Pipecat CLI

March 27, 2026 · View on GitHub

A complete toolkit for building, deploying, and monitoring Pipecat AI voice agents.

  • Scaffold new projects with pipecat init
  • Deploy to production with pipecat cloud
  • Monitor live bots with pipecat tail

Requirements

  • Python 3.10+

Installation

uv tool install pipecat-ai-cli

This installs the CLI globally. If you don't have uv, you can also use pipx install pipecat-ai-cli.

Tip: All commands can use either pipecat or the shorter pc alias.

Optional: Install Tail Dashboard

To use the pipecat tail monitoring dashboard, install with the tail extra:

uv tool install "pipecat-ai-cli[tail]"

Create a New Project

Create a new quickstart Pipecat project with default settings:

pipecat init quickstart

Or create a new Pipecat project interactively:

pipecat init

The CLI will guide you through selecting:

  • Bot type and client framework
  • Transport provider (Daily, Twilio, etc.)
  • Pipeline mode (Cascade or Realtime)
  • AI services (STT, LLM, TTS)
  • Optional features and deployment target

Generated Project Structure

mybot/
├── server/                  # Python bot server
│   ├── bot.py              # Main bot implementation
│   ├── pyproject.toml      # Python dependencies
│   ├── .env.example        # Environment variables template
│   ├── Dockerfile          # Container image (if cloud enabled)
│   └── pcc-deploy.toml     # Deployment config (if cloud enabled)
├── client/                  # Web client (if generated)
│   ├── src/
│   ├── package.json
│   └── ...
├── .gitignore
└── README.md                # Project setup instructions

Deploy to Pipecat Cloud

Deploy and manage your bot in production with Pipecat Cloud:

# Authenticate
pipecat cloud auth login

# Deploy
pipecat cloud deploy

# Manage deployments
pipecat cloud agent list
pipecat cloud agent logs <agent-name>

Cloud commands provide:

  • 🔐 Authentication and credential management
  • 🐳 Docker build and registry integration
  • 🚀 One-command deployment
  • 📊 Agent status and log monitoring
  • 🔧 Runtime configuration management

Note: When you enable "Deploy to Pipecat Cloud" during project creation, the necessary deployment config files are automatically generated.

Learn more in the Pipecat Cloud documentation.

Monitor Your Bot

Use the built-in Tail dashboard to monitor your bot in real-time:

# Connect to local bot (default: ws://localhost:9292)
pipecat tail

# Connect to remote session
pipecat tail --url wss://your-bot.example.com

Note: The tail command requires the optional tail extra. Install with uv tool install "pipecat-ai-cli[tail]" if not already installed.

Tail provides:

  • 📜 Real-time system logs
  • 💬 Live conversation tracking
  • 🔊 Audio level monitoring
  • 📈 Service metrics and usage stats

📚 Next steps