AI YouTube Shorts Generator Anil-matcha/AI-Youtube-Shorts-Generator

Python CLI and library that ranks the most viral moments in a long video with an LLM and renders them as vertical shorts.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

AI YouTube Shorts Generator at a glance

Checked 16 Oct 2026

A Python 3.10+ CLI and library: give it a YouTube URL (or a local file in local mode) and it transcribes with Whisper, has an LLM score highlights 0-100 with a hook and reason, dedupes them and crops the top clips to 9:16 or any ratio. Default API mode sends everything to the paid MuAPI service; local mode uses yt-dlp, faster-whisper, ffmpeg and OpenCV face tracking but still needs an OpenAI or Gemini key. MIT. No captions, no GUI, no publishing. The README promotes the author's paid MuAPI.

Cite this page

RepoQuarry. “AI YouTube Shorts Generator.” Checked 16 Oct 2026. https://repoquarry.dev/projects/ai-youtube-shorts-generator

How much of Opus Clip does it replace?

3 of 5 jobs. Highlight picking, scoring and vertical crop only; no burned-in captions, editor or social publishing.

AI picks highlight clips from a long video Partial replacement

Auto-reframe to vertical 9:16 (speaker or face tracking) Partial replacement

Animated burned-in captions on clips Not covered

Virality score per clip Partial replacement

Schedule and publish clips to social platforms Not covered

For animated burned-in captions on clips, schedule and publish clips to social platforms, see other Opus Clip alternatives. You may also need to build an interface, an API server and hosting yourself.

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction

QuestionAnswerSourceChecked

Runs on my machine? Local mode runs on your machine except the LLM call; default API mode runs on MuAPI's servers `--mode local` runs entirely on your machine with `yt-dlp`, `faster-whisper`, and `ffmpeg`/`opencv` github.com · AI-Youtube-Shorts-Generator#api-mode-vs-local-mode ↗ 1d ago

Code licence MIT github.com · LICENSE ↗ 1d ago

Model weights licence No separate model weights; uses faster-whisper locally and OpenAI or Gemini for ranking github.com · AI-Youtube-Shorts-Generator#api-mode-vs-local-mode ↗ 1d ago

Commercial use Yes, MIT code; terms of the LLM API you use apply github.com · LICENSE ↗ 1d ago

Paid services needed? A cloud API key is required in both modes (MuAPI in API mode; OpenAI or Gemini in local mode); no local LLM option an LLM API key (`OPENAI_API_KEY` or `GEMINI_API_KEY`; only the LLM step is remote) github.com · AI-Youtube-Shorts-Generator#api-mode-vs-local-mode ↗ 1d ago

Hardware Not documented; local faster-whisper runs on CPU or CUDA Know the answer? —

Operating systems README documents a Python CLI with POSIX-shell virtualenv commands and /Users path examples, but does not confirm a Windows/macOS/Linux support matrix source venv/bin/activate github.com · AI-Youtube-Shorts-Generator#readme ↗ today

Setup effort Easy, clone, pip install -r requirements.txt (plus requirements-local.txt and ffmpeg for local mode), add keys to .env pip install -r requirements.txt github.com · AI-Youtube-Shorts-Generator#installation-self-hosted ↗ 1d ago