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

# Avaluma AI: Photorealistic AI Avatars for Your App

> Avaluma AI lets you embed real-time photorealistic animated AI avatars into any application using GPU-accelerated rendering and LiveKit.

Avaluma AI is a platform for embedding real-time photorealistic animated AI avatars directly into your applications. You provide a LiveKit room and an Avaluma-issued `.hvia` avatar file; Avaluma handles GPU-accelerated rendering, lip-sync, and video streaming — so your users see a lifelike avatar speaking, not a static image or a cartoon.

## How It Works

Avaluma AI is built on two cooperating components that you deploy independently.

**Avatar Server** runs on an NVIDIA GPU and is the rendering engine. It reads your `.hvia` avatar files, animates the avatar frame-by-frame in response to incoming audio, and publishes the resulting video track directly into a LiveKit room. You can host the Avatar Server yourself or use Avaluma's managed endpoint at `https://api.avaluma.ai`.

**LiveKit Agent** is a Python-based voice AI pipeline that drives a conversation. It captures microphone input, runs it through Speech-to-Text (STT), passes the transcript to a Large Language Model (LLM), synthesises speech with Text-to-Speech (TTS), and then hands the audio to the Avatar Server via the `avaluma-livekit-plugin`. The avatar animates that audio and streams the video back into the room.

## Prerequisites

Before you deploy, make sure you have the following:

* An **Avaluma license key** — obtain one at [avaluma.ai](https://avaluma.ai)
* One or more **`.hvia` avatar files** issued with your license
* A **LiveKit account** — [LiveKit Cloud](https://livekit.io) or self-hosted
* An **NVIDIA GPU** with CUDA 12 support, OpenGL, and at least **6 GB VRAM** (each simultaneous avatar session uses \~2.5 GB)
* **Docker & Docker Compose** installed on your server
* **NVIDIA Container Toolkit** installed so Docker can access the GPU

<Note>
  The Avatar Server is GPU-only. A CPU-only host is not supported. Tested architectures include Ampere, Ada Lovelace, and Blackwell.
</Note>

## Explore the Docs

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/en/self-hosting/quickstart">
    Deploy the Avatar Server and LiveKit Agent in minutes and connect your first client.
  </Card>

  <Card title="Architecture" icon="sitemap" href="/en/self-hosting/architecture">
    Understand how the Avatar Server and LiveKit Agent work together to render and stream your avatar.
  </Card>

  <Card title="Avatar Server" icon="server" href="/en/self-hosting/avatar-server/overview">
    Configure GPU resources, manage `.hvia` files, and set up an HTTPS reverse proxy for production.
  </Card>

  <Card title="LiveKit Agent" icon="microphone" href="/en/self-hosting/livekit-agent/overview">
    Customise the STT → LLM → TTS pipeline and connect it to any LiveKit room.
  </Card>
</CardGroup>