Hi HN,
University lectures are long, dense, and fast-paced. Like many students, I used to record them thinking I’d revisit them later — but that never really worked. Even transcripts felt like raw logs.
So I built [Notorium](https://www.notorium.app) — an AI assistant that records live lectures and automatically turns them into structured notes, flowcharts, and mind maps— within minutes after class.
What it does:
- Record lectures inside the app (in-person, live)
- Transcribe using Whisper
- Send the full transcript to LLM
- Use a custom system prompt to:
- Summarize the lecture
- Break it into topics
- Generate visual aids: flowcharts and mind maps
Extras:
- Download notes as clean PDFs
- Tap Simplify to make notes more digestible
- Tap Expand to deepen explanations
- Tag notes by subject (e.g., Physics, CS) for filtering and fast retrieval
Built for
- In-person learners
- Visual learners (flowcharts, concept trees, diagrams)
- Students who want control — skim when you're tired, expand when you're focused
Coming soon:
A spaced-repetition-based flashