AI Video Generator

A full-stack autonomous AI app that generates short narrated videos from text prompts using MetaGPT, ElevenLabs, DALL·E, and FFmpeg.

Features

• Story Generation: Uses MetaGPT to create engaging stories from text prompts
• Voice Synthesis: ElevenLabs API for high-quality narration
• Image Generation: OpenAI DALL·E for scene visualization
• Video Assembly: FFmpeg for professional video creation
• Web Interface: React frontend with real-time progress tracking
• Persistent Storage: Supabase for job management and video storage

Project Structure

AI Project/
├── agents/                 # MetaGPT agents
│   ├── storywriter.py     # Story generation
│   ├── narrator.py        # Voice synthesis
│   ├── visual.py          # Image generation
│   └── editor.py          # Video assembly
├── tools/                  # API wrappers
│   ├── elevenlabs_client.py
│   ├── openai_client.py
│   ├── ffmpeg_utils.py
│   └── supabase_client.py
├── backend/
│   └── api/
│       └── app.py         # FastAPI backend
├── frontend/              # React frontend
│   ├── src/
│   │   ├── App.jsx
│   │   ├── main.jsx
│   │   └── index.css
│   ├── package.json
│   └── vite.config.js
├── main.py                # Standalone pipeline
├── requirements.txt       # Python dependencies
└── .gitignore            # Git ignore rules

Prerequisites

Before you begin, ensure you have the following installed:

• Python 3.9+ (but less than 3.12)
• Node.js 16+ and npm
• FFmpeg (for video processing)
• Git (for cloning the repository)

Quick Start

1. Clone the Repository

git clone <your-repository-url>
cd AI-Project

2. Install MetaGPT

Option A: Install via pip (Recommended)

pip install metagpt

Option B: Install from source (if you need the latest version)

git clone https://github.com/geekan/MetaGPT.git
cd MetaGPT
pip install -e .
cd ..

3. Install Python Dependencies

pip install -r requirements.txt

4. Install Frontend Dependencies

cd frontend
npm install
cd ..

5. Set Up Environment Variables (Optional)

Create a .env file in the root directory:

# API Keys (optional - mock mode available)
OPENAI_API_KEY=your_openai_key
ELEVENLABS_API_KEY=your_elevenlabs_key
SUPABASE_URL=your_supabase_url
SUPABASE_ANON_KEY=your_supabase_key

6. Install FFmpeg

Windows:

# Download from https://ffmpeg.org/download.html
# Add to PATH

macOS:

brew install ffmpeg

Linux:

sudo apt update
sudo apt install ffmpeg

Verify FFmpeg installation:

ffmpeg -version

Running the Application

Option 1: Standalone Pipeline

Test the core pipeline with a hardcoded prompt:

python main.py

Option 2: Full Web Application

Start the Backend

cd backend/api
uvicorn app:app --reload --host 0.0.0.0 --port 8000

Start the Frontend

cd frontend
npm run dev

The application will be available at:

• Frontend: http://localhost:3000
• Backend API: http://localhost:8000
• API Docs: http://localhost:8000/docs

API Endpoints

• POST /generate - Start video generation
• GET /status/{job_id} - Get job status
• GET /result/{job_id} - Get video result
• GET /download/{job_id} - Download video file

Development

Mock Mode

All API clients support mock mode for development:

• ElevenLabs: Generates silent audio files
• OpenAI DALL·E: Creates placeholder images with text
• Supabase: Uses local file storage
• FFmpeg: Requires actual FFmpeg installation

Adding Real APIs

1. Set your API keys in environment variables
2. The clients will automatically switch from mock to real mode
3. For Supabase, create a videos table with the schema from VideoMetadata

Customization

• Story Style: Modify prompts in agents/storywriter.py
• Voice: Change voice settings in tools/elevenlabs_client.py
• Image Style: Adjust DALL·E parameters in tools/openai_client.py
• Video Effects: Add FFmpeg filters in tools/ffmpeg_utils.py

Troubleshooting

Common Issues

1. FFmpeg not found: Install FFmpeg and ensure it's in your PATH
2. Import errors: Make sure you're in the project root directory
3. API rate limits: Add delays or use mock mode for development
4. CORS errors: The frontend proxy should handle this automatically
5. MetaGPT import errors: Ensure MetaGPT is properly installed

Debug Mode

Enable debug logging by setting environment variables:

export PYTHONPATH=.
export DEBUG=1

MetaGPT Configuration

If you encounter MetaGPT configuration issues:

# Initialize MetaGPT config
metagpt --init-config

# This creates ~/.metagpt/config2.yaml
# Edit the file with your API keys:
# llm:
#   api_type: "openai"
#   model: "gpt-4-turbo"
#   api_key: "YOUR_OPENAI_API_KEY"

Production Deployment

Backend (FastAPI)

# Using Gunicorn
pip install gunicorn
gunicorn app:app -w 4 -k uvicorn.workers.UvicornWorker

Frontend (React)

cd frontend
npm run build
# Serve the dist/ directory

Environment Setup

1. Set up a Supabase project for production storage
2. Configure API keys for all services
3. Set up proper CORS and security headers
4. Use a reverse proxy (nginx) for production

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

License

MIT License - see LICENSE file for details

Acknowledgments

• MetaGPT - Multi-agent framework
• ElevenLabs - Voice synthesis
• OpenAI - Image generation
• FFmpeg - Video processing
• Supabase - Backend as a service