JARVIS is an AI-powered desktop voice assistant inspired by the fictional assistant from the Marvel Cinematic Universe. The system is designed to interpret and respond to natural language voice commands, enabling hands-free interaction with desktop applications and services. It seamlessly integrates speech recognition, text-to-speech, and automation capabilities to offer a responsive and intelligent user experience.
This project is built in Python3, and the GUI was designed using QT Designer.
This application can be used by any user to perform operations in the system using voice as an input and this is possible with the help of Speech recognition where JARVIS utilizes advanced speech recognition technology to understand user commands accurately.
1. Voice Command Processing: Recognizes and processes real-time user voice input using natural language.
2. Task Automation: Executes tasks such as launching applications, retrieving information, setting reminders, and more.
3. Interactive GUI: Developed using Qt Designer, providing an intuitive and user-friendly interface.
4. System Control: Capable of performing system-level operations like opening files, folders, or managing utilities.
5. Information Retrieval: Answers general queries using integrated APIs and logic-driven modules.
It Can do a lot of cool things, following are the cool features of this application;
1. Greet User.
2. Tell us the current time and date.
3. Launch application/software.
4. Find Ip Address of the device.
5. Find location of the user.
6. Open any website.
7. Open YouTube and search according to the user.
8. Send WhatsApp Messages to anyone.
9. Control Music system.
10. Tell us about device battery information.
11. Tell us about any person(via wikipedia).
12. Switch the window and return back to the main window.
13. Take important note in notepad.
I will add some more cool features in futures.
├── driver
├── Jarvis # Main folder for features
│ ├── config # Contains all secret API Keys
│ ├── features # All functionalities of JARVIS
│ └── utils # GUI images
├── __init__.py # Definition of feature's functions
├── gui.ui # GUI file (in .ui format)
├── main.py # main driver program of Jarvis
├── requirements.txt # all dependencies of the program
- The code structure if pretty simple. The code is completely modularized and is highly customizable.
- To add a new feature:
- Make a new file in features folder, write the feature's function you want to include
- Add the function's definition to init.py
- Add the voice commands through which you want to invoke the function
Contributions are welcome! Feel free to fork this repository, make improvements, and submit pull requests.
Together, let's make this voice assistant even more powerful and versatile.
This project is licensed under the MIT License 2024 Faisal Khan
If you like this project don’t forget to 🌟 the repository and Clone this repository, start using jarvis😎.