---
title: "LiveKit"
description: "Build voice, video, and physical AI agents."
canonical: "https://livekit.com/"
---

# LiveKit

Build voice, video, and physical AI agents.

An open source framework and developer platform for building, testing, deploying, scaling, and
observing agents in production.

## Trusted by

Powering billions of calls in production for companies including OpenAI, Skydio, Nvidia,
Salesforce, Oracle, Spotify, Decagon, Cresta, and Coursera.

## Built for every kind of agent

- **Voice AI** — OpenAI built ChatGPT's Advanced Voice on LiveKit Cloud, serving millions of users
  every day. Run millions of concurrent calls with automatic turn detection and interruption
  handling.
- **Video AI** — Verkada uses LiveKit Cloud for 24/7 video security and access control across more
  than 30,000 organizations, with high-concurrency AI inference and ultra-low-latency streaming.
- **Robotics** — Skydio uses LiveKit for remote observation and teleoperation of its drones,
  processing sensor data and commands in realtime.

## Quickly build voice agents

- [Voice AI quickstart](https://docs.livekit.io/agents/start/voice-ai/) — build a simple voice
  agent with Python or Node.js in under 10 minutes.
- [Voice agent starter apps](https://docs.livekit.io/agents/start/frontend/#starter-apps) — bring
  your agent to life through a web or mobile app.
- [Telephony integration](https://docs.livekit.io/agents/start/telephony/) — make or take phone
  calls with your agent.
- [Deploy to LiveKit Cloud](https://docs.livekit.io/agents/ops/deployment/) — run agents on
  LiveKit's global realtime infrastructure.

## The complete stack for Voice AI

- Open source framework to build and test agents.
- Inference gateway to access TTS, LLM, and STT models.
- Cloud platform for deploying and scaling agents.
- Phone numbers and SIP integrations for telephony.
- Full-stack observability for every agent session.

[Explore the LiveKit Cloud platform](https://livekit.com/products/agent-platform)

## How it works

1. A user speaks to the agent through an app, browser, or phone call.
2. Speech streams from the device to the agent over WebRTC through LiveKit's global edge network,
   with under 100ms latency.
3. The agent runs your business logic, built on the open source framework and deployed on your own
   infrastructure or LiveKit Cloud.
4. The agent responds, streamed back over LiveKit's global network.

## Enterprise-grade infrastructure

GDPR, SOC 2 Type 2, and HIPAA compliant.

- 99.99% uptime
- Under 100ms global latency
- 300,000+ developers
- 3,000,000,000+ calls annually

## Chosen by innovators, from startups to industry giants

> "Reliability and accelerating time to production often seem at odds, but with LiveKit's Agent
> Platform, we achieved both!" — Walker Ward, Principal Software Engineer, Podium

> "We recently moved from a homegrown WebSocket stack to LiveKit Cloud." — Zexia Zhang, CTO, Retell
> AI

[View all customers](https://livekit.com/customers)

## Ready to build?

Start building a voice AI agent with a free account — no credit card required, 1,000 free agent
session minutes monthly. Reach out if you're interested in custom pricing.

- [Start building](https://cloud.livekit.io)
- [Pricing](https://livekit.com/pricing.md)
- [Contact sales](https://livekit.com/contact-sales)