jiang-clips  by ayush-that

AI-powered YouTube to viral clip generator

Created 3 weeks ago

New!

284 stars

Top 92.1% on SourcePulse

GitHubView on GitHub
Project Summary

Automated pipeline that converts long-form YouTube videos into viral-ready vertical clips. This project addresses the challenge of efficiently repurposing video content for short-form platforms by leveraging AI for content selection and automated video processing. It is targeted at content creators, social media managers, and anyone looking to maximize the reach of their YouTube videos across platforms like TikTok, Instagram Reels, and YouTube Shorts, offering a significant time-saving benefit.

How It Works

The core of the pipeline orchestrates AI-driven analysis and video manipulation. It uses Google Gemini to understand video content, identify engaging segments, and generate summaries or key moments suitable for short clips. FFmpeg is integrated for essential video processing tasks, including cutting, transcoding, and reformatting videos into a vertical aspect ratio (defaulting to 1080x1920). The system is designed for modularity, with distinct modules for pipeline orchestration, AI processing, and video rendering, allowing for potential future extensions.

Quick Start & Requirements

  • Primary install / run command: Install dependencies using bun install. Run the pipeline with bun run src/index.ts pipeline for single videos or bun run src/index.ts batch for channel processing.
  • Non-default prerequisites and dependencies: Bun runtime, FFmpeg (required for video processing), and a Google Gemini API Key (set as the GEMINI_API_KEY environment variable).
  • Configuration: Key environment variables include GEMINI_API_KEY (required), WHISPER_MODEL (default: base), MAX_PARALLEL_CLIPS (default: 3), SILENCE_THRESHOLD_DB (default: -35), OUTPUT_WIDTH (default: 1080), and OUTPUT_HEIGHT (default: 1920).

Highlighted Details

  • Automated extraction of short-form clips from long-form YouTube videos.
  • Generates viral-ready vertical video formats suitable for social media.
  • Supports batch processing of entire YouTube channels.
  • Configurable parameters for AI models, clip processing, and video output dimensions.

Maintenance & Community

The provided project description does not include details on notable contributors, sponsorships, community channels (e.g., Discord, Slack), or a public roadmap.

Licensing & Compatibility

The README does not specify a software license. Consequently, its terms for commercial use or integration into closed-source projects remain undetermined.

Limitations & Caveats

Operation requires a Google Gemini API key, which incurs costs. FFmpeg must be installed and accessible on the system. The pipeline is tightly coupled to the specified AI and video processing tools, potentially limiting flexibility for alternative service integrations without code modification.

Health Check
Last Commit

3 weeks ago

Responsiveness

Inactive

Pull Requests (30d)
1
Issues (30d)
3
Star History
285 stars in the last 21 days

Explore Similar Projects

Feedback? Help us improve.