Architecture

User (Voice) ↓ Speech Recognition (voice.py) ↓ Command Router (router.py) ↓ Decision Engine (brain.py) ↓ Action Layer ├─ System Control ├─ Vision Engine ├─ Internet ├─ Code Generator ↓ Response Generator ↓ Neural Voice Output (tts_system.py) ↓ Jarvis UI (PyQt Ring + Status)

📦 MODULE BREAKDOWN

1️⃣ Voice Layer

Files:

  • voice.py

  • tts_system.py

Responsibilities:

  • Microphone listening

  • Noise handling

  • ElevenLabs neural voice output

  • Real-time speaking/listening sync


2️⃣ Intelligence Layer

Files:

  • brain.py

  • emotion_ai.py

  • language_normalizer.py

  • memory.py

Responsibilities:

  • AI reasoning

  • Emotion detection

  • Context memory

  • Natural language cleanup


3️⃣ Command Router

File:

  • router.py

Responsibilities:

  • Decide what the user wants

  • Map voice → task

  • Prevent unsafe execution


4️⃣ Action / Execution Layer

Files:

  • input_control.py

  • vision_engine.py

  • internet.py

  • universal_generator.py

Responsibilities:

  • OS automation

  • Screen OCR + clicking

  • File generation

  • Browser & system tools


5️⃣ UI Layer (Jarvis Ring)

Framework: PySide6 (Qt)

Responsibilities:

  • Iron-Man style ring animation

  • Visual feedback (Listening / Speaking / Idle)

  • Native desktop window (taskbar visible)


🛡️ SECURITY DESIGN

  • No background server

  • No auto execution without user command

  • Local-first processing

  • Optional internet access only when needed

Last updated