Jarvix – AI Assistant

Jarvix is an intelligent AI assistant built with Python that can think, listen, speak, and perform multiple tasks — including real-time Q&A, PC automation, AI image generation, content creation, and multilingual support.

Features

• Voice & Text Input – Accepts commands via microphone or text

• Smart Chatbot – AI-powered conversation using Cohere API

• Real-Time Search – Fetches and summarizes live web data with Groq API

• PC Automation – Opens/controls apps and system settings

• AI Image Generation – Creates high-quality images via HuggingFace API

• Text-to-Speech – Natural voice output using Edge-TTS

• Persistent Storage – Saves chat logs, generated images, and documents

Tech Stack

• Language:

  • Python 3.10+

• Libraries & Frameworks:

  • PyQt5 – GUI

  • Selenium – Browser automation

  • Pygame – Audio handling

  • Pillow – Image processing

  • Requests / BeautifulSoup – Web scraping

  • Edge-TTS – Speech synthesis

  • mtranslate – Translation

• APIs:

  • Cohere – NLP & decision-making

  • Groq – Real-time summarization

  • HuggingFace – AI image generation

• Tools:

  • ChromeDriver – Selenium support

  • python-dotenv – Secure environment variable handling

Project Structure

Jarvix/Jarvis AI

│

├── Backend/

| ├── Model.py # Decision-making logic

| ├── Chatbot.py # AI chatbot using Cohere API

| ├── RealtimeSearchEngine.py # Real-time search + Groq summarization

| ├── Automation.py # PC and system task automation

| ├── ImageGeneration.py # AI image generation

| ├── SpeechToText.py # Voice input to text

| ├── TextToSpeech.py # Text-to-speech output

|

├── Data/ # Stores chat logs, images, docs, audio

|

├── Frontend/

| ├── .gitignore

| ├── Main.py # Entry point, integrates all modules

| ├── Requirements.txt # Dependencies list

├── LICENSE

│

└── README.md

Installation

1️. Clone the repository

```bash
git clone https://github.com/yourusername/Jarvix.git
cd Jarvix

2️. Install dependencies

```bash
pip install -r Requirements.txt

3️. Set up environment variables

• Create a .env file in the project root

• Add your API keys:

  • COHERE_API_KEY=your_key_here

  • GROQ_API_KEY=your_key_here

  • HF_API_KEY=your_key_here

4️. Run the application

```bash
python Main.py

System Architecture

(Make sure to replace architecture.png with your actual diagram file)

Screenshots

• GUI

• ChatBot

  

• Image Generation Output

  

• Speech to text

  

How It Works

• User provides voice or text input

• Input goes to SpeechToText (if voice)

• Model.py decides whether it’s a chatbot, search, automation, or image request

• Executes task through the respective module

• TextToSpeech + GUI present results

• All data saved to Data folder

Future Enhancements

• Internet of Things (IoT) device control

• Advanced behavioral learning or emotional intelligence

• Offline LLM support

• Multi-user profiles

• Calendar & email automation

• Mobile deployment

Contributing

Pull requests are welcome! For major changes, please open an issue first to discuss what you’d like to change.

License

This project is licensed under the MIT License.