Professional voice analytics and observability for AI agents. Monitor, analyze, and improve your voice AI applications with beautiful dashboards and actionable insights.
🚀 Get Started • 📊 Live Demo • 📖 Documentation • ⭐ Star on GitHub
- 🔍 Real-time Monitoring - Track every voice interaction with comprehensive analytics
- 💰 Cost Tracking - Monitor STT, TTS, and LLM costs across all providers
- ⚡ Performance Metrics - Analyze latency, response times, and quality scores
- 🎯 Multi-Project Support - Organize and compare multiple voice AI applications
- 📈 Beautiful Dashboards - Intuitive visualizations with customizable views
- 🔒 Privacy-First - Self-host option with complete data control
- 📤 Data Export - Export analytics to CSV for further analysis
- 🔧 Easy Integration - One-line SDK integration with LiveKit agents
- 🌐 Open Source - Full transparency and community-driven development
Get started in under 2 minutes with our hosted platform:
- Sign up at Whispey Voice Analytics Dashboard
- Get your Agent ID from the dashboard
- Generate your API Key from your account settings
Create a .env file in your project root:
# Whispey Voice Analytics
WHISPEY_API_KEY=your_whispey_api_key_here# Install the SDK
pip install whispeyfrom dotenv import load_dotenv
from whispey import LivekitObserve
# Load environment variables
load_dotenv()
# Initialize observability with your Agent ID
whispey = LivekitObserve(
agent_id="your-agent-id-from-dashboard",
apikey=os.getenv("WHISPEY_API_KEY")
)
# Wrap your LiveKit session
session = AgentSession(...)
session_id = whispey.start_session(session, phone_number="+1234567890")
# Ensure data is exported on shutdown
async def whispey_shutdown():
await whispey.export(session_id)
ctx.add_shutdown_callback(whispey_shutdown)
await session.start(...)📊 View your analytics: https://whispey.xyz/
For complete control over your data, deploy Whispey on your own infrastructure:
# Clone and setup
git clone https://github.com/PYPE-AI-MAIN/whispey
cd whispey
npm install
# Setup database (choose one method)
# Option 1: Direct connection (recommended)
psql -h db.YOUR_PROJECT_REF.supabase.co -p 5432 -U postgres -d postgres -f setup-supabase.sql
# Option 2: Copy SQL to Supabase dashboard
# Copy setup-supabase.sql content to Supabase SQL Editor
# Configure environment
cp .env.example .env.local
# Edit .env.local with your Supabase and Clerk credentials
# Run development server
npm run dev🔧 Detailed setup guide: Self-hosting Documentation
Whispey consists of three main components:
- Python SDK - Lightweight library for data collection
- Dashboard - Next.js web application for analytics visualization
- Backend - Supabase for data storage and real-time updates
| Metric | Description | Providers |
|---|---|---|
| Latency | Response times for each component | All STT/TTS/LLM providers |
| Costs | Token usage and billing across services | OpenAI, Anthropic, Google, Azure |
| Quality | Transcription accuracy, response relevance | Custom scoring algorithms |
| Usage | Call volume, session duration, user patterns | Built-in analytics |
- Production Monitoring - Keep voice AI applications running smoothly
- Cost Optimization - Identify expensive operations and optimize spending
- Quality Assurance - Review call transcripts and agent responses
- Performance Debugging - Diagnose latency issues and bottlenecks
- Business Intelligence - Generate reports for stakeholders
- Frontend: Next.js 14, React, Tailwind CSS, shadcn/ui
- Backend: Supabase (PostgreSQL + Real-time)
- Authentication: Clerk.dev
- SDK: Python 3.8+, asyncio
- Analytics: Custom metrics engine
- Deployment: Vercel, Docker support
- 🚀 Getting Started Guide
- 🔧 SDK Reference
- 🏠 Self-hosting Guide
- 📊 Dashboard Tutorial
- 🔌 API Documentation
- ❓ FAQ
- GitHub Examples Repository: https://github.com/PYPE-AI-MAIN/whispey-examples
- Live Examples: Check out real-world implementations and use cases
We welcome contributions from the community! Here's how to get started:
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Make your changes and add tests
- Run the test suite:
npm test - Commit your changes:
git commit -m 'Add amazing feature' - Push to the branch:
git push origin feature/amazing-feature - Open a Pull Request
Please read our Contributing Guidelines and Code of Conduct before contributing.
# Clone the repository
git clone https://github.com/PYPE-AI-MAIN/whispey
cd whispey
# Install dependencies
npm install
# Set up environment
cp .env.example .env.local
# Start development server
npm run dev# Navigate to SDK directory
cd sdk
# Install Python dependencies
pip install -r requirements.txt
# Install in development mode
pip install -e .Security is a top priority for Whispey. We implement:
- End-to-end encryption for data in transit
- SOC 2 compliant infrastructure partners
- Regular security audits and dependency updates
- Privacy-first design with optional self-hosting
Found a security issue? Please email security@whispey.ai instead of opening a public issue.
- Multi-language SDK support (JavaScript, Go, Rust)
- Advanced ML-powered insights and anomaly detection
- Slack/Discord integrations for alerts
- GraphQL API
- Mobile app for monitoring on-the-go
- Custom webhook integrations
- 🐛 Bug Reports: GitHub Issues
- 💡 Feature Requests: GitHub Discussions
- 📧 Email: deepesh@pypeai.com
- 📚 Examples: GitHub Examples Repository
Need enterprise features like SSO, custom deployments, or dedicated support?
Contact us: dhruv@pypeai.com
This project is licensed under the MIT License - see the LICENSE file for details.
- Built with ❤️ by the PYPE team
- Inspired by the observability tools from Datadog, New Relic, and Honeycomb
- Special thanks to the LiveKit community for their amazing real-time infrastructure
⭐ Star us on GitHub if Whispey helps your voice AI applications!