Get Voice Summary running in 5 minutes!
git clone https://github.com/yourusername/voicesummary.git
cd voicesummary
./setup.sh# Terminal 1: Start backend
./start_backend.sh
# Terminal 2: Start frontend
./start_frontend.sh- Frontend: http://localhost:3000
- API Docs: http://localhost:8000/docs
That's it! 🎉
- Python 3.9+: Download here
- Node.js 18+: Download here
- PostgreSQL: Install guide
- AWS S3 Bucket: Create here
# Check Python
python3 --version # Should show 3.9+
# Check Node.js
node --version # Should show 18+
# Check PostgreSQL
psql --version # Should show PostgreSQL versioncp env.example .env# Required: Database
DATABASE_URL=postgresql://username:password@localhost:5432/voicesummary
# Required: AWS S3
AWS_ACCESS_KEY_ID=your_access_key
AWS_SECRET_ACCESS_KEY=your_secret_key
S3_BUCKET_NAME=your-bucket-name
AWS_REGION=us-east-1createdb voicesummary# Health check
curl http://localhost:8000/health
# Should return: {"status": "healthy"}curl -X POST "http://localhost:8000/api/calls/" \
-H "Content-Type: application/json" \
-d '{
"call_id": "test_001",
"transcript": {
"turns": [
{
"role": "AGENT",
"content": "Hello! How can I help you today?",
"timestamp": "2025-01-01T10:00:00Z"
}
]
},
"timestamp": "2025-01-01T10:00:00Z"
}'- Open http://localhost:3000
- You should see your test call listed
# Install Python 3.9+
# macOS: brew install python@3.9
# Ubuntu: sudo apt install python3.9
# Windows: Download from python.org# Install Node.js 18+
# macOS: brew install node
# Ubuntu: curl -fsSL https://deb.nodesource.com/setup_18.x | sudo -E bash -
# Windows: Download from nodejs.org# Start PostgreSQL service
# macOS: brew services start postgresql
# Ubuntu: sudo systemctl start postgresql
# Windows: Start from Services app
# Create database
createdb voicesummary# Verify your .env file has correct AWS credentials
# Test with AWS CLI
aws sts get-caller-identity# Kill process using port 8000
lsof -ti:8000 | xargs kill -9
# Kill process using port 3000
lsof -ti:3000 | xargs kill -9- FastAPI server serving the API
- PostgreSQL database storing call data
- S3 integration for audio file storage
- Audio processing with AI analysis
- Next.js app with React components
- Real-time timeline visualization
- Audio player for call playback
- Transcript viewer with enhanced data
- Full Documentation: README.md
- API Reference: http://localhost:8000/docs
- Code Examples: See
examples/folder
- Add your own audio processing in
app/utils/ - Extend the frontend in
frontend/components/ - Modify database schema in
app/models.py
- Production setup: See README.md#deployment
- Docker deployment: See README.md#docker
- GitHub Issues: Create an issue
- Discussions: Join the conversation
- Documentation: Check the main README
Happy voice analyzing! 🎤✨