██╗ █████╗ ██████╗ ██╗ ██╗██╗███████╗
██║██╔══██╗██╔══██╗██║ ██║██║██╔════╝
██║███████║██████╔╝██║ ██║██║███████╗
██ ██║██╔══██║██╔══██╗╚██╗ ██╔╝██║╚════██║
╚█████╔╝██║ ██║██║ ██║ ╚████╔╝ ██║███████║
╚════╝ ╚═╝ ╚═╝╚═╝ ╚═╝ ╚═══╝ ╚═╝╚══════╝
MARK VII — IRON MAN HUD EDITION
Just A Rather Very Intelligent System — now with a real HUD
"Sometimes you gotta run before you can walk."
◈ ─────────────────────────────────────────────────── SYSTEM STATUS ── ◈
VOICE ENGINE ██████████ ONLINE
SPEECH INPUT ██████████ ONLINE
CLAUDE API ██████████ CONNECTED
HUD INTERFACE ██████████ ACTIVE
◈ ──────────────────────────────────────────────────────────────────── ◈
JARVIS is a voice-enabled AI desktop assistant with a full Iron Man HUD interface — animated rotating rings, live system diagnostics, a cinematic boot sequence, and Claude AI powering every conversation.
This isn't just a chatbot. It's a personal command center that looks like it belongs in Stark Tower.
┌─────────────────────────────────────────────────────────────────────┐
│ ◈ JARVIS // MARK VII ◉ CLAUDE API │
├────────────────────┬────────────────────────────────────────────────┤
│ │ // INITIALIZING J.A.R.V.I.S MARK VII ... │
│ ╭──────────╮ │ // ALL SYSTEMS NOMINAL. WELCOME BACK. │
│ ╱ ◉ ◉ ◉ ╲ │ │
│ │ ─────── │ │ [22:41:05] JARVIS ▶▶ │
│ ╲ ─ ◈ ─ ╱ │ ┃ Good evening. How can I assist you today? │
│ ╰──────────╯ │ │
│ │ [22:41:18] YOU ▶▶ │
│ [ SYSTEM ONLINE ] │ ┃ Open YouTube │
│ MODE: STANDBY │ │
│ ───────────── │ [22:41:18] JARVIS ▶▶ │
│ CPU ████░░ 42% │ ┃ Opening YouTube for you, sir. │
│ RAM ██████ 61% │ │
│ PWR ████████ 82% │ ───────────────────────────────────────── │
│ ───────────── │ ▶ INPUT: [________________] [🎤] [TRANSMIT] │
│ 22:41:24 │ │
│ SUNDAY 19 APR │ │
└────────────────────┴────────────────────────────────────────────────┘
◉ ANIMATED HUD RING Rotating arcs that change color based on
Jarvis's current state — cyan (standby),
orange (thinking), green (listening)
◉ LIVE SYSTEM STATS Real-time CPU, RAM, and battery bars
powered by psutil — updates every 1.5s
◉ BOOT SEQUENCE Cinematic line-by-line startup animation
like a real system initializing
◉ CLAUDE AI BRAIN Every unrecognised command goes to Claude
Sonnet with full conversation memory
◉ VOICE INPUT Speak to Jarvis — Google Speech API
transcribes and processes your command
◉ TEXT-TO-SPEECH Jarvis talks back — offline via pyttsx3,
no internet needed for voice output
◉ SMART FALLBACK Built-in commands run instantly (no API),
everything else routes to Claude
◉ TIMESTAMPED LOGS Every message tagged [HH:MM:SS] — looks
and feels like a real terminal
┌──────────────────────┐
│ USER INPUT │
│ (Type OR Speak) │
└──────────┬───────────┘
│
┌────────────────────▼─────────────────────┐
│ main.py │
│ Iron Man HUD Interface │
│ tkinter + customtkinter + canvas rings │
└───────┬─────────────────┬────────────────┘
│ │
┌─────────────▼──┐ ┌────────▼────────────┐
│ voice.py │ │ command.py │
│ │ │ │
│ pyttsx3 (TTS) │ │ Built-in commands │
│ SpeechRecog │ │ ───────────────── │
│ (microphone) │ │ time / date │
└────────────────┘ │ open youtube │
│ search google │
│ calculator │
│ jokes │
└────────┬─────────────┘
│
MATCH FOUND?
