# LiveKit Agents

> LiveKit Agents builds voice agents that join LiveKit rooms, mixing STT, LLM, TTS or realtime APIs via plugins. Code is Apache-2.0; its turn-detection models use the LiveKit Model License (only with LiveKit Agents). The README example uses LiveKit Inference (usage-billed, in LiveKit Cloud) with Deepgram, Cartesia and Gemma. LiveKit server can be self-hosted and docs cover a local Ollama LLM; no local STT/TTS plugin was found.

- Repository: https://github.com/livekit/agents
- Official docs: https://docs.livekit.io/agents/
- Checked: 2026-10-16

## What it replaces
- ElevenLabs: Voice agents (partial). Framework only; STT and TTS come from plugged-in providers, which in the documented plugins are hosted services.
- Vapi: Voice agents, Phone calls (telephony) (partial). Framework plus LiveKit SIP telephony stack; STT/TTS come from plugged-in providers.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes; console mode runs locally, and the full stack including LiveKit server can be self-hosted; LiveKit Cloud is the hosted option | https://github.com/livekit/agents#features | 2026-10-15 |
| Code licence | Confirmed | Apache-2.0 | https://github.com/livekit/agents/blob/main/LICENSE | 2026-10-15 |
| Model weights licence | Partial | LiveKit turn-detection models are under the LiveKit Model License: royalty-free, but only usable with LiveKit Agents and not to train other models | https://github.com/livekit/agents/blob/main/MODEL_LICENSE | 2026-10-15 |
| Commercial use | Partial | Apache-2.0 framework; bundled turn-detector models carry LiveKit Model License restrictions; plugged-in providers have their own terms | https://github.com/livekit/agents#license | 2026-10-15 |
| Paid services needed? | No | README example uses LiveKit Inference (part of LiveKit Cloud, billed by usage) or provider keys for Deepgram, OpenAI and Cartesia. LiveKit server can be self-hosted and docs cover a local Ollama LLM, but no local STT or TTS plugin is documented in the sources checked | https://docs.livekit.io/agents/models/inference.md | 2026-10-15 |
| Hardware | Partial | Framework requirements not stated; the turn-detector model runs on CPU and needs under 500 MB RAM | https://github.com/livekit/agents/tree/main/livekit-plugins/livekit-plugins-turn-detector | 2026-10-15 |
| Operating systems | Partial | Official voice-agent quickstart includes macOS, Linux and Windows setup paths, with Python/Node agent run instructions; selected model/transport plugins can add platform requirements | https://docs.livekit.io/agents/start/voice-ai/ | 2026-10-16 |
| Setup effort | Confirmed | Easy; pip install livekit-agents with provider extras, then set LiveKit URL and API key/secret | https://github.com/livekit/agents#installation | 2026-10-15 |

GitHub: 14763 stars, 3945 forks, last push 2026-10-16, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/livekit-agents). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.