LiveAvatar

Talk face-to-face with your OpenClaw agent using a real-time video avatar powered by LiveAvatar

Security Scan

The skill's requirements and runtime instructions match its purpose (running a LiveAvatar front-end that talks to OpenClaw and LiveAvatar), but it will download and run an npm package at runtime so you should vet the package and be mindful of voice/data privacy.

Purpose & Capability

Name/description, required binaries (node, npm), required env var (LIVEAVATAR_API_KEY), and the declared npm package (openclaw-liveavatar) are all consistent with providing a real‑time avatar frontend that uses LiveAvatar's service.

Instruction Scope

SKILL.md stays within the stated purpose: it checks for LIVEAVATAR_API_KEY, instructs the user to run the avatar (npx openclaw-liveavatar), and explains the local OpenClaw Gateway connection (port 18789) and localhost UI (http://localhost:3001). Be aware the instructions tell you to run npx which will fetch/execute code from npm at runtime; the doc does not request unrelated files, env vars, or system credentials.

Install Mechanism

The install uses an npm package (openclaw-liveavatar) which is a common mechanism but carries supply‑chain risk: npx/install will execute package code from the public registry. The SKILL.md includes a GitHub link to the project's repo, which helps auditability, but the manifest does not pin a specific package version.

Credentials

Only LIVEAVATAR_API_KEY is required which is appropriate for a third‑party avatar service. No unrelated credentials or config paths are requested.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. It runs a local server and connects to the local OpenClaw Gateway as expected; there is no indication it modifies other skills or system-wide settings.

Assessment

This skill appears coherent with its stated purpose, but take these precautions before installing: - Review the npm package source (https://github.com/eNNNo/openclaw-liveavatar) or the published package contents before running npx to ensure no unexpected behavior. - Prefer installing a pinned package version (npm install openclaw-liveavatar@<version>) rather than always running npx on the latest tag. - Be aware audio and transcriptions are sent to LiveAvatar and your OpenClaw Gateway; avoid using sensitive voice data unless you trust those services and their privacy policies. - Store the LIVEAVATAR_API_KEY in a secure place (not a world-readable file); avoid exporting secrets in shared shells. - The skill launches a local web UI (http://localhost:3001) — ensure you only run it on trusted networks and close the session when finished. If you cannot or will not review the package code, treat the runtime npm install as a potential risk and consider declining installation.

OpenClaw LiveAvatar

Give your OpenClaw agent a face and voice! This skill launches a real-time AI avatar that you can talk to naturally using your microphone. The avatar listens to you, sends your speech to your OpenClaw agent, and speaks the response back with lip-synced video.

Powered by LiveAvatar - real-time AI avatar technology.

Setup

1. Get Your API Key (Free)

1. Go to app.liveavatar.com
2. Create a free account
3. Copy your API key from the dashboard

2. Set Your API Key

export LIVEAVATAR_API_KEY=your_api_key_here

Or add to ~/.openclaw/openclaw.json:

{
  "skills": {
    "entries": {
      "liveavatar": {
        "env": {
          "LIVEAVATAR_API_KEY": "your_api_key_here"
        }
      }
    }
  }
}

Usage

Run /liveavatar to start the video avatar interface.

When the user runs this command:

1. Check if LIVEAVATAR_API_KEY is set. If not, tell them:

   You need a LiveAvatar API key. Get one free at https://app.liveavatar.com Then set it: export LIVEAVATAR_API_KEY=your_key

2. Launch the interface:

   npx openclaw-liveavatar
   

3. Tell the user:

   Your LiveAvatar interface is starting at http://localhost:3001 It will connect automatically to your OpenClaw Gateway.

   Tips:

   • Allow microphone access when prompted
   • Click the green mic button to speak
   • The avatar will respond with your agent's answers
   • Click the X button to end the session

How It Works

You speak → Avatar transcribes → OpenClaw processes → Avatar speaks response

1. Voice Input: Speak into your microphone
2. Transcription: LiveAvatar converts speech to text
3. Agent Processing: Text sent to OpenClaw Gateway (port 18789)
4. Response: Agent response returned
5. Avatar Speech: Avatar speaks with natural lip-sync

Features

• Real-time video avatar with expressions
• Voice-to-voice conversations
• Text chat fallback option
• Smart TTS summarization for long responses
• Echo cancellation (won't respond to itself)
• Multiple avatar choices

Requirements

• OpenClaw Gateway running (openclaw gateway)
• LiveAvatar API key
• Modern browser with microphone
• Node.js 18+

Troubleshooting

"OpenClaw Disconnected"

openclaw gateway

"No avatars available"

• Check LIVEAVATAR_API_KEY is set correctly

Voice not working

• Allow microphone access in browser
• Check system audio settings

Links

• LiveAvatar - Real-time avatar platform
• OpenClaw - Your personal AI assistant
• GitHub - Source code