LiveAvatar provides a real-time video and voice interface for your agents, enabling face-to-face AI communication.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install liveavatar
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install liveavatar using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is LiveAvatar?
The LiveAvatar integration for Openclaw Skills brings a human-like dimension to AI interactions. By combining real-time video synthesis with voice recognition, users can engage in natural, face-to-face conversations with their agents. This skill leverages the LiveAvatar platform to handle transcription and lip-syncing, ensuring a seamless flow between the user's speech and the agent's response.
Integrating this into your workflow allows you to move beyond text-based interfaces. The avatar dynamically reacts to user input, providing a more engaging and empathetic experience. As a highlight of the Openclaw Skills ecosystem, this tool bridges the gap between digital intelligence and human presence through advanced multimodal capabilities.
LiveAvatar Use Cases
- Building interactive AI-driven education platforms where students talk to a virtual tutor.
- Creating personalized virtual assistants for companionship or accessibility support.
- Enhancing customer service interfaces with a visual, empathetic face for brand engagement.
- Demonstrating the power of multimodal Openclaw Skills in live demos and presentations.
How LiveAvatar Works
- The user provides voice input via the browser's microphone on the LiveAvatar interface.
- The system transcribes the speech into text in real-time using LiveAvatar technology.
- The transcribed text is sent to the local OpenClaw Gateway (running on port 18789).
- The AI agent processes the input and generates a text-based response.
- LiveAvatar synthesizes the response into speech and animates the video avatar with natural lip-sync and expressions.
LiveAvatar Setup
To use this within the Openclaw Skills framework, first obtain a free API key from the LiveAvatar dashboard. Then, set your environment variable:
export LIVEAVATAR_API_KEY=your_api_key_here
Alternatively, add the key to your local configuration at ~/.openclaw/openclaw.json. Once configured, you can launch the interface by invoking the command through your agent:
/liveavatar
Ensure your OpenClaw Gateway is running, and then navigate to http://localhost:3001 in a modern browser to begin the session.
LiveAvatar Data Schema & Taxonomy
The skill manages configuration and real-time data streams to maintain the avatar connection. The organization includes:
| Component | Detail |
|---|---|
| Credentials | LIVEAVATAR_API_KEY stored in environment or openclaw.json |
| Local Connection | Connects to OpenClaw Gateway via localhost:18789 |
| Frontend | Local server hosted on port 3001 via node/npx |
| Avatar Assets | Metadata and video streams provided via the LiveAvatar API |
LiveAvatar Advanced Features
- Smart echo cancellation to prevent the AI from responding to its own voice output.
- Multi-avatar support allowing users to choose between different characters and expressions.
- Intelligent TTS summarization that optimizes long-form agent responses for verbal delivery.
- Text-chat fallback capability for situations where voice input is not available or desired.
SKILL.md
Loading
Related Openclaw Skills
Kenya Tax Rates Skill
A specialized utility for calculating accurate Kenya payroll deductions, including PAYE, SHIF, and Housing Levy using 2024/2025 rates.
Agent Money Tracker
A comprehensive TypeScript library for AI agents to manage finances, budgets, and savings through natural language parsing and structured data.
Daily Devotion Skill
A comprehensive spiritual AI agent skill that generates personalized daily devotions including scripture, pastoral reflections, and structured first-person prayers.
Xiaohongshu Long-Form Publisher
An automated workflow for publishing professional long-form articles on the Xiaohongshu creator platform via the built-in browser.
OpenCode Remote Control
A sophisticated remote management skill for OpenCode servers that enables multi-session orchestration and automated progress monitoring via HTTP API.
Adaptive Reasoning
Dynamically adjust AI reasoning depth based on task complexity to balance response speed and analytical depth.