🎬 AI Video Automation

Fully automated YouTube Shorts generation with AI - From text prompt to published video in minutes.

---

✨ Features

🎯 Complete Pipeline

• AI Script Generation - Uses Perplexity AI for engaging, factual scripts
• Text-to-Speech - Google Cloud TTS with natural Neural2 voices
• AI Image Generation - Pollinations.ai (100% FREE, no API key)
• Stock Videos - Pexels integration for B-roll
• Video Rendering - FFmpeg with transitions, captions, and effects
• Auto Upload - Direct YouTube Shorts publishing

🖥️ Modern Dashboard

• Beautiful Next.js 14 frontend with dark mode
• Real-time video generation progress
• API key management with rate limiting
• Usage analytics and cost tracking
• User authentication (JWT + Sessions)

🤖 MCP Integration

• Model Context Protocol server for AI agents
• Claude Desktop compatible
• Full API access through natural language

💰 Cost Efficient

Service	Cost per Video
Perplexity AI	~$0.02
Google TTS	~$0.01
Pexels	FREE
Pollinations AI	FREE
Total	~$0.03/video

---

🚀 Quick Start

Prerequisites

• Node.js 20+
• pnpm 10.28.0+ (required - npm not supported)
• PostgreSQL 16+
• FFmpeg (for video rendering)

# Install pnpm
npm install -g pnpm

# Install FFmpeg (macOS)
brew install ffmpeg

# Install FFmpeg (Ubuntu)
sudo apt install ffmpeg

Installation

# Clone the repository
git clone https://github.com/aayushbaluni/Video-Automation-Creation.git
cd Video-Automation-Creation

# Install dependencies
cd backend && pnpm install
cd ../frontend && pnpm install
cd ..

# Configure environment
cp backend/env.template backend/.env
# Edit backend/.env with your API keys

# Setup database
cd backend
pnpm run db:migrate

# Start everything
cd ..
./start-local.sh

Opens:

• Frontend Dashboard: http://localhost:3000
• Backend API: http://localhost:8000
• API Health: http://localhost:8000/api/v1/health

---

⚙️ Configuration

Copy backend/env.template to backend/.env and configure:

Required

Variable	Description	Get it from
DATABASE_URL	PostgreSQL connection	Your PostgreSQL instance
JWT_SECRET	Auth secret (32+ chars)	openssl rand -hex 32
PERPLEXITY_API_KEY	Script generation	perplexity.ai
GOOGLE_CLOUD_TTS_API_KEY	Text-to-speech	Google Cloud Console
PEXELS_API_KEY	Stock videos	pexels.com/api

Optional

Variable	Description
YOUTUBE_*	YouTube upload (OAuth)
AWS_*	S3 video storage
SMTP_*	Email verification
HUGGINGFACE_TOKEN	Additional AI images

---

📁 Project Structure

Video-Automation-Creation/
├── backend/                 # Node.js/Express/TypeScript API
│   ├── src/
│   │   ├── api/            # REST API routes
│   │   ├── mcp/            # MCP server for AI agents
│   │   ├── pipeline/       # Video generation pipeline
│   │   ├── services/       # External service integrations
│   │   └── db/             # Database migrations
│   └── env.template        # Environment template
├── frontend/               # Next.js 14 React dashboard
│   └── src/
│       ├── app/            # App router pages
│       ├── components/     # React components
│       └── lib/            # Utilities
├── documentation/          # Project documentation
├── start-local.sh          # Start all services
└── stop-local.sh           # Stop all services

---

📋 Available Commands

Backend (backend/)

pnpm run dev:api       # Start API server (development)
pnpm run dev:mcp       # Start MCP server for Claude
pnpm run db:migrate    # Run database migrations
pnpm run db:seed       # Seed initial data
pnpm run build         # Build for production
pnpm run generate      # CLI: Generate video

Frontend (frontend/)

pnpm run dev           # Start development server
pnpm run build         # Build for production
pnpm run lint          # Run linter

---

🔌 API Usage

Authentication

# Login to get session token
curl -X POST http://localhost:8000/api/v1/auth/login \
  -H "Content-Type: application/json" \
  -d '{"email": "user@example.com", "password": "your-password"}'

Generate Video

# Start video generation
curl -X POST http://localhost:8000/api/v1/pipeline/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "topic": "5 Amazing Facts About Space",
    "style": "educational",
    "duration": 60
  }'

Check Job Status

curl http://localhost:8000/api/v1/pipeline/jobs/JOB_ID \
  -H "Authorization: Bearer YOUR_API_KEY"

See API Documentation for full API reference.

---

🤖 MCP Integration (Claude Desktop)

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "video-automation": {
      "command": "pnpm",
      "args": ["run", "dev:mcp"],
      "cwd": "/absolute/path/to/Video-Automation-Creation/backend",
      "env": {
        "API_KEY": "your-api-key-here"
      }
    }
  }
}

Then ask Claude: "Generate a 60-second video about AI trends in 2026"

---

🔒 Security

• ✅ JWT authentication with refresh tokens
• ✅ API key management with scoped permissions
• ✅ Rate limiting per key/IP
• ✅ Email verification
• ✅ Password hashing (bcrypt)
• ✅ CORS configuration
• ✅ Helmet security headers
• ✅ Input validation (Zod schemas)

---

🛠️ Tech Stack

Layer	Technology
Backend	Node.js 20, TypeScript, Express.js
Frontend	Next.js 14, React 18, Tailwind CSS
Database	PostgreSQL 16
Video	FFmpeg
AI	Perplexity, Google TTS, Pollinations.ai
Storage	AWS S3 (optional)
Package Manager	pnpm 10.28.0

---

🐛 Troubleshooting

Port Already in Use

./stop-local.sh && ./start-local.sh

Database Connection Failed

# macOS
brew services start postgresql@16

# Or check if running
pg_isready

FFmpeg Not Found

# macOS
brew install ffmpeg

# Ubuntu/Debian
sudo apt install ffmpeg

# Verify
ffmpeg -version

"pnpm: command not found"

npm install -g pnpm
# OR
brew install pnpm

---

🤝 Contributing

1. Fork the 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. Open a Pull Request

Development Guidelines

• Use pnpm exclusively (not npm or yarn)
• Follow TypeScript strict mode
• Write meaningful commit messages
• Add tests for new features
• Update documentation as needed

---

📄 License

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

---

🙏 Acknowledgments

• Perplexity AI - Script generation
• Google Cloud TTS - Text-to-speech
• Pollinations.ai - Free AI image generation
• Pexels - Free stock videos
• FFmpeg - Video processing

---

📊 Project Status

Component	Status
Backend API	✅ Production Ready
Frontend Dashboard	✅ Production Ready
MCP Server	✅ Complete
Documentation	✅ Complete
Tests	🚧 In Progress

---

Ready to generate videos? Run ./start-local.sh and visit http://localhost:3000 🚀