Back to search
stream-auto-clipper
SkillGitHub
Automated highlight detection, vertical video synthesis, and thumbnail generator for stream VODs.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/jvstin47--stream-auto-clipper)HTML
<a href="/listings/jvstin47--stream-auto-clipper"><img src="/api/listings/jvstin47--stream-auto-clipper/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
# 1. Install dependencies python3 -m venv .venv source .venv/bin/activate pip install -r requirements.txt # 2. Configure settings cp config.example.json config.json # 3. Run clipper python stream_clipper.py --file input.mp4 --count 5
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 50 lines
- # stream-auto-clipper
- An automated pipeline and agent skill for generating vertical short-form video highlights from live streams and long-form video files.
- ## Features
- - **Multimodal Peak Detection**: Combines audio loudness analysis with computer vision frame motion variance to find peak action moments.
- - **Dynamic Clip Durations**: Adjusts clip lengths between 30 and 75 seconds depending on action continuity.
- - **Vertical 9:16 Video Synthesis**:
- - Stacked layout: Streamer facecam cropped to the top third, gameplay tracking on the bottom two thirds.
- - Landscape fit: Center gameplay with dynamically blurred background padding.
- - Smooth audio mixing with background music ducking.
- - **Thumbnail Generation**: Automated cover frame extraction with color grading, bold typography, and safe zone constraints for mobile social platforms.
- - **Social Media Publishing**: Multi-platform publishing support via social media APIs.
- ## Quick Start
- ```bash
- # 1. Install dependencies
- python3 -m venv .venv
- source .venv/bin/activate
- pip install -r requirements.txt
- # 2. Configure settings
- cp config.example.json config.json
- # 3. Run clipper
- python stream_clipper.py --file input.mp4 --count 5
- ```
- ## Repository Structure
- - `stream_clipper.py`: Main highlight detection and video synthesis script.
- - `thumbnail_engine.py`: Standalone thumbnail generation tool.
- - `zernio_publish.py`: Cross-platform publishing integration.
- - `clipper_config.py`: Configuration schema and loader.
- - `skills/stream-auto-clipper/`: Agent skill instructions.
- ## Acknowledgements & Credits
- This project builds upon ideas and techniques explored in several open-source projects:
- - **[GTA-Auto-Clipper](https://github.com/AnIntellectualBeing/GTA-Auto-Clipper)** by AnIntellectualBeing: Live stream ingest pipelines and initial audio chunking architectures.
- - **[neonclipping](https://github.com/iamajmeena/neonclipping)** by iamajmeena: Stacked vertical video layout patterns and corner facecam detection techniques.
- - **[youtube-instagram-auto-uploader](https://github.com/Abhinavkumar-07/youtube-instagram-auto-uploader)** by Abhinavkumar-07: Reference patterns for cross-platform social media dispatch.
- - **[OpenCV Model Zoo](https://github.com/opencv/opencv_zoo)**: The lightweight YuNet ONNX face detection model.
- ## License
- MIT
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.