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

# Welcome to LemonSlice

LemonSlice generates real-time, interactive video avatars for voice and video agent applications — lip-synced video over WebRTC, with [zero-shot avatars from any reference image](/introduction/capabilities).

Already running a voice agent? Keep your STT, LLM, and TTS. LemonSlice adds synced avatar video on top, streamed over WebRTC into the same session. See [Reference](/reference/overview) to connect it.

<Card icon="play" href="/introduction/quickstart" cta="Get started" title="Quickstart (5 min)">
  Clone a production-ready Next.js + LiveKit agent
</Card>

<Accordion title="Compare integrations">
  Each option delivers the same core avatar video. They differ in who runs the speech and intelligence stack, and how much UI you build yourself.

  |                           | **Self-Managed Pipeline (LiveKit, Agora, etc)** | **Widget**                               | **Hosted pipeline**                         |
  | ------------------------- | ----------------------------------------------- | ---------------------------------------- | ------------------------------------------- |
  |                           | ⭐⭐⭐                                             | ⭐                                        | ⭐⭐                                          |
  | **Coding level**          | Full customization                              | No-code (like embedding a YouTube video) | Low-code (UI customization only)            |
  | **Avatar video**          | Lip-synced realtime video                       | Lip-synced realtime video                | Lip-synced realtime video                   |
  | **Speech & intelligence** | You choose any STT, LLM, and TTS                | LemonSlice-managed                       | LemonSlice-managed                          |
  | **Frontend**              | You build your call UI                          | You get our prebuilt UI                  | You build your call UI                      |
  | **Avatar selection**      | Any image at runtime                            | Manually design an avatar in the web app | Manually design an avatar in the web app    |
  | **Best for**              | Production agents, custom stacks, full control  | Sites with no backend                    | Custom UI without running your own AI stack |

  ### LiveKit / Pipecat (Recommended)

  Add LemonSlice as the video layer on top of your agent stack — available as a [LiveKit integration](/livekit) or [Pipecat integration](/pipecat). You control STT, LLM, TTS, and the call experience; LemonSlice handles avatar generation only.

  ### Widget

  A prebuilt, embeddable web component for a no-code embed on your website. Design your agent in our web app and paste one snippet — no backend required. See the [Widget overview](/widget/overview). Best when you need a corner chat widget on a marketing or content site, not a custom agent application.

  ### Hosted pipeline

  LemonSlice runs STT, LLM, and TTS; you control the frontend via [Daily](https://www.daily.co/) rooms. See the [Hosted pipeline overview](/hosted/overview). Consider this when you want a custom call UI but do not want to manage the AI pipeline yourself.
</Accordion>