tools
LiveKit Cloud
LiveKit Cloud hosts AI voice, video, and physical-agent applications with realtime media, telephony, inference, deployment, and observability.

In inglese
LiveKit Cloud is a managed platform for building, deploying, and operating AI agents and realtime audio, video, and data applications. It includes agent hosting, Agent Builder, built-in inference, phone numbers, global media transport, analytics, logs, and session observability.
Developers, product teams, and enterprises use it for voice agents, video applications, telephony workflows, livestreaming, and physical-agent systems. The service is usage-based beyond plan allowances, and model inference, telephony, data transfer, and media services may incur additional charges.
Features
- Deploy and host AI agents with managed scaling, builds, and rollback
- Stream realtime audio, video, and data through a global edge network
- Build agents in the browser with Agent Builder
- Run supported AI models through built-in LiveKit Inference
- Provision phone numbers and connect PSTN calls to LiveKit rooms
- Monitor transcripts, traces, recordings, logs, usage, and quality metrics
- Use APIs, SDKs, webhooks, CLI tools, and end-to-end encryption
Use cases
- Build voice agents for customer support and appointment scheduling
- Deploy video-conferencing and realtime collaboration applications
- Connect AI agents to phone calls, Twilio, and WhatsApp Business Calling
- Stream and record live audio or video sessions
- Run globally distributed physical-agent and teleoperation applications
Pros
Cons
Capabilities
- Command line — “Manage and interact with your application from the command line” source
- Choice of models — “Yes. LiveKit Inference supports over 50 AI models out-of-the-box, no API keys or additional configuration required.” source
- Self-hosted — “The LiveKit Agents framework and LiveKit media server are both completely open source and available to run locally or host on your own infrastructure.” source
- No code retained — “Prompts, audio, and model outputs aren't logged or stored in LiveKit or underlying model providers” source
- API — “Metrics export APIs” source
- Official SDKs — “Build voice agents with open source SDKs and complete developer control.” source
- Runs models for you — “Call popular models with LiveKit's inference service” source
- Traces and evaluates — “Agent observability events” source
Security
Pricing
- Starting price
- $50/mo
- Prices checked
- 2026-09-25
Build
Free
- Agent deployment
- Agent observability
- Inference credits
- Global edge network
- Telephony (1 free number)
- Session metrics and analytics
Ship
- STARTING AT $50/mo
- Team collaboration
- Custom voices
- Instant rollback to a previous agent deployment
- Email support
Scale
- STARTING AT $500/mo
- Role-based access
- Metrics export APIs
- Region pinning
- Private links
- Security reports / HIPAA
- Inference discounts
Enterprise
Price on request
- Volume pricing, including inference
- Shared Slack channel
- SSO
- Support SLA