A self-evolving voice assistant UI that allows you to modify its own source code and appearance using natural language voice commands.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install voice-ui
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 voice-ui 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 Voice UI?
Voice UI represents a breakthrough in interactive development, functioning as a living interface within the ecosystem of Openclaw Skills. It combines advanced speech recognition via Whisper and expressive text-to-speech capabilities to create a truly conversational AI assistant. Unlike static interfaces, Voice UI is designed to evolve in real-time; users can verbally request changes to the interface's style, layout, or logic, and the agent will modify its own codebase on the fly.
This skill provides a tangible robot UI that reacts with facial expressions, making the interaction feel more natural and engaging. It is an ideal tool for developers exploring the boundaries of self-modifying software and voice-driven IDE enhancements.
Voice UI Use Cases
- Rapidly prototyping web layouts and styles using hands-free voice commands.
- Implementing self-modifying UI components that adapt to user feedback in real-time.
- Developing accessible developer tools where vocal instructions replace manual coding for repetitive styling tasks.
- Demonstrating the power of Openclaw Skills to automate frontend evolution and version control.
How Voice UI Works
- The user triggers the microphone through the web interface or by holding the spacebar shortcut.
- Audio is captured and processed via OpenAI's Whisper model to generate a precise text transcription.
- The transcribed command is sent to the configured AI agent, which interprets the intent (e.g., changing a background color or adding a button).
- The agent executes file system operations to modify
index.htmlor associated styles directly within the workspace. - The changes are immediately reflected in the browser via hot reloading, and the system automatically creates a Git commit for the evolution.
Voice UI Setup
To get started with this skill, navigate to your workspace and run the installation commands:
cd <workspace>/skills/voice-ui
npm install
./start.sh
Access the interface at http://localhost:8765. You must also update your Openclaw config at ~/.openclaw/openclaw.json to include the voice agent:
{
"agents": {
"list": [{
"id": "voice",
"name": "Voice Assistant",
"model": { "primary": "anthropic/claude-sonnet-4-5" }
}]
}
}
Ensure your OPENAI_API_KEY is set in your environment variables for Whisper and TTS functionality.
Voice UI Data Schema & Taxonomy
The skill manages its state and evolution through a specific set of local files:
| File | Description |
|---|---|
index.html |
The primary frontend entry point containing the UI logic and styling. |
server.cjs |
The Node.js backend that handles API requests and file system updates. |
CONTEXT.md |
A specialized context file that guides the AI on how to modify the project safely. |
start.sh |
A shell script to initialize the environment and launch the local server. |
Voice UI Advanced Features
- Real-time self-evolution allowing for CSS, HTML, and JS modifications through speech.
- Integrated version control that automatically commits code changes to Git after every successful modification.
- Expressive robot UI with dynamic facial states that respond to agent activity and user input.
- Seamless integration with existing Openclaw Skills to leverage high-performance LLMs like Claude 3.5 Sonnet.
SKILL.md
Loading
Related Openclaw Skills
Game Architect
A specialized domain knowledge reference for designing high-performance game architectures, combat systems, and AI frameworks.
Animation Shader Skill
A comprehensive domain knowledge plugin for configuring animation-style shaders like lilToon and Poiyomi within AI-driven development workflows.
RPM Packager
Automate the transformation of source code into production-ready RPM packages for CentOS and RHEL systems.
Relation Keeper
An AI-powered social relationship manager that tracks personal profiles, archives shared experiences, and automates event reminders.
Password Generator
An automated security tool for generating and logging highly secure, random passwords.
Cross-Agent Collaboration
A specialized tool for distributing AI tasks and managing file transfers across multiple machines in a local network using SSH.
Featured*
