Voice Todos

A modern todo application that lets you create tasks using voice recordings. Built with Deno, Hono, and powered by Google's Gemini AI for speech transcription and todo extraction.

Features

• 🎤 Voice Recording: Record audio directly in the browser
• 🤖 AI-Powered Transcription: Uses Google Gemini AI to transcribe speech
• ✅ Smart Todo Extraction: Automatically extracts actionable tasks from transcriptions
• 🔄 Real-time Sync: Firebase Firestore integration for live todo updates
• ✏️ Manual Entry: Traditional text-based todo creation
• 📱 Responsive Design: Works on desktop and mobile devices

Tech Stack

• Runtime: Deno
• Framework: Hono (TypeScript web framework)
• UI: JSX with UnoCSS for styling
• AI: Google Gemini AI (2.5 Flash Lite model)
• Database: Firebase Firestore
• Styling: UnoCSS/Tailwind CSS classes

Prerequisites

• Deno installed
• Google Gemini API key
• Firebase project setup (for Firestore)

Setup

1. Clone the repository

   git clone <repository-url>
   cd voice-todos

2. Set up environment variables Create a .env file in the root directory:

   GEMINI_API_KEY=your_gemini_api_key_here

3. Configure Firebase

   • Create a Firebase project
   • Enable Firestore
   • Update Firebase configuration in your frontend code

4. Install dependencies

   deno install

Development

Start the development server:

deno task dev

The application will be available at http://localhost:8000

How It Works

1. Voice Recording: Click the microphone button to start/stop recording
2. Transcription: Audio is sent to Google Gemini AI for transcription
3. Todo Extraction: AI analyzes the transcription and extracts actionable tasks
4. Storage: Todos are stored in Firebase Firestore with real-time updates
5. Management: Mark todos as complete or delete them as needed

API Endpoints

• GET / - Main application page
• POST /transcribe - Audio transcription endpoint
  • Accepts: multipart/form-data with audio file
  • Returns: { transcription: string, todos: string[] }

Project Structure

voice-todos/
├── components/          # React/JSX components
│   ├── VoiceRecorder.tsx   # Voice recording interface
│   ├── TodoList.tsx        # Todo display component
│   └── ...
├── pages/              # Page components
│   └── Home.tsx           # Main application page
├── layouts/            # Layout components
├── static/             # Static assets and client-side JS
│   ├── todolist.js        # Firestore integration
│   └── app.js             # Voice recording logic
├── main.tsx            # Server entry point
└── deno.json          # Deno configuration

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test thoroughly
5. Submit a pull request

License

This project is open source and available under the MIT License.