opensource-clipping

🎬 Ultimate AI Auto-Clipper - Transform long-form videos & podcasts into viral shorts! Features smart face-tracking, kinetic karaoke subtitles, contextual B-rol

What is opensource-clipping?

🎬 Ultimate AI Auto-Clipper - Transform long-form videos & podcasts into viral shorts! Features smart face-tracking, kinetic karaoke subtitles, contextual B-roll, AI voice-overs, and auto-uploaders (YouTube/FB). Powered by Whisper, Gemini, MediaPipe, & Pyannote.

Overview of opensource-clipping

What it is

OpenSource Clipping is an open-source AI auto-clipper that transforms long-form videos and podcasts into short-form highlights. It uses Faster-Whisper for word-level transcription, Google Gemini for content curation, MediaPipe BlazeFace for face tracking, and Pyannote for speaker diarization. The tool generates cinematic teaser hooks, karaoke subtitles, kinetic typography, contextual B-roll, auto-thumbnails, and supports auto-upload to YouTube and Facebook Reels.

Key features

  • AI Transcriber: word-level transcription using Faster-Whisper (large-v3)
  • AI Content Curator: Google Gemini analyzes context, picks viral moments, and generates metadata
  • Smart Auto-Framing: face-tracking via MediaPipe BlazeFace with smooth pan, deadzone, and anti-jitter
  • Karaoke Subtitles: word-by-word highlighted .ASS subtitles (Alex Hormozi / Veed style)
  • Kinetic Typography: AI-driven word emphasis with bounce/stagger animations and dual-font system
  • B-Roll Integration: auto-fetches contextual stock footage from Pexels with crossfade and Ken Burns
  • Auto YouTube Uploader: automatically upload highlight clips to YouTube with scheduling and full metadata

Use cases

  • Convert long-form YouTube videos or podcasts into viral short-form clips for TikTok, YouTube Shorts, or Instagram Reels
  • Generate cinematic teaser hooks with dark overlay, glitch transitions, and karaoke subtitles
  • Produce podcast split-screen or camera-switch videos with automatic speaker diarization
  • Create AI voice-over commentary or reaction videos from existing clips
  • Automate content repurposing with scheduled uploads to YouTube and Facebook

Getting started

git clone https://github.com/NaufalRizqullah/opensource-clipping.git
cd opensource-clipping
pip install -r requirements.txt
cp .env.sample .env
### Edit .env and add your GOOGLE_API_KEY
python main.py --url "https://youtube.com/watch?v=VIDEO_ID"

For Google Colab, open a new notebook with T4 GPU runtime and run the setup cells provided in the repository.

License and pricing

This project is licensed under the MIT License and is open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/naufalrizqullahopensource-clipping.svg)](https://yunodb.com/tools/naufalrizqullahopensource-clipping?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/naufalrizqullahopensource-clipping?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/naufalrizqullahopensource-clipping.svg" alt="Featured on YunoDB" height="20"></a>