This project is not affiliated with, endorsed by, or sponsored by Google LLC or the Gemini AI team. This is an independent, open-source desktop application that provides a wrapper interface for accessing Google's Gemini AI service through their official website.

• Gemini AI is a trademark of Google LLC
• This application simply loads the official Gemini website (gemini.google.com) in a desktop wrapper
• All AI functionality is provided by Google's servers
• No data is collected or stored by this application
• Users must comply with Google's Terms of Service when using Gemini AI

• 🖥️ Native Desktop Experience - Full-featured Electron app with native OS integration
• 🔄 Dual Window Modes - Switch between full window and drawer
• ⌨️ Global Hotkeys - Customizable keyboard shortcuts for instant access
• 🎨 System Tray Integration - Quick access from your system tray
• 🎤 Voice Mode - Hands-free voice interaction with automatic speech-to-text and text-to-speech

Download the latest release for your platform:

Note: Currently, only Windows builds are available. macOS and Linux builds are coming soon! 🚀

1. Download the installer
2. Run the installer
3. Follow the setup wizard
4. Launch from Start Menu or Desktop shortcut

These platforms are currently under development. You can still run the app from source code (see Development section below) or wait for the official releases coming soon!

1. Launch the Application

   • Use your desktop shortcut or application menu
   • Or use the system tray icon for quick access

2. Set Up Hotkeys (Optional)

   • Open Settings from the tray menu
   • Configure global hotkeys for drawer and main window
   • Customize voice mode hotkey (default: Ctrl+Shift+V)
   • Save your preferences

3. Start Using Gemini AI

   • The app loads Google's Gemini official website (gemini.google.com)
   • Use drawer for quick queries
   • Switch to full mode for extended conversations
   • You can also open it in full screen mode (click F11)

4. Voice Mode 🎤

   • Press your voice mode hotkey (default: Ctrl+Shift+V) to activate hands-free mode
   • Speak your question - the app will automatically detect when you're done
   • Your speech will be converted to text and sent to Gemini
   • The response will be read aloud using text-to-speech
   • Perfect for hands-free interaction while working on other tasks

The Voice Mode feature provides a completely hands-free way to interact with Gemini AI using speech-to-text and text-to-speech capabilities.

FYI: This feature uses Gemini's original built-in speech-to-text (STT) and text-to-speech (TTS) functionality - no additional services or APIs required!

1. Activation: Press the voice mode hotkey (default: Ctrl+Shift+V)
2. Voice Recording: The app automatically starts recording your voice
3. Smart Detection: Automatically detects when you've finished speaking (2-second pause)
4. Auto-Send: Converts your speech to text and sends it to Gemini
5. Audio Response: Gemini's response is automatically read aloud using text-to-speech

• Node.js 20+ (Download)
• yarn
• Git

# Clone the repository
git clone https://github.com/dortanes/gemini-desktop.git
cd gemini-desktop

# Install dependencies
yarn install

# Start development server
yarn start

# Build for Windows specifically
yarn build-win

# Build for development testing
yarn dist

Note: macOS and Linux build scripts are temporarily disabled but will be re-enabled soon. For now, focus is on Windows builds for better testing and stability.

# Run in development mode
yarn start

# Build and test locally
yarn dist

The app stores settings in your system's user data directory:

• Windows: %APPDATA%/gemini-desktop/
• macOS: ~/Library/Application Support/gemini-desktop/
• Linux: ~/.config/gemini-desktop/

This project is licensed under the MIT License - see the LICENSE file for details.