SIYA AI 🤖

SIYA (Smart Intelligent Youth Assistant) is a Python-based AI voice assistant with a custom graphical user interface. It listens to your voice, understands your intent, and responds — whether that means answering a question, searching the web in real time, automating a task, or generating an image.

---

✨ Features

• 🎙️ Voice Input — Speak naturally; SIYA transcribes your voice using speech recognition
• 🔊 Text-to-Speech Output — Responses are spoken back to you in real time
• 🧠 Smart Decision Layer — A first-layer model routes your query to the right handler: chatbot, real-time search, or automation
• 🌐 Real-Time Web Search — Fetches live answers for time-sensitive queries
• ⚙️ Task Automation — Open/close apps, play media, perform Google or YouTube searches, and more
• 🎨 Image Generation — Generate AI images from natural language prompts
• 🖥️ Custom GUI — A built-in graphical interface with live chat display and assistant status
• 💾 Chat Memory — Conversation history is persisted via a JSON chat log

---

📁 Project Structure

SIYA-AI/
│
├── Backend/
│   ├── Chatbot.py           # Handles general conversational queries
│   ├── RealtimeSearchEngine.py  # Performs real-time web searches
│   ├── SpeechToText.py      # Converts microphone input to text
│   ├── TextToSpeech.py      # Converts text responses to audio
│   ├── Automation.py        # Handles system/task automation commands
│   ├── ImageGeneration.py   # AI image generation module
│   └── Model.py             # First-layer decision-making model (DMM)
│
├── Frontend/
│   └── GUI.py               # Graphical user interface
│
├── Data/
│   └── ChatLog.json         # Persistent conversation history
│
├── Main.py                  # Entry point — ties all modules together
├── Requirements.txt         # Python dependencies
└── .env                     # Environment variables (username, assistant name, API keys)

---

🚀 Getting Started

Prerequisites

• Python 3.9+
• A microphone
• API keys (configured in .env)

Installation

1. Clone the repository

   git clone https://github.com/HemantKSharmaa/SIYA-AI.git
   cd SIYA-AI

2. Install dependencies

   pip install -r Requirements.txt

3. Set up your .env file

   Open the .env file and fill in your details:

   Username=YourName
   Assistantname=SIYA
   # Add any required API keys here

4. Run SIYA

   python Main.py

---

🛠️ How It Works

1. SIYA listens for your voice via the microphone.
2. Your speech is converted to text using the SpeechToText module.
3. The First Layer Decision Model classifies the query as:
   • general → handled by the AI Chatbot
   • realtime → handled by the Real-Time Search Engine
   • open / close / play / system / ... → handled by the Automation module
   • generate → triggers the Image Generation pipeline
4. The response is displayed in the GUI and spoken aloud via Text-to-Speech.

---

📺 Demo

Watch SIYA in action: YouTube Demo

---

🤝 Contributing

Contributions, issues, and feature requests are welcome! Feel free to open a pull request or raise an issue.

---

📄 License

This project is open source. See the LICENSE file for details.

---

Built with ❤️ by Hemant Kumar Sharma