converts PDFs, Office files and more into structured text | 92 out of 100 |
| 2 | mineruParses PDFs, images and Office files into Markdown and structured JSON | 91 out of 100 |
| 3 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 90 out of 100 |
| #4 | agent-reachCLI that gives coding agents read access to login-gated and Chinese web platforms | 88 out of 100 |
| #5 | markitdownPython library and CLI that converts office files, PDFs and audio to Markdown | 87 out of 100 |