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 YouTube Shorts without expensive monthly subscriptions or per-clip credit limits.

How it works

The tool processes videos through a multi-step pipeline:

  1. Ingestion: Downloads the video via YouTube URLs or local files.
  2. Transcription: Uses Whisper (via MuAPI or locally via faster-whisper) to create a timestamped transcript.
  3. Analysis: An LLM (GPT or Gemini) analyzes the transcript using a specific "virality framework" to identify high-impact moments based on hooks, emotional peaks, and practical value.
  4. Processing: Long videos are chunked to ensure no highlights are missed, and overlapping clips are deduplicated.
  5. Rendering: The selected highlights are cropped vertically. In API mode, this is handled by MuAPI; in local mode, it uses OpenCV face tracking and motion smoothing with FFmpeg.

Who it’s for

  • Content Creators: Who want to repurpose long-form content into shorts for free.
  • Agencies: Who need to process large volumes of videos without high SaaS costs.
  • Developers: Who want to integrate an AI clipping pipeline into their own applications via the provided Python library or CLI.

Highlights

  • Dual Operation Modes: Offers a fast API-driven mode (MuAPI) and a local mode for offline processing (except for the LLM call).
  • ** uma Virality-Aware Ranking**: Ranks clips based on specific signals like "opinion bombs" and "revelation moments" rather than generic interest.
  • Smart Vertical Cropping: Uses face tracking in local mode to ensure the subject remains centered in the 9:16 frame.
  • Automation Friendly: Supports batch processing via xargs and can export results as JSON for downstream workflows.

Related

  • Project
    RafaelGodoyEbert/ViralCutter

    An open-source, local AI tool that transforms long YouTube videos into viral short-form clips with automatic cropping, dynamic captions, and face tracking.

  • Project
    FujiwaraChoki/supoclip

    An open-source, AI-powered video clipping tool that transforms long-form videos into viral vertical clips with automatic face-centering, subtitles, and virality scoring.

  • 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 open-source tool that automatically converts long videos into short-form clips for social media, generating the video, cover, and captions using AI.

  • Project
    jipraks/yt-short-clipper

    YT Short Clipper v2 is a Windows‑only desktop app that automatically turns a long YouTube video into vertical (9:16) short clips. It downloads the video and its original subtitles, feeds the transcript to an LLM to pick highlight segments, cuts and re‑frames each segment, burns word‑by‑word captions, and can upload the results to Repliz. Built with React + TypeScript, Tauri (Rust), and a Python side‑car using yt‑dlp, FFmpeg, and MediaPipe, it supports any OpenAI‑compatible model or an in‑app wallet‑based AI service. The project is MIT‑licensed, beta‑stage, and Windows‑only.