whatisgithub

What is jarvis-type-ai?

tarikurrahmanbd/jarvis-type-ai — explained in plain English

Analysis updated 2026-05-18

20PythonAudience · vibe coderComplexity · 3/5Setup · moderate

In one sentence

JARVIS is a Python voice assistant for Windows that controls system functions like volume and apps, and answers questions using Google Gemini AI.

Mindmap

mindmap
  root((JARVIS Voice AI))
    What it does
      Voice control of Windows
      Gemini AI answers
      Dual mode switching
    Tech stack
      Python
      SpeechRecognition
      pyttsx3
      Gemini AI
    Use cases
      Hands-free system control
      Conversational AI mode
      App automation
    Audience
      Windows users
      Developers exploring voice AI

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Control Windows system functions like volume, brightness, and apps entirely by voice.

USE CASE 2

Switch to AI Mode to ask Gemini AI questions and get spoken answers.

USE CASE 3

Take a screenshot or lock and shut down the PC using a voice command.

What is it built with?

PythonSpeechRecognitionpyttsx3pyautoguiGemini AI

How does it compare?

tarikurrahmanbd/jarvis-type-aia-shojaei/constructdrawingaialex72-py/aria-termux
Stars202020
LanguagePythonPythonPython
Setup difficultymoderatemoderatemoderate
Complexity3/54/52/5
Audiencevibe coderdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires a Windows PC, several Python packages, and likely a Gemini API key for the AI mode.

No license information is provided in the README.

So what is it?

JARVIS is a Python voice assistant built to control a Windows computer entirely by speaking to it. Unlike simpler assistants, it connects to Google Gemini AI, so it can both carry out system tasks and answer general questions in real time, acting a bit like a voice-controlled version of Siri built specifically for Windows. The assistant works in two separate modes that you switch between with a spoken phrase. Saying Activate System puts it into System Mode, where it can adjust volume and screen brightness, open or force-close apps such as Photoshop, VS Code, Illustrator, and Chrome, take a screenshot and save it to a folder, or even lock or shut down the computer, all by voice. Saying Activate AI switches to AI Mode, where JARVIS instead behaves like a conversational assistant powered by Gemini, giving short spoken answers to whatever you ask. To run it, you need Python installed on your PC, along with several dependencies including pyttsx3 for text to speech, SpeechRecognition for listening to commands, pyautogui and psutil for controlling apps and the system, screen_brightness_control for adjusting the display, and google-genai to connect to Gemini. The README shows the pip install command for these packages but is cut off before further setup steps are shown. Because it directly controls system functions like shutting down the PC or force-closing programs, this project is meant to run locally on a Windows machine you trust with that level of access, rather than in a shared or production environment. This would appeal to Windows users who want a hands-free way to control their desktop and get quick AI answers, as well as developers curious about combining voice recognition with system automation and a large language model.

Copy-paste prompts

Prompt 1
Help me install the Python dependencies needed to run this JARVIS voice assistant.
Prompt 2
Explain how System Mode and AI Mode differ in this project.
Prompt 3
Show me how the voice command for taking a screenshot works in this code.
Prompt 4
Help me add a new app to the list this assistant can open and close by voice.

Frequently asked questions

What is jarvis-type-ai?

JARVIS is a Python voice assistant for Windows that controls system functions like volume and apps, and answers questions using Google Gemini AI.

What language is jarvis-type-ai written in?

Mainly Python. The stack also includes Python, SpeechRecognition, pyttsx3.

What license does jarvis-type-ai use?

No license information is provided in the README.

How hard is jarvis-type-ai to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is jarvis-type-ai for?

Mainly vibe coder.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.