AI Desktop Assistant

JARVIS

Python Flask Socket.IO Voice AI Groq API Gemini API Desktop Automation LLM Tool Calling
JARVIS — AI Desktop Assistant
Overview

JARVIS is a custom-built AI desktop assistant designed to control everyday computer tasks through natural voice and text commands. It combines real-time voice recognition, text-to-speech, desktop automation, web search, file handling, system controls, and an interactive web-based interface into one productivity-focused AI tool.

Built with Python and powered by a Flask + Socket.IO interface for real-time communication, JARVIS can open applications, search the web, check weather and news, manage files, control system settings, run commands, set timers, take screenshots, and respond through a natural voice interface.

The goal was to build a practical AI assistant that functions as a real desktop copilot. Instead of only answering questions, JARVIS interacts with the operating system, automates repetitive actions, and provides a hands-free workflow for daily computer use. LLM-powered tool calling with Groq and Gemini enables flexible, context-aware task handling beyond simple command routing.

Voice Control
Natural voice commands with real-time speech recognition and text-to-speech response via edge-tts and pyttsx3.
System Automation
Controls volume, brightness, Wi-Fi, disk info, screenshots, and system status through Windows automation.
Web Interface
Flask + Socket.IO browser-based interface for real-time communication alongside background voice mode.
LLM Tool Calling
Groq and Gemini APIs handle flexible task routing — local commands fire first, AI handles the rest.
File Management
Search, open, and navigate files and folders through voice or text without touching the keyboard.
Smart Commands
Built-in tools for web search, weather, news, definitions, app launching, and website shortcuts.
Category
AI Desktop Assistant
Services Delivered
AI Agent Development
Voice Interface
Desktop Automation
LLM Integration
Stack
Python
Flask
Flask-SocketIO
SpeechRecognition
sounddevice
edge-tts / pyttsx3
psutil / pycaw
Groq API
Gemini API
Windows Automation
Type
Personal Project
Want an AI system
built for your workflow?