Anil-matcha/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.

What it solves

This project provides an open-source alternative to paid AI clipping tools. It allows users to convert long-form YouTube videos into short, viral-ready vertical clips (9:16) for platforms like TikTok, Reels, and Shorts without expensive monthly subscriptions, per-clip credits, or watermarks.

How it works

The tool processes videos through a multi-step pipeline:

  1. Extraction: It downloads the source video from YouTube or a local file.
  2. Transcription: It uses Whisper (via MuAPI or locally via faster-whisper) to generate a timestamped transcript.
  3. Analysis: An LLM (GPT or Gemini) analyzes the transcript using a "virality framework" to identify high-impact moments based on hooks, emotional peaks, and practical value.
  4. Refinement: For long videos, it chunks the content to ensure no highlights are missed and deduplicates overlapping clips.
  5. Cropping: It converts the horizontal video to a vertical format using either MuAPI's auto-crop or local OpenCV face tracking with motion smoothing.

Who it’s for

  • Content Creators: Those looking to repurpose long videos into shorts for free.
  • Agencies: Teams managing multiple channels who need batch processing capabilities.
  • Developers: Users who want a white-label or embeddable Python library to build their own clipping SaaS.

Highlights

  • Dual Operation Modes: Offers a fast API-driven mode (MuAPI) and a local mode for offline processing (except for the LLM call).
  • Virality-Aware Ranking: Clips are not just randomly selected but ranked by a viral score, complete with a suggested hook and a reason for the clip's potential success.
  • Flexible Output: Supports various aspect ratios (9:16, 1:1) and resolutions.
  • Automation Friendly: Includes a CLI and a Python library with JSON output for integration into larger workflows.

Related

  • Project
    OStudi/short-video-generator-AI

    An open-source tool that converts long YouTube videos into viral short clips by using AI to detect highlights, transcribe audio, and auto-crop video.

  • Project
    JayWebtech/autoshorts

    A local-first desktop app that uses AI to identify viral moments in long-form video or audio and automatically crops them into vertical short-form clips.

  • Project
    zhouxiaoka/autoclip

    An AI-powered video clipping tool that automatically downloads videos from YouTube and Bilibili, analyzes content via LLMs to extract highlights, and generates short-form collections.

  • Project
    pmarreck/yt-transcriber

    A CLI tool that transcribes YouTube videos or local media files using Whisper, with optional AI-powered summarization and translation.

  • Project
    jipraks/yt-short-clipper

    A Windows desktop app that uses LLMs to identify highlights from YouTube videos and automatically converts them into captioned, 9:16 portrait clips.