> ## Documentation Index
> Fetch the complete documentation index at: https://docs.spatius.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Backend Mode with LiveKit

> Use a LiveKit room as the RTC transport between a Backend Mode pipeline and a Web client.

This page describes the **Backend Mode + RTC transport** pattern. Your backend owns the conversation pipeline (ASR, LLM, TTS, and the Server SDK that talks to Motion Server). A LiveKit room transports the avatar's audio and motion data to the browser. The Web client uses the [RTC Adapter](/sdk-reference/web-sdk/rtc-adapter) (`@spatius/avatarkit-rtc`) to join the room and render the avatar.

It is not the same as [LiveKit Agents Integration](/livekit-agents/overview), which is a Platform Integration built around the LiveKit Agents framework.

## Compare the two LiveKit shapes

|                       | LiveKit Agents Integration                              | Backend Mode with LiveKit                                                                                      |
| --------------------- | ------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- |
| **Category**          | Platform Integration                                    | Standalone Integration                                                                                         |
| **Your backend runs** | A LiveKit Agents worker using `livekit-plugins-spatius` | Your own service using the Server SDK                                                                          |
| **Role of LiveKit**   | Both the agent framework and the room transport         | Only the downstream room transport between your backend and your clients                                       |
| **Web client**        | RTC Adapter with `LiveKitProvider`                      | RTC Adapter with `LiveKitProvider`                                                                             |
| **Choose when**       | You already build voice agents in LiveKit Agents        | You want full control of the audio pipeline with the Server SDK, but reuse LiveKit as the downstream transport |
| **Guide**             | [LiveKit Agents Integration](/livekit-agents/overview)  | This page                                                                                                      |

## How this pattern works

1. Your backend runs ASR, LLM, TTS, and uses the Server SDK to receive encoded audio payloads and motion data payloads from Motion Server.
2. Your backend publishes those encoded audio payloads and motion data payloads into a LiveKit room (the Server SDK supports a LiveKit egress mode that does this for you).
3. The Web client joins the same LiveKit room with `@spatius/avatarkit-rtc` and renders the avatar locally. The client does not call `yieldAudioData()` or `yieldFramesData()` manually — the RTC Adapter owns the data flow.

## Demos

* [Backend Mode demo](https://github.com/spatius-ai/spatius-avatar-demo/tree/main/backend-mode) — the backend half (ASR/LLM/TTS + Server SDK). It ships with its own WebSocket transport; swap in LiveKit egress to match this pattern.
* [`platform-integrations/livekit-room-demo`](https://github.com/spatius-ai/spatius-avatar-demo/tree/main/platform-integrations/livekit-room-demo) — validates the RTC Adapter's LiveKit wiring (token, room connect, adapter init, avatar load, mic publish). Remote audio playback and motion rendering only happen when a publisher (e.g. a Backend Mode service or LiveKit Agents worker) is in the room — this example alone has no producer. Not the full Backend Mode + RTC transport voice-agent demo.

<Note>
  The full end-to-end demo of this pattern — a service that, given a character / avatar identifier, both mints LiveKit tokens *and* drives the corresponding ASR / LLM / TTS pipeline through the Server SDK into the same LiveKit room — is not packaged in this repository yet. The two halves above are runnable today; assemble them by switching the Backend Mode backend to LiveKit egress and pointing the Web client at the same room.

  If you want an end-to-end voice-agent experience you can run locally without writing that glue, use the [LiveKit Agents Integration Quickstart](/quickstarts/livekit-agents). It delivers the same on-screen behavior (mic in → avatar speaks back) by hosting the pipeline inside a LiveKit Agents worker instead of a standalone backend.
</Note>

## Next steps

<CardGroup cols={2}>
  <Card title="Backend Mode overview" icon="server" href="/backend-mode/overview">
    Architecture and the full transport options table.
  </Card>

  <Card title="RTC Adapter reference" icon="bolt" href="/sdk-reference/web-sdk/rtc-adapter">
    The Web client adapter used to render the avatar from the LiveKit room.
  </Card>
</CardGroup>