Build, run, and observe AI agents
LiveKit is a developer platform for voice, video, and physical AI. Build agents with our open source SDKs, deploy them across a global network of data centers, and monitor them in production with realtime observability.

Your agent, your code.
With LiveKit, you control how your AI agent sounds, how it behaves, and what actions it takes. When you’re ready to deploy to production, LiveKit Cloud takes care of the runtime infrastructure, from version control and dispatching to autoscaling and turn-by-turn telemetry.
Built for the full agent development lifecycle
Voice agents are fundamentally different from web and mobile apps. They listen, think, and respond in real time, maintaining context throughout the conversation. LiveKit's infrastructure is designed to facilitate multimodal, low-latency, high-volume conversations between agents and humans.
1from dotenv import load_dotenv23from livekit import agents, rtc4from livekit.agents import AgentServer,AgentSession, Agent, room_io5from livekit.plugins import noise_cancellation, silero6from livekit.plugins.turn_detector.multilingual import MultilingualModel78load_dotenv(".env.local")910class Assistant(Agent):11def __init__(self) -> None:12super().__init__(13instructions="""You are a helpful voice AI assistant.14You eagerly assist users with their questions by providing information from your extensive knowledge.15Your responses are concise, to the point, and without any complex formatting or punctuation including emojis, asterisks, or other symbols.16You are curious, friendly, and have a sense of humor.""",17)1819server = AgentServer()2021@server.rtc_session(agent_name="my-agent")22async def my_agent(ctx: agents.JobContext):23session = AgentSession(24stt="deepgram/nova-3:multi",25llm="openai/gpt-4.1-mini",26tts="cartesia/sonic-3:9626c31c-bec5-4cca-baa8-f8ba9e84c8bc",27vad=silero.VAD.load(),28turn_detection=MultilingualModel(),29)3031await session.start(32room=ctx.room,33agent=Assistant(),34room_options=room_io.RoomOptions(35audio_input=room_io.AudioInputOptions(36noise_cancellation=lambda params: noise_cancellation.BVCTelephony() if params.participant.kind == rtc.ParticipantKind.PARTICIPANT_KIND_SIP else noise_cancellation.BVC(),37),38),39)4041await session.generate_reply(42instructions="Greet the user and offer your assistance."43)444546if __name__ == "__main__":47agents.cli.run_app(server)
Build
Build voice agents with open source SDKs and complete developer control. Write agent logic directly in code, test it against real scenarios, and iterate without vendor lock-in.

Run
Deploy agents to a global network built for production-grade reliability and performance. LiveKit Cloud handles the realtime infrastructure, routing, and scaling so your team can focus on the product, not the ops.

Observe
Gain end-to-end visibility into every conversation. Track latency, quality, and outcomes in real time, then use those insights to continuously improve your agents.
Features
Conversation handling
Built-in models for noise cancellation, end-of-turn detection, and interruption handling
Native client SDKs
Ship voice agents to any platform, including web, iOS, Android, and microcontrollers
Coding agent resources
Turn Claude Code, Cursor, Codex, or Gemini into a LiveKit expert
Global cloud network
Connect to users with ultra-low latency on a distributed mesh of media servers
Elastic scaling
Serve thousands of concurrent voice agent sessions at any given time
SIP support
Connect agents to any phone number for inbound and outbound calling
Conversation quality
Built-in models for noise cancellation, turn detection, and interruption handling
Realtime metrics
Subscribe to agent metric events or forward them to external services
Recording exports
Send audio and video recordings directly to a storage provider
Get started with LiveKit Cloud
Build your first voice agent on LiveKit with a coding assistant, Agent Builder, or Agents SDKs.

Built for production workloads at scale
LiveKit Cloud is architected to meet the security, compliance, and operational requirements of enterprise teams, including end-to-end encryption, role-based access controls, and support plans.
“LiveKit enables us to very granularly fine-tune our agent code for every workflow and use any model provider. No other platform gives us this level of control.”
Jeffery Liu Founder & Co-CEO, Assort Health
FAQs
What is LiveKit Cloud?
How do I get started with LiveKit Cloud?
Is LiveKit secure and compliant?
Can I use my own AI models with LiveKit?
Yes. LiveKit Inference supports over 50 AI models out-of-the-box, no API keys or additional configuration required. In addition, the LiveKit Agents framework supports another 200+ models via plugins, including an OpenAI plugin that supports most models compatible with the OpenAI API format.
For models not currently available via LiveKit Inference or a plugin, the LiveKit Agents plugin framework is extensible and community-driven. We welcome contributions for new STT, LLM, and TTS plugins. To learn more about using AI models with LiveKit, visit our docs.
