JARVIS » "Good morning, Sir. All systems are online."
FINKLINK » Awaiting your command...
FINK LINK is your personal J.A.R.V.I.S — an AI-powered voice assistant that gives you complete, hands-free control over your laptop using nothing but your voice.
Just like Tony Stark spoke to JARVIS and the suit responded — you speak, FINK LINK acts.
Built with a purpose: designed especially for people with disabilities so that every human being can use a computer freely, without barriers.
"The most powerful input device ever created isn't a keyboard. It's the human voice."
┌─────────────────────────────────────────────────────────┐
│ SYSTEM MODULE │
├─────────────────────────────────────────────────────────┤
│ "wake up" → Greet + time & date │
│ "take screenshot" → Capture screen → save PNG │
│ "open settings" → Launch Windows Settings │
│ "camera" → Open live webcam preview │
│ "go to sleep" → Shut down assistant │
├─────────────────────────────────────────────────────────┤
│ APPS & MEDIA MODULE │
├─────────────────────────────────────────────────────────┤
│ "notepad" → Launch Notepad │
│ "youtube" → Open YouTube in browser │
│ "music" → Play random local song │
│ "open gpt" → Start Gemini AI chatbot │
├─────────────────────────────────────────────────────────┤
│ KNOWLEDGE MODULE │
├─────────────────────────────────────────────────────────┤
│ "search <topic>" → Wikipedia search + speak │
├─────────────────────────────────────────────────────────┤
│ COMMUNICATION MODULE │
├─────────────────────────────────────────────────────────┤
│ "send whatsapp message" → Prompt number → send msg │
│ "instagram" → Send Instagram DM │
├─────────────────────────────────────────────────────────┤
│ PRODUCTIVITY MODULE │
├─────────────────────────────────────────────────────────┤
│ "set alarm" → Voice-guided alarm setter │
└─────────────────────────────────────────────────────────┘
🎙️ You speak a command
│
▼
SpeechRecognition captures audio
│
▼
Google Speech API → text conversion
│
▼
Python keyword matching engine
│
┌───────┴────────┐
▼ ▼
Simple Command AI Command
(app, alarm, (Gemini chatbot,
screenshot...) Wikipedia...)
│ │
▼ ▼
Execute directly API response
│ │
└───────┬────────┘
▼
pyttsx3 speaks result back to you
│
▼
🔊 "Done, Sir."
Language : Python 3.x
AI Engine : Google Gemini Pro (generativeai)
Speech Input : SpeechRecognition + Google Speech API
Voice Output : pyttsx3 (Text-to-Speech Engine)
Computer Vision : OpenCV (webcam & photo capture)
Screenshot : Pillow / ImageGrab
Wikipedia : wikipedia-python
WhatsApp : pywhatkit
Instagram DM : instagrapi
Date & Time : datetime (built-in)
IoT Ready : Expandable via GPIO / MQTT THE PROBLEM
───────────────────────────────────────────────────────
✗ People with physical disabilities struggle with
keyboards and mice
✗ Traditional computers require full motor function
✗ Existing voice tools are limited & expensive
THE SOLUTION — FINK LINK
───────────────────────────────────────────────────────
✓ Full laptop control via natural voice commands
✓ AI-backed responses — not just keywords
✓ Free, open-source, customizable
✓ 30% of e-commerce already runs on voice search
✓ Connects with IoT to control entire systems
THE IMPACT
───────────────────────────────────────────────────────
♿ Accessibility → Technology for every human being
⚡ Efficiency → Voice is 3× faster than typing
🎯 Convenience → Hands-free multitasking
🤖 AI-Powered → Understands natural language
Step 1 — Clone the repository
git clone https://github.com/SOMU3103/FINKLINK.git
cd FINKLINKStep 2 — Install dependencies
pip install pyttsx3 SpeechRecognition google-generativeai \
Pillow wikipedia pywhatkit opencv-python instagrapiStep 3 — Set your Gemini API key
# In main.py, replace:
genai.configure(api_key="# insert the End point key #")
# With your key from → https://ai.google.dev
genai.configure(api_key="YOUR_GEMINI_API_KEY")Step 4 — Set your music folder path
# In the music() function, update:
music = "C:\\Users\\YOUR_USERNAME\\Downloads\\Music"Step 5 — Launch FINK LINK
python main.py JARVIS » "Welcome back, Sir. FINK LINK is ready."
FINKLINK/
│
├── 🤖 main.py # Core assistant — all commands & logic
├── 📋 requirements.txt # Python dependencies
└── 📖 README.md
COMPLETED ✅
─────────────────────────────────────
[✓] Voice-controlled app launcher
[✓] Google Gemini AI chatbot
[✓] WhatsApp messaging via voice
[✓] Instagram DM automation
[✓] Alarm, camera, screenshot
UPCOMING 🚀
─────────────────────────────────────
[ ] Multi-language voice support
[ ] GUI dashboard — command history
[ ] IoT device control (lights, fans)
[ ] Custom wake word ("Hey JARVIS")
[ ] Mobile companion app
[ ] Face recognition login
git checkout -b feature/new-command
git commit -m "feat: add new voice command"
git push origin feature/new-command
# → Open a Pull Request
⚠️ Never push your API keys or Instagram credentials to a public repo. Use a.envfile andpython-dotenvto keep secrets safe.
pip install python-dotenvfrom dotenv import load_dotenv
import os
load_dotenv()
genai.configure(api_key=os.getenv("GEMINI_API_KEY"))MIT License — Copyright (c) 2026 Somnath (SOMU3103)
Free to use, modify, and distribute with attribution.
╔══════════════════════════════════════════════════════╗
║ Built by SOMU3103 · Team TECH MARVEL ║
║ "Powered by AI. Driven by Voice. Built for All." ║
╚══════════════════════════════════════════════════════╝
⭐ Star this repo if FINK LINK inspired you — it means the world!
🤖 — "Your voice is the new keyboard." — 🎙️