Vision + Speech + Text. A multilingual personal tutor that can see what is on the page or screen, listen to questions, speak clear explanations, and write step-by-step answers on demand.
Tech Stack
Local LLMNVIDIA RTX 4070 SuperOllamaTTS/STTVision AI
Access full source code & live demo
This project's overview, tech stack, and demo are open. For full source code access, live walkthrough, licensing, collaboration, or custom builds, please get in touch:
[email protected]