Projects · 15
JARVIS AI assistant
By Haider Ali ·
JARVIS, by Haider Ali, is a multimodal desktop voice assistant in Python: hot-word speech, screen and webcam vision, web search and Spotify control.
A multimodal, Iron-Man-style desktop voice assistant: hot-word speech, screen and webcam vision, web search and Spotify control. Solo Python build.
2024 · shipped
An Iron-Man-style desktop voice assistant that can see your screen or webcam, search the web and run your music. A solo Python build.
Key facts
- Voice, screen, camera, web, music
- Solo Python build
Listening
- Whisper voice loop with hot words.
- Fuzzy corrections for a misheard “Jarvis”.
- Spoken replies, backed by the OpenAI Assistants API.
What it can do
- Vision: looks at your screen or through the webcam and answers questions about what it sees.
- Search the web and images, and check the weather.
- Control the volume and Spotify.
Stack
- python
- openai assistants api
- whisper
- opencv
- spotify api
#ai #multimodal #agent #python