How mahitech580/jarvis-ai works
JARVIS is a local voice assistant with a separate browser-based interface. In the desktop workflow, the user speaks, audio is transcribed, intent is detected, commands are handled locally or answered by the built-in conversational engine, the exchange is stored, and the response is spoken. The web workflow sends recognized text to Flask and uses browser speech synthesis for replies. The excerpts show the main orchestration and module calls; unsampled capabilities and configuration wiring are not expanded beyond documented behavior.
Main entry points: app.py Desktop assistant · web_server.py Flask API · script.js Browser interface · database.py Conversation database
Components 13
User interfaces
- Desktop assistant
app.py - Browser interface
web/script.js - Flask API
web_server.py
Conversation processing
- Intent detection
src/intent_engine.py
Assistant capabilities
- Command handling
src/command_handler.py - Local conversational answers
src/ai_engine.py
Conversation state
- Conversation database
src/database.py - SQLite store
data
Speech I/O
- Whisper transcription
src/speech_to_text.py - Speech output
src/text_to_speech.py
Other components
- User
- Browser speech APIs
- Websites and search
Connections 20
- User → Desktop assistant: speaks to
app.py - Desktop assistant → Whisper transcription: listens through
app.py - Desktop assistant → Intent detection: detects intent
app.py - Desktop assistant → Command handling: dispatches commands
app.py - Desktop assistant → Local conversational answers: falls back to
app.py - Desktop assistant → Conversation database: saves exchanges
app.py - Desktop assistant → Conversation database: loads history
app.py - Desktop assistant → Speech output: speaks response
app.py - Whisper transcription → User: captures speech
src/speech_to_text.py - Speech output → User: plays response
src/text_to_speech.py - Command handling → Websites and search: opens or searches
src/command_handler.py - Conversation database → SQLite store: reads and writes
src/database.py - User → Browser interface: uses
web/script.js - Browser interface → Browser speech APIs: recognizes and speaks
web/script.js - Browser interface → Flask API: posts command
web/script.js - Flask API → Intent detection: detects intent
web_server.py - Flask API → Command handling: dispatches commands
web_server.py - Flask API → Local conversational answers: falls back to
web_server.py - Flask API → Conversation database: saves and reads
web_server.py - Flask API → Browser interface: serves interface
web_server.py