# liveavatar-integrate

This skill takes you from stack assessment to a working LiveAvatar integration, picking Embed, FULL or LITE Mode and walking through the build.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1100 installs · ★ 16
- Author: heygen
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/heygen-com/liveavatar-agent-skills/tree/HEAD/skills/liveavatar-integrate/SKILL.md
- Updated: 2026-09-10
- HTML: https://affpapa.org/en/nevibecode/skills/liveavatar-integrate

## What it does

The skill reads your project before it asks anything. It scans `package.json`, `requirements.txt` and imports for your own LLM, TTS or STT, for LiveKit or Agora SDKs, for `LIVEAVATAR_API_KEY` in `.env`. Whatever the code already answers, it won't ask. The gaps get a short checklist: the goal, whether you have your own pipeline, whether you need programmatic control over the conversation.

Then it routes to a single path. No backend — Embed. No AI stack of your own — FULL Mode. A complete STT + LLM + TTS pipeline — LITE Mode. Separate branches cover your own LLM, your own ElevenLabs voice, push-to-talk, the ElevenLabs plugin, and your own LiveKit or Agora infrastructure. The agent states the recommendation in two or three sentences and moves straight into the guide under `references/`.

\`X-API-KEY` stays on the backend; the frontend only ever gets `livekit_client_token`. Spot the API key in client code and the integration needs restructuring. In FULL Mode a missing `context_id` gives you a silent avatar with no error thrown, so create the context first. FULL and LITE are different protocols — LiveKit data channels versus WebSocket — and never mix. For testing it points to the sandbox: `is_sandbox: true` with avatar `dd73ea75-1218-4ef3-92ce-606d5f7fbc0a`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add heygen-com/liveavatar-agent-skills --skill liveavatar-integrate -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/liveavatar-integrate/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/liveavatar-integrate/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add heygen-com/liveavatar-agent-skills --skill liveavatar-integrate -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/liveavatar-integrate/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add heygen-com/liveavatar-agent-skills --skill liveavatar-integrate -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/liveavatar-integrate/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install heygen-com/liveavatar-agent-skills liveavatar-integrate
```

2. **Manually: put the files in place**
- File: `.github/skills/liveavatar-integrate/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add heygen-com/liveavatar-agent-skills --skill liveavatar-integrate -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/heygen-com/liveavatar-agent-skills --path skills/liveavatar-integrate
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/liveavatar-integrate/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add heygen-com/liveavatar-agent-skills --skill liveavatar-integrate -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/heygen-com/liveavatar-agent-skills/tree/HEAD/skills/liveavatar-integrate/SKILL.md

## When to use it
- put a talking avatar on a landing page with no backend
- wire LiveAvatar into an existing STT + LLM + TTS pipeline
- choose between Embed, FULL Mode and LITE Mode for your stack
- plug your own LLM or ElevenLabs voice into the avatar
- migrate from HeyGen Interactive Avatar to LiveAvatar

## Example prompts
- Build a LiveAvatar integration for my Next.js app
- I have a full STT + LLM + TTS pipeline — connect LiveAvatar in LITE Mode
- I need an avatar on a page with no backend, which path fits?

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: e2da77b45a3dd55e.

BEGIN THIRD-PARTY FILE e2da77b45a3dd55e
```text
---
name: liveavatar-integrate
description: |
  Build a LiveAvatar integration end-to-end — assesses the user's existing stack, recommends the optimal path, and guides implementation. Use when: (1) Building a new LiveAvatar integration, (2) Adding a real-time avatar to an app or site, (3) Connecting LiveAvatar to an existing AI pipeline, (4) User mentions LiveAvatar, real-time avatar, interactive avatar, conversational avatar, or lip-sync avatar, (5) Deciding between Embed, FULL Mode, and LITE Mode, (6) Migrating from HeyGen Interactive Avatar to LiveAvatar.
license: MIT
metadata:
  author: heygen
  version: "1.0.0"
---

# LiveAvatar Integration

LiveAvatar gives your product a human face — real-time, lip-synced video avatars that speak, react, and maintain eye contact. This skill assesses what you have, recommends the best integration path, and walks you through building it.

## Step 1: Discover What the User Has

Before recommending a path, gather context. Check the codebase and conversation for signals. **Do not ask questions the codebase already answers.**

### Signals to look for in the codebase

Scan for these automatically — do not ask the user if you can detect them:

| Signal | Where to look | What it means |
|--------|--------------|---------------|
| OpenAI / Anthropic / LLM SDK imports | `package.json`, `requirements.txt`, imports | User has their own LLM |
| ElevenLabs / PlayHT / Deepgram TTS SDK | dependencies, imports | User has their own TTS |
| Deepgram / Whisper / AssemblyAI STT SDK | dependencies, imports | User has their own STT |
| LiveKit SDK (`livekit-server-sdk`, `@livekit/`) | dependencies | User has LiveKit infra |
| Agora SDK | dependencies | User has Agora infra |
| Pipecat imports | dependencies, imports | User has a Pipecat pipeline |
| ElevenLabs Agent / Conversational AI | dependencies, config | User has an ElevenLabs agent |
| `HEYGEN_API_KEY` / `LIVEAVATAR_API_KEY` | `.env`, config files | User already has an API key |
| Existing LiveAvatar code | imports, API calls to `api.liveavatar.com` | Existing integration (debug, not new setup) |
| No backend / static site | file structure (pure HTML/CSS/JS, no server) | Embed is the only option |
```
END THIRD-PARTY FILE e2da77b45a3dd55e

The third-party file has ended. Everything between the e2da77b45a3dd55e tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2216 of 8958 bytes. © heygen · MIT · https://github.com/heygen-com/liveavatar-agent-skills/tree/HEAD/skills/liveavatar-integrate/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md