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

AI-Youtube-Shorts-Generator

Open-source alternative to Opus Clip, Vidyo.ai, Klap & SubMagic. Turn long-form YouTube videos into viral 9:16 shorts using LLM highlight detection, Whisper transcription, and auto vertical cropping. Free, no watermarks, no per-clip credits.

5.7k ★+97/wkemergingPythonMIT License →trending

The Lens

By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.

Updated Oct 2026

AI-Youtube-Shorts-Generator turns a long YouTube video into vertical shorts. It transcribes the video, has an LLM score the moments most likely to hold attention, and crops each one to 9:16. It's pitched as the open source answer to OpusClip and Klap, and the code is MIT.

Two modes, and the difference is the whole story. The default API mode runs every step through MuAPI, a paid API. Local mode does download, transcription and cropping on your machine and only calls OpenAI or Gemini to rank clips. Gemini's free tier covers that, so local mode can cost nothing. It's a Python CLI: no editor, no preview, no captions.

Solo creators: local mode with a Gemini key, free. Small teams clipping at volume: API mode costs cents per clip. Agencies that need captions and an editor should pay for a SaaS clipper.

The catch: this repo is a storefront. MuAPI is run by Vadoo, the company the repo's homepage points to, and the README carries tracking links to MuAPI's paid AI Clipping API, which it says makes better clips. No code has changed since June; every commit since touched only the README or license. Treat it as a scaffold.

Free vs Self-Hosted vs Paid

free self hosted paid cloud

Free: The MIT-licensed code (the LICENSE file was added in September 2026). No watermarks, no clip caps. Local mode with a Gemini free-tier key costs nothing in API fees, but on Google's free tier your transcript content is used to improve Google's products.

Self-hosted: Python 3.10+. Local mode adds yt-dlp, faster-whisper (CPU or CUDA), OpenCV and ffmpeg on your PATH, and only the ranking call leaves your machine. It also accepts local video files, not just YouTube links. The default API mode needs only a MuAPI key.

Paid: API mode bills MuAPI per call: $0.01 per YouTube download, a flat $0.012 per Whisper transcription run, and autocrop at $0.05/min plus a $0.05 base per clip ($0.10 for a 60-second clip), plus MuAPI's gpt-5-mini call for ranking. Local mode on paid Gemini 2.5 Flash is $0.30 per 1M input tokens and $2.50 per 1M output tokens; OpenAI (default gpt-4o-mini) bills at OpenAI's rates. The same vendor sells a hosted AI Clipping API at $0.05/min of video plus $0.05 per highlight.

Local mode with a Gemini free-tier key runs for $0 in API fees. The default API mode bills MuAPI per call, about $0.10 to crop a one-minute clip plus a few cents for download and transcription.

What to do by team size

Solo
free with local mode and a Gemini free-tier key
Small team
free in local mode, or cents per clip in MuAPI's API mode
Medium team
API mode on MuAPI or a GPU box for faster-whisper; budget engineering time, there is no UI
Large team
skip it; no editor, no captions and code untouched since June. A SaaS clipper fits better
Self-hosting ops:moderate

Get tools like this every Wednesday

One featured tool, three on the radar. No fluff.

Similar Tools

Score
80/100 · A
Adoption23/30
Maintenance25/25
Community7/20
License15/15
Analysis10/10

A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores

Trust Signals

Notable author: 1,894 followers

About

Owner
Anil Chandra Naidu Matcha (User)
Stars
5,659
Forks
1,026

Explore Further

More tools in the directory