│ │
YES NO
│ │
INSTANT ┌────▼────────────┐
RESPONSE │ api_client.py │
│ │
│ Anthropic SDK │
│ Chat history │
│ (last 20 msgs) │
└────┬────────────┘
│
┌─────────▼──────────┐
│ Anthropic Cloud │
│ claude-sonnet-4 │
└────────────────────┘
│
┌───────────────▼───────────────┐
│ Response → Chat bubble + TTS │
└───────────────────────────────┘
| Module | Library | Why |
|---|---|---|
| HUD Interface | tkinter + customtkinter |
Native Python GUI — no browser, no Electron |
| AI Brain | anthropic SDK |
Official Claude API with conversation history |
| Text-to-Speech | pyttsx3 |
Fully offline TTS — works without internet |
| Voice Input | SpeechRecognition |
Google Speech API via microphone |
| Microphone Access | pyaudio |
Low-level audio capture |
| System Stats | psutil |
Real CPU / RAM / battery readings |
| Secrets | python-dotenv |
API key never touches source code |
- Python
3.10+ - A microphone
- Anthropic API key → console.anthropic.com
# 1. Clone the repo
git clone https://github.com/YOUR_USERNAME/jarvis-ai.git
cd jarvis-ai
# 2. Create virtual environment
python -m venv venv
venv\Scripts\activate # Windows
source venv/bin/activate # macOS/Linux
# 3. Install all dependencies
pip install -r requirements.txt
# 4. Set up your API key
cp .env.example .env
# Open .env and add: ANTHROPIC_API_KEY=sk-ant-...
# 5. Launch
python main.pyWindows — pyaudio install fail?
pip install pipwin && pipwin install pyaudio
| Command | Action |
|---|---|
hello / hi / hey |
Time-aware greeting |
what time is it |
Current time |
what's today's date |
Full date |
search [anything] |
Google search in browser |
youtube search [query] |
YouTube search |
open youtube / open github |
Opens in browser |
calculate 99 * 12 |
Quick math |
tell me a joke |
Programmer joke |
bye / exit |
Closes Jarvis |
Anything not matched above:
You: "Explain how neural networks work"
You: "Write a Python function to sort a dict by value"
You: "What did we talk about earlier?" ← it remembers!
You: "Translate this to Hindi: ..."
Change Jarvis personality → api_client.py:
SYSTEM_PROMPT = """You are JARVIS... (rewrite this however you want)"""Add a new command → command.py:
if "open spotify" in q:
webbrowser.open("https://open.spotify.com")
return "Opening Spotify, sir."Change voice speed → voice.py:
_engine.setProperty("rate", 175) # higher = fasterChange ring color scheme → main.py palette section:
CYAN = "#00d4ff" # change to any hex
ORANGE = "#ff6b1a" # thinking color
GREEN = "#00ff88" # listening colorjarvis-ai/
│
├── main.py // Iron Man HUD — UI, animations, layout
├── command.py // Built-in command handler
├── voice.py // TTS (pyttsx3) + STT (SpeechRecognition)
├── api_client.py // Claude API + conversation history
│
├── .env // 🔑 secret API key
├── .env.example // Template
├── .gitignore
├── requirements.txt // All dependencies
└── README.md // This file
○ Weather widget in sidebar (OpenWeatherMap API)
○ Spotify playback controls
○ Chat history saved to JSON file
○ Wake word detection ("Hey Jarvis...")
○ Multiple AI personas / personality switching
○ Custom hotkey to activate voice input
MIT License — build on it, break it, ship it.
If it helped you, leave a ⭐
◈ ─────────────────────────────────────────────────────────── ◈
BUILT WITH PYTHON · INSPIRED BY TONY STARK'S J.A.R.V.I.S
◈ ─────────────────────────────────────────────────────────── ◈