JARVIS - Intelligent Voice Assistant for Desktop Automation

JARVIS is a voice assistant for desktop
automation, which is designed to simplify computer usage
through voice interaction. Speech-to-Text, a Large
Language Model for command understanding, and Text-to�Speech technologies are used to create a smooth interface
between the user and the computer. Speech is recognized
using a microphone, translated into text using a Speech
Recognition model, and then processed using a Large
Language Model framework, which is implemented using
LangGraph.
The voice assistant is capable of handling various
tasks,such as opening or closing an application, controlling
the computer’s brightness and volume, handling virtual
desktops, controlling YouTube videos, searching the
internet, and checking the number of unread WhatsApp
messages.
It is implemented using a structured tool system, which
helps the model understand the user’s intent and call the
correct function automatically. It also has the capability to
remember the conversation, so it can respond accordingly.
Additionally, it can be interrupted by the user at any time.
The system is implemented using a structured tool system,
which is efficient and scalable.