LiveKit Academy

Learn to build voice AI
that actually works.

Project-based courses from architecture to production. Built on the only open-source platform where AI, humans, and phones share one room.

Why LiveKit

The only platform where AI, humans, and phones share one room.

WebRTC-native

Sub-100ms latency for voice AI. Not WebSocket buffering — real UDP transport with adaptive bitrate.

Room architecture

Humans, AI agents, and SIP callers in one session. Same primitives, same SDKs, infinite combinations.

Fully open source

Self-host everything. Apache 2.0 licensed. Same APIs whether you use Cloud or your own infrastructure.

12+ SDKs

Web, iOS, Android, Flutter, React Native, Unity, C++, Rust, Python, Node.js, Go, ESP32.

Featured Course
Beginner4.5 hours · 13 chapters

Voice AI Foundations

Build a dental clinic AI receptionist from scratch

Build a dental clinic receptionist that greets callers, answers FAQs, checks appointment availability via tool calls, books appointments, and handles edge cases. Deployed to LiveKit Cloud and testable from Playground.

Start this course

Chapters

  1. 01What is voice AI? Why WebRTC matters
  2. 02Project setup & your first agent
  3. 03Understanding AgentSession
  4. 04Writing great agent instructions
  5. 05Adding your first tool: check availability
  6. 06RunContext, state & the booking tool
  7. 07Noise cancellation & room configuration
  8. 08Testing your agent
  9. 09Turn detection deep dive
  10. 10Conversation context & multi-turn state
  11. 11Beyond audio: the data plane
  12. 12Deploy to LiveKit Cloud
  13. 13Polish & production readiness