In today’s digital era, voice-based technologies are transforming the way users interact with computer systems. However, traditional interaction methods such as keyboards and mice are still widely used, which require manual effort and time. To overcome these limitations, this project presents JARVIS: Voice Assistant System, an intelligent platform that uses speech recognition and artificial intelligence to perform tasks through voice commands. The proposed system integrates multiple functionalities such as voice input processing, command execution, real-time responses, and web-based interaction. The system captures user voice, converts it into text, processes the command using Python, and provides output either in text or voice format. JARVIS can perform various operations such as opening applications, searching the internet, providing time and date information, and answering general queries. The system is developed using HTML, CSS, and JavaScript for frontend and Python for backend processing. The results show that the system improves user interaction, reduces manual effort, and provides a faster and more efficient way of performing tasks. It is a cost-effective, user-friendly, and scalable solution for modern intelligent systems.