🤖 AIVA — Artificially Intelligent Voice Assistant 🎙️

A full-stack, JARVIS-inspired voice assistant web application.

---

🏗️ Architecture

• 🔙 Backend — Node.js + Express server with API key authentication, CORS, and REST APIs
• 🖥️ Frontend — Next.js application with futuristic UI and voice interaction

---

✨ Features

• 🗣️ Voice command input using Web Speech API (speech recognition)
• 🔊 Text-to-speech replies with dynamic voices
• 🌍 Multilingual greetings — Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi & English
• 🎯 Smart voice selection — voices grouped by language with Indian accent prioritization
• 🌦️ Enhanced weather lookup with WeatherAPI & OpenWeatherMap fallback
• 🏏 Live Sports Scores — CricketData & API-Football integration
• 📰 Headlines Delivery via GNews & NewsAPI.org fallback
• 🧠 Dynamic AI Search Hierarchy:
  1. Internal specialized modules (Weather, Sports, News)
  2. Gemini 2.5 Flash (Primary)
  3. Llama 3.3 70B via Groq (Secondary)
  4. Tavily AI Web Search (Tertiary)
  5. Google Custom Search Engine (Quaternary Backup)
• ⌨️ Dynamic Input Modes — Switch between Voice Mode and Text/Type Mode by speaking (e.g., "enable type mode")
• 💬 Chat-centric UI — mic embedded in input bar, suggestion chips, timestamps, copy/clear
• 🔒 Secure API via x-api-key header (bypassed in dev mode)
• 🎨 Futuristic glassmorphic theme — featuring a stunning deep rose and hot pink color palette

---

🚀 Setup

🔙 Backend

1. 📂 Navigate to backend/ directory
2. 📦 Install dependencies: npm install
3. ⚙️ Configure .env:

   PORT=5000
   GEMINI_API_KEY=your_gemini_key
   GROQ_API_KEY=your_groq_api_key_here
   OPENWEATHER_API_KEY=your_openweather_key
   WEATHER_API_KEY=your_weatherapi_key
   CRICKET_API_KEY=your_cricket_key
   SPORTS_API_KEY=your_sports_key
   NEWS_API_KEY=your_gnews_key
   TVLY_API_KEY=your_tavily_key
   GOOGLE_SEARCH_API_KEY=your_google_key
   GOOGLE_SEARCH_CX=your_cx_engine_id

4. ▶️ Run: node server.js

🖥️ Frontend

1. 📂 Navigate to frontend/ directory
2. 📦 Install dependencies: npm install
3. ▶️ Run: npm run dev
4. 🌐 Open http://localhost:3000 in your browser

---

🔌 API Endpoints

Method	Endpoint	Description
POST	/api/voice	🗣️ Process a voice command and get an AI response

Request body: { "command": "string" } Response: { "response": "string", "action?": "string", "voiceName?": "string" }

🔐 All endpoints require the x-api-key header. Development mode skips the check.

🔄 Frontend /api/voice is a proxy to the backend. Set BACKEND_URL environment variable if running the backend elsewhere.

---

🛠️ Tech Stack

Layer	Technology
🖥️ Frontend	Next.js 14, React 18, Lucide Icons
🔙 Backend	Express.js, OpenAI SDK (Groq)
🧠 AI Model	Gemini 2.5 Flash & Llama 3.3 70B
🌐 APIs	Gemini, Groq, wttr.in, Open-Meteo, DuckDuckGo, Wikipedia
🗣️ Speech	Web Speech API (Recognition + Synthesis)
🔤 Fonts	Chakra Petch, Space Grotesk, Orbitron, JetBrains Mono

---

💡 Philosophy

Voice-first interaction, intelligent and responsive behavior.

---

📜 License

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

---

Developed with ❤️ for the future of Voice AI
AIVA is a continuous exploration into building responsive, smart, and accessible voice interfaces.

👩‍💻 Debasmita Bose

👨‍💻 Babin Bid