Skip to main content
close
Product

Agents on
LiveKit Cloud

Built for production-grade usage, LiveKit Cloud takes care of the full agent lifecycle for AI voice agents, from deployment to scaling to serving at the edge.

Illustration of isometric grid with Agents on LiveKit Cloud elements
300,000+ developers
Billions of calls annually
300+ AI model integrations

Reliable, realtime, agent runtime

LiveKit Cloud handles the operational challenges of running voice agents in production at scale.

Load balancing

Designed for long-lived agent sessions, LiveKit Cloud auto-scales based on demand and places sessions by effective load to minimize end-to-end latency and jitter.

LiveKit Cloud auto-scales based on demand and places sessions by effective load to minimize end-to-end latency and jitter.

Version control

Deploy new agent versions without downtime. LiveKit Cloud gracefully drains agent servers during updates. Roll back to a previous version with a single click or CLI command.

A screenshot of LiveKit CLI commands for creating an agent.

Agent telemetry

Monitor and analyze agent deployments with realtime dashboards. Debug sessions with full-stack agent insights, including recordings, transcripts, traces, and logs.

A map of the world with dots representing LiveKit Cloud data center locations.

Global network

Agents on LiveKit Cloud are deployed on the same infrastructure as LiveKit’s global edge network for workloads that need high availability, horizontal scalability, and low latency.

Image of a globe with dots representing our data center locations.
The LiveKit Platform

Build, run, and observe
agents with LiveKit Cloud

Our end-to-end platform powers enterprise-grade voice AI
for customer support at global scale.

Open AI
Salesforce
Deutsche Telekom
Zocdoc
Coursera
xAI
Headspace
Oracle
Assort Health
Spotify
Explore the full platform

FAQs

How do I get started with agents on LiveKit Cloud?
Sign up for a LiveKit Cloud account, use the LiveKit Agents SDKs or Agent Builder to build an agent, then deploy to LiveKit Cloud using the CLI or with a single click in the dashboard. To learn more, visit our docs.
Where can I deploy agents on LiveKit Cloud?
Agents can be deployed to three regions on LiveKit Cloud: us-east (Virginia, USA), eu-central (Frankfurt, Germany), and ap-south (Mumbai, India), with more regions coming soon. To learn more, visit our docs.
What are the quotas or limits for agents on LiveKit Cloud?
Each LiveKit Cloud plan includes a monthly quota on agent session minutes (billed at $0.01/minute) and a limit on the number of unique agent deployments. To learn more, visit our pricing page and our docs.
How much does it cost to run agents on LiveKit Cloud?
Agents deployed to LiveKit Cloud are billed for the time they are in a session, referred to as agent session minutes. Each LiveKit plan includes a monthly quota of agent session minutes. For more details, visit our pricing page.
Can I self-host agents built with LiveKit?
The LiveKit Agents framework is completely open source and available to run locally or host on your own infrastructure. LiveKit Cloud is the best way to run LiveKit agents in production, with fully managed agent deployments, built-in observability and dashboards, and ultra low-latency global media transport.

Sign up for LiveKit Cloud here, or refer to our docs on how to run LiveKit’s media server locally or deploy LiveKit Agents in a custom environment.
How can I debug agents deployed to LiveKit Cloud?
Use Agent Observability to debug and troubleshoot sessions. View turn-by-turn playbacks, synchronized transcripts and trace spans, and full stack logs for each agent conversation.

Ready to build?

Start building a voice AI agent with a free account. Reach out to us if you're interested in custom pricing.

No credit card required • 1,000 free agent session minutes monthly