🎯 Just Say "Hey Claude" - Instantly launch your development tools
🔒 Privacy-First - All voice processing happens on your device
⚡ Lightning Fast - Minimal latency, maximum productivity
🎨 Beautiful Interface - Modern React UI with smooth animations
🖥️ Windows Native - Professional installer and system integration

1. 🔽 Download Wake-Word-Detector-Setup.exe from v1.0.0b release
2. 🛡️ Run as Administrator and follow the setup wizard
3. 🔑 Configure your Picovoice API key (free tier available)
4. 🎤 Say "Hey Claude" and watch the magic happen!

# Clone and install
git clone https://github.com/Traves-Theberge/Wakeword.git
cd Wakeword
npm install

# Build and package
npm run dist

# Create installer
npm run installer:quick

• Close-field microphone (headset/USB mic) works best
• Quiet environment improves accuracy
• Consistent distance from microphone
• Clear pronunciation of "Hey Claude"

Wake-Word-Detector/
├── 🎤 src/main/                 # Electron main process
│   ├── main.ts                  # Core app logic + voice detection
│   └── preload.ts               # Secure IPC bridge
├── 🎨 src/renderer/             # React frontend
│   ├── App.tsx                  # Main application component
│   ├── components/              # UI components
│   │   ├── settings-panel.tsx   # 🛠️ Configuration interface
│   │   ├── custom-header.tsx    # 🖼️ Window controls
│   │   └── animated-background.tsx # ✨ Visual effects
│   └── hooks/                   # React hooks for state
├── 🔊 keywords/                 # Picovoice wake word models
│   ├── hey-claude.ppn          # 🎯 Trained voice model
│   └── LICENSE.txt             # Picovoice licensing
├── 🖼️ assets/                   # Application resources
│   ├── app.ico                 # Main application icon
│   ├── Green.ico               # Listening state indicator
│   └── Red.ico                 # Stopped state indicator
└── 📦 installer.nsi            # Professional Windows installer

• Node.js: Version 18 or higher
• Windows: 10 or 11 (64-bit)
• Microphone: System microphone access required
• Picovoice Account: Free API key from Picovoice Console
• Cursor IDE: Installed and accessible via system PATH
• WSL: For Claude CLI functionality (optional)

1. Clone and Install

   git clone [repository-url]
   cd Wakeword
   npm install

2. Environment Configuration Create a .env file in the root directory:

   PICOVOICE_ACCESS_KEY=your_picovoice_api_key_here

3. Get Picovoice API Key

   • Visit Picovoice Console
   • Create a free account
   • Generate an access key
   • Add to your .env file

4. Development Mode

   npm run dev

1. Build Application

   npm run build

2. Package for Windows

   npm run package

3. Create Installer

   npm run make

Build Output:

release/
└── Wake Word Detector-win32-x64/
    ├── Wake-Word-Detector.exe    # Main executable
    ├── resources/                       # App resources
    └── [electron runtime files]

1. Launch Application

   • Run the executable or use npm run dev
   • Application appears in system tray

2. Configure Settings

   • Right-click tray icon → "Show Settings"
   • Enter your Picovoice API key
   • Enable desired commands (Cursor/Claude)
   • Click "Save Configuration"

3. Test Connection

   • Use "Test API Key" button to verify setup
   • Ensure microphone permissions are granted

• Picovoice API Key: Required for wake word detection
• Enable Cursor: Toggle Cursor IDE launching
• Enable Claude: Toggle Claude CLI launching
• Wake Word Sensitivity: Adjustable detection threshold

1. Start Listening

   • Right-click tray icon → "Start Listening"
   • Tray icon turns green when active

2. Voice Activation

   • Say "Hey Claude" clearly
   • Application automatically launches configured tools

3. System Tray Controls

   • Green Icon: Listening for wake word
   • Red Icon: Detection stopped
   • Right-click Menu: Access settings and controls

When "Hey Claude" is detected:

• Cursor IDE: Opens silently in background
• Claude CLI: Launches in WSL terminal
• Status Update: Tray icon briefly indicates activation

Common Issues:

• No detection: Check microphone permissions and API key
• Cursor won't open: Verify Cursor.exe is in system PATH
• Claude CLI fails: Ensure WSL is installed and configured

Debug Mode:

npm run dev  # See console output for detailed logging

1. Extend Config Interface (main.ts)

   interface Config {
     picovoiceAccessKey?: string
     enableCursor?: boolean
     enableClaude?: boolean
     enableNewCommand?: boolean  // Add new option
   }

2. Update Command Execution

   if (config.enableNewCommand) {
     // Add your command logic
   }

3. Add UI Control (settings-panel.tsx)

   // Add toggle switch for new command

1. Create Custom Keyword

   • Use Picovoice Console to train new wake words
   • Download .ppn file to keywords/ directory

2. Update Detection

   const keywordPath = join(__dirname, '../../keywords/your-keyword.ppn')

1. Fork the Repository
2. Create Feature Branch

   git checkout -b feature/amazing-feature

3. Commit Changes

   git commit -m 'Add amazing feature'

4. Push to Branch

   git push origin feature/amazing-feature

5. Open Pull Request

• Electron - Enabling cross-platform desktop development
• React - Modern, component-based UI framework
• Tailwind CSS - Utility-first styling that just works
• Framer Motion - Beautiful, smooth animations
• NSIS - Professional Windows installer creation
• TypeScript - Type safety and developer experience

• Vite - Lightning-fast build tooling
• GitHub Actions - Automated CI/CD pipeline
• VS Code - The editor that made this possible

1. Check existing issues
2. Create a detailed bug report with:
   • Steps to reproduce
   • Expected vs actual behaviour
   • System information
   • Console logs (if applicable)

Have an idea? We'd love to hear it! Open a feature request and let's discuss.

1. Fork the repository
2. Create a feature branch (git checkout -b amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to branch (git push origin amazing-feature)
5. Open a Pull Request