Voice UI

Self-evolving AI Assistant UI — An interface that improves itself through voice conversation

Features

• 🎤 Speech recognition (Whisper)
• 🔊 Text-to-speech (TTS)
• 🤖 Cute robot UI with expressive animations
• 🔄 Self-evolution (voice commands to modify the UI)
• 📝 Automatic Git commits

Setup

cd /skills/voice-ui
npm install
./start.sh

Open http://localhost:8765 in your browser.

Required Configuration

Add the voice agent to your OpenClaw config (~/.openclaw/openclaw.json):

{
  "agents": {
    "list": [{
      "id": "voice",
      "name": "Voice Assistant",
      "model": { "primary": "anthropic/claude-sonnet-4-5" }
    }]
  }
}

Usage

1. Tap the microphone button (or hold the Space key)
2. Speak your request
3. AI responds

Self-evolution Commands

• “Make the background blue” → Automatically edits CSS
• “Make the button larger” → Modifies styling
• “Add a new feature” → Edits JavaScript

All changes are automatically committed to Git.

File Structure

• index.html — Main UI
• server.cjs — Node.js server
• start.sh — Startup script
• CONTEXT.md — Context information provided to the AI

Environment Variables

• OPENAI_API_KEY — OpenAI API Key (used for Whisper and TTS)

If not set, the system will attempt to auto-fetch it from the OpenClaw configuration.