Skip to content

A python tool that uses GPT-4, FFmpeg, and OpenCV to automatically analyze videos, extract the most interesting sections, and crop them for an improved viewing experience.

License

Notifications You must be signed in to change notification settings

eltociear/AI-Youtube-Shorts-Generator

 
 

Repository files navigation

AI Youtube Shorts Generator

AI Youtube Shorts Generator is a Python tool designed to generate engaging YouTube shorts from long-form videos. By leveraging the power of GPT-4 and Whisper, it extracts the most interesting highlights, detects speakers, and crops the content vertically for shorts. This tool is currently in version 0.1 and might have some bugs.

Youtube tutorial -> https://youtu.be/dKMueTMW1Nw

Demo Input Video

Demo Output Video

Features

  • Video Download: Given a YouTube URL, the tool downloads the video.
  • Transcription: Uses Whisper to transcribe the video.
  • Highlight Extraction: Utilizes OpenAI's GPT-4 to identify the most engaging parts of the video.
  • Speaker Detection: Detects speakers in the video.
  • Vertical Cropping: Crops the highlighted sections vertically, making them perfect for shorts.

Installation

Prerequisites

  • Python 3.7 or higher
  • FFmpeg
  • OpenCV

Steps

  1. Clone the repository:

    git clone https://github.com/SamurAIGPT/AI-Youtube-Shorts-Generator.git
    cd AI-Youtube-Shorts-Generator
  2. Install the required Python packages:

    pip install -r requirements.txt
  3. Set up the environment variables. Create a .env file in the project root directory and add your OpenAI API key:

    OPENAI_API=your_openai_api_key_here

Usage

  1. Ensure your .env file is correctly set up with your OpenAI API key.
  2. Run the main script and enter the desired YouTube URL when prompted:
    python main.py

Contributing

Contributions are welcome! Please fork the repository and submit a pull request.

License

This project is licensed under the MIT License.

Disclaimer

This is a v0.1 release and might have some bugs. Please report any issues on the GitHub Repository.

Other useful Video AI Projects

Text to Video AI

Faceless Video Generator

AI B-roll generator

About

A python tool that uses GPT-4, FFmpeg, and OpenCV to automatically analyze videos, extract the most interesting sections, and crop them for an improved viewing experience.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%