← Back to Skills Marketplace
ennno

LiveAvatar

by eNNNo · GitHub ↗ · v1.0.1
cross-platform ✓ Security Clean
2304
Downloads
9
Stars
7
Active Installs
1
Versions
Install in OpenClaw
/install liveavatar
Description
Talk face-to-face with your OpenClaw agent using a real-time video avatar powered by LiveAvatar
README (SKILL.md)

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

Usage Guidance
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.
Capability Analysis
Type: OpenClaw Skill Name: liveavatar Version: 1.0.1 The skill bundle is classified as benign. The `SKILL.md` file provides clear instructions for the OpenClaw agent to launch a local real-time video avatar interface using `npx openclaw-liveavatar`. This command executes the skill's primary component, which is declared in the `metadata.install` section. The instructions are directly aligned with the stated purpose of providing a video avatar, requiring a `LIVEAVATAR_API_KEY` and communicating via `http://localhost:3001` and the local OpenClaw Gateway. There is no evidence of prompt injection, data exfiltration, malicious execution, persistence, or obfuscation within the provided files. All actions described are consistent with the skill's intended functionality.
Capability Assessment
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.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install liveavatar
  3. After installation, invoke the skill by name or use /liveavatar
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Initial release: voice/video avatar interface for OpenClaw agents
Metadata
Slug liveavatar
Version 1.0.1
License
All-time Installs 7
Active Installs 7
Total Versions 1
Frequently Asked Questions

What is LiveAvatar?

Talk face-to-face with your OpenClaw agent using a real-time video avatar powered by LiveAvatar. It is an AI Agent Skill for Claude Code / OpenClaw, with 2304 downloads so far.

How do I install LiveAvatar?

Run "/install liveavatar" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is LiveAvatar free?

Yes, LiveAvatar is completely free (open-source). You can download, install and use it at no cost.

Which platforms does LiveAvatar support?

LiveAvatar is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created LiveAvatar?

It is built and maintained by eNNNo (@ennno); the current version is v1.0.1.

💬 Comments