ProxiCall

ProxiCall is a next-generation voice-first communication platform that bridges the gap between human intuition and artificial intelligence. It transforms your smartphone into a seamless extension of your mind, enabling you to communicate, transact, and create effortlessly through natural conversation.

🚀 The Vision

In a world saturated with screens and notifications, ProxiCall returns to the most natural interface: the human voice. We believe that technology should adapt to us, not the other way around. By leveraging the power of advanced AI, ProxiCall eliminates the friction of traditional apps, allowing you to stay present in your life while your device handles the complexities in the background.

✨ Key Features

🗣️ Voice-First Interface

• Natural Conversation: Speak to ProxiCall as you would to a friend. No menus, no taps, no searching—just pure conversation.
• Real-Time Translation: Communicate with anyone, anywhere. ProxiCall breaks down language barriers instantly.
• Voice Cloning: Create a digital twin of your voice that can handle calls, messages, and tasks with your unique personality and tone.

🧠 AI-Powered Autonomy

• Proactive Assistance: ProxiCall anticipates your needs, managing your schedule, communications, and tasks before you even ask.
• Contextual Awareness: The AI understands the nuances of your life—your relationships, preferences, and priorities—to provide truly personalized support.
• Smart Delegation: Offload repetitive or complex tasks to your AI assistant, freeing you to focus on what matters most.

🛡️ Privacy & Control

• User-Centric Design: You are always in control. Every action, every decision, every communication is transparent and auditable.
• Secure by Design: Built with state-of-the-art security protocols to protect your identity, your voice, and your data.
• Ethical AI: Advanced verification systems ensure that AI actions are aligned with your intentions, preventing errors and maintaining trust.

🛠️ Technology Stack

ProxiCall is built on a foundation of cutting-edge technologies:

• Frontend: Next.js 14 (App Router), React 18, TypeScript, Tailwind CSS
• Backend: Node.js, Express.js
• Database: MongoDB (Mongoose ODM)
• AI/ML: Google Gemini API, Web Speech API
• Real-Time Communication: Socket.IO
• Authentication: JWT (JSON Web Tokens)
• Deployment: Vercel (Frontend), Render (Backend)

📂 Project Structure

proxicall/
├── web/                    # Next.js Frontend
│   ├── app/                # App Router pages and layouts
│   ├── components/         # Reusable React components
│   ├── lib/                # Utility functions and helpers
│   └── public/             # Static assets
├── server/                 # Node.js Backend
│   ├── config/             # Configuration files
│   ├── controllers/        # Request handlers
│   ├── models/             # Mongoose schemas
│   ├── routes/             # API route definitions
│   └── server.js           # Express application entry point
├── .env                    # Environment variables
├── package.json            # Project dependencies
└── README.md               # Project documentation

🚀 Getting Started

Prerequisites

• Node.js (v18 or higher)
• MongoDB (local or cloud)
• Google Gemini API Key

Installation

1. Clone the repository

   git clone <repository-url>
   cd proxicall

2. Backend Setup

   cd server
   npm install
   # Create .env file based on .env.example
   cp .env.example .env
   # Configure your environment variables in .env
   # Start the server
   npm start

3. Frontend Setup

   cd ../web
   npm install
   # Create .env.local file based on .env.local.example
   cp .env.local.example .env.local
   # Configure your environment variables in .env.local
   # Start the development server
   npm run dev

4. Access the Application Open http://localhost:3000 in your browser to access the ProxiCall dashboard.

📂 Codebase Overview

Frontend (web/)

• app/: Contains the Next.js App Router structure.

  • layout.tsx: Root layout with global styles and providers.
  • page.tsx: Dashboard landing page.
  • login/page.tsx: Login and authentication pages.
  • dashboard/page.tsx: Main dashboard with navigation.
  • dashboard/voice-clone/page.tsx: Voice cloning interface.
  • dashboard/ai-assistant/page.tsx: AI assistant configuration.
  • dashboard/ai-verification/page.tsx: AI action verification.
  • dashboard/settings/page.tsx: User settings and preferences.

• components/: Reusable UI components.

  • AuthProvider.tsx: Authentication context provider.
  • ToastProvider.tsx: Toast notification system.
  • dashboard/VoiceClone.tsx: Voice cloning UI.
  • dashboard/GeminiChat.tsx: AI chat interface.
  • dashboard/AIVerification.tsx: AI action verification UI.
  • dashboard/Settings.tsx: Settings management.

• lib/: Utility functions.

  • api.ts: API client for backend communication.
  • auth.ts: Authentication helpers.

Backend (server/)

• config/: Configuration files.

  • db.js: MongoDB connection setup.

• controllers/: Request handlers.

  • authController.js: Authentication logic.
  • voiceController.js: Voice cloning endpoints.
  • aiController.js: AI assistant endpoints.
  • settingsController.js: Settings management.

• models/: Mongoose schemas.

  • User.js: User model.
  • VoiceClone.js: Voice clone data.
  • AISettings.js: AI assistant settings.

• routes/: API route definitions.

  • authRoutes.js: Authentication routes.
  • voiceRoutes.js: Voice cloning routes.
  • aiRoutes.js: AI assistant routes.
  • settingsRoutes.js: Settings routes.

• server.js: Express application entry point.

  • Sets up middleware, routes, and error handling.

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

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

📞 Support

For issues or questions, please open an issue in the repository.

---

Built with ❤️ for the future of communication