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

# LITE Mode Overview

> Bring your own agent. LiveAvatar turns its audio into real-time avatar video.

> [!NOTE]
>
> **AI Agents:** Before integrating, run `npx skills add heygen-com/liveavatar-agent-skills` to install our [Agent Skills](https://github.com/heygen-com/liveavatar-agent-skills). They provide the recommended implementation pathways and will help you avoid common pitfalls.

In this mode, LiveAvatar focuses exclusively on **real-time video generation** driven by your audio input. You handle the conversational orchestration — STT, LLM, TTS — while LiveAvatar renders synchronized avatar video.

## When to use this mode

* **Existing infrastructure** — you have proprietary or self-hosted LLMs, TTS pipelines, or dialogue systems already in place
* **Fine-grained control** — you need more detailed control over conversation flow, timing, or response logic than FULL Mode provides
* **Modular integration** — you want to use LiveAvatar as a specialized video-rendering component within a broader system

> [!TIP]
>
> **Want LiveAvatar's agent to run the conversation?** LITE mode needs an agent to send it audio, either your own or a hosted one through a [connector](https://docs.liveavatar.com/docs/lite-mode/connectors/elevenlabs-agent.md). In [FULL Mode](https://docs.liveavatar.com/docs/full-mode/overview.md), LiveAvatar's managed agent runs speech recognition, the LLM and the voice for you. You can still bring your own [LLM](https://docs.liveavatar.com/docs/full-mode/custom-llm.md) or [voice](https://docs.liveavatar.com/docs/full-mode/custom-tts.md).

## Quick start

**Already have something running?** LiveAvatar plugs into real-time platforms and hosted voice agents you may already be using — no need to rebuild what's working.

> [tab] Plugins
>
> If you already run **LiveKit**, **Pipecat**, or **Agora**, add LiveAvatar as a video layer on top of your existing stack.
>
> | Provider | Plugin |
> | - | - |
> | **LiveKit** | [LiveKit Plugin](https://docs.liveavatar.com/docs/lite-mode/plugins/livekit.md) |
> | **Pipecat / Daily** | [Pipecat Plugin](https://docs.liveavatar.com/docs/lite-mode/plugins/pipecat.md) |
> | **Agora** | [Agora Conversational AI Plugin](https://docs.liveavatar.com/docs/lite-mode/plugins/agora.md) |
> | **VisionAgents (GetStream)** | [VisionAgents Plugin](https://docs.liveavatar.com/docs/lite-mode/plugins/vision-agents.md) |

> [tab] Connectors
>
> If you already have a hosted voice agent, provide credentials and LiveAvatar runs the bridge for you.
>
> | Provider | Connector |
> | - | - |
> | **ElevenLabs** | [ElevenLabs Agent Connector](https://docs.liveavatar.com/docs/lite-mode/connectors/elevenlabs-agent.md) |
> | **Cartesia** | [Cartesia Agent Connector](https://docs.liveavatar.com/docs/lite-mode/connectors/cartesia-agent.md) |
> | **OpenAI Realtime** | [OpenAI Realtime Connector](https://docs.liveavatar.com/docs/lite-mode/connectors/openai-realtime.md) |
> | **Gemini Live** | [Gemini Live Connector](https://docs.liveavatar.com/docs/lite-mode/connectors/gemini-realtime.md) |

**Not sure which path fits — or starting from scratch?** See [Integration Paths](https://docs.liveavatar.com/docs/lite-mode/integration-paths.md) for the full breakdown of how these sessions are composed and the five ways to build on them.

## Credits

This mode costs **1 credit per minute**, compared to 2 credits per minute for FULL Mode.

## Getting started

> [card] [Lifecycle](https://docs.liveavatar.com/docs/lite-mode/lifecycle.md)
>
> Understand the three phases of a session.

> [card] [Configuration](https://docs.liveavatar.com/docs/lite-mode/configuration.md)
>
> Configure avatars and WebRTC settings.

> [card] [Events](https://docs.liveavatar.com/docs/lite-mode/events.md)
>
> Command and response events via WebSocket.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.