English | 简体中文

⚡ CodexReel: Where AI Meets Video Rendering

🚀 Transform Articles into Viral-Ready Video Reels with AI-Powered Precision

📖 Project Introduction

CodexReel is a next-generation AI video content engine that leverages cutting-edge multimodal LLM technology to intelligently transform ordinary articles into professionally-produced interactive dialogue videos.

✨ Key Features

• 🤖 Smart Content Understanding - Automatically extract the essence of articles and deeply understand the main theme.
• 🎭 Multi-role Dialogue - AI-driven dialogue generation makes content more vivid and engaging.
• 🔍 Smart Material Matching - Semantic-based intelligent matching of video materials.
• 🗣️ AI Voice Synthesis - Natural and smooth multi-role dubbing system.
• 🎥 Professional Video Production - Automatic editing and synthesis to create refined video content.

📂 Examples

Note: The following example videos have been edited and compressed, showing only part of the effect. Complete videos can be generated by clicking the title to view the original article.

▶️ "The Embarrassment of Being Seated at the Kids' Table in Europe"	▶️ "How Northeastern Billionaires Stay Relevant After Nezha's Success"	▶️ "Non-invasive Glucose Monitoring Devices: Making Life Easier with Technology"
11.mp4	12.mp4	14.mp4

🎯 Application Scenarios

• 📰 News Information Videos - Quickly convert hot news into short videos.
• 📚 Article Content Visualization - Make article content more expressive.
• 🎤 Podcast Content Creation - Automatically generate conversational podcasts.
• 📱 Short Video Content Production - Mass-produce high-quality short videos.
• 🎮 Game Information to Video - Video presentation of game strategies and news.

🛠️ Technology Stack

• Backend Framework: FastAPI
• Frontend Interface: Streamlit
• AI Service: OpenAI GPT API
• Voice Synthesis: Tongyi TTS
• Video Processing: FFmpeg
• Data Storage: SQLite

🚀 Quick Start

Environment Requirements

• Python 3.10+
• FFmpeg
• ImageMagick

Installation Steps

1. Clone the repository:

git clone https://github.com/chenwr727/CodexReel.git
cd CodexReel

2. Create and activate conda environment:

conda create -n url2video python=3.10
conda activate url2video

3. Install dependencies:

pip install -r requirements.txt
conda install -c conda-forge ffmpeg

Configuration

1. Copy the configuration template:

copy config-template.toml config.toml

2. Edit config.toml and configure the following necessary parameters:

• OpenAI API key
• Tongyi TTS service key
• Pexels API key
• Other optional configurations

📂 Project Structure

CodexReel/
├── api/                    # API interface module
│   ├── crud.py             # Database operations
│   ├── database.py         # Database configuration
│   ├── models.py           # Data models
│   ├── router.py           # Route definitions
│   └── service.py          # Business logic
├── schemas/                # Data model definitions
│   ├── config.py           # Configuration model
│   ├── task.py             # Task model
│   └── video.py            # Video model
├── services/               # External service integration
│   ├── material/           # Material service
│   │   ├── base.py         # Material service interface
│   │   ├── pexels.py       # Pexels video material service
│   │   └── pixabay.py      # Pixabay video material service
│   ├── tts/                # Voice synthesis service
│   │   ├── base.py         # Voice synthesis service interface
│   │   ├── dashscope.py    # DashScope voice synthesis service
│   │   ├── edge.py         # Edge voice synthesis service
│   │   └── kokoro.py       # Kokoro voice synthesis service
│   ├── llm.py              # LLM service
│   └── video.py            # Video processing service
├── utils/                  # Utility modules
│   ├── config.py           # Configuration management
│   ├── log.py              # Logging tools
│   ├── subtitle.py         # Subtitle handling
│   ├── text.py             # Text processing
│   ├── url.py              # URL handling
│   └── video.py            # Video tools
└── web.py                  # Web interface entry point

🖥️ Usage

Web Interface

1. Start the service:

python app.py

2. Launch the web interface:

streamlit run web.py --server.port 8000

Command Line Usage

Process a single URL:

python main.py https://example.com/article

🤝 Contribution Guide

Contributions are welcome! Please follow these steps:

1. Fork this repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Submit a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• NotebookLlama - Inspiration for this project
• All contributors and users