LiveKit Agents
Open-source framework for building ultra-low-latency multimodal voice and video agents
Replaces custom scripts and internal glue code for voice & phone agents workflows.
Dossier overview
LiveKit Agents provides real-time WebRTC transport, turn detection, voice activity detection, and pluggable STT/LLM/TTS or speech-to-speech pipelines so you can ship production voice and video AI agents.
Quickstart
pip install livekit-agentsWhat people say on X
Live feed on X ↗We pull unfiltered builder mentions (praise and complaints) from X on our daily sync. Inspect the live unfiltered stream directly on X right now:
Read latest "LiveKit Agents" mentions on X ↗Best use cases
- Inbound and outbound AI phone agents over SIP
- Real-time multimodal tutors and customer support avatars
- Low-latency voice interfaces with live tool calling
Field notes
Strengths
- Sub-500ms global WebRTC media routing
- Built-in semantic turn detection and interruption handling
- Designed specifically for dev teams / byok
Tradeoffs
- Free/starter tiers have rate or seat limits
- Self-hosting requires managing your own model keys and runtime
Compare with Voice alternatives
| Tool | Best for | Runs in | Pricing | Setup |
|---|---|---|---|---|
| LiveKit Agents | Dev teams / BYOK | API / SDK | Freemium | CLI / SDK install |
| Vapi | Enterprise teams | API / SDK | Paid | API / SDK setup |
| Pipecat | Dev teams / BYOK | API / SDK | Free / OSS | CLI / SDK install |
| Retell AI | Enterprise teams | API / SDK | Paid | API / SDK setup |
| Bland AI | Enterprise teams | API / SDK | Paid | API / SDK setup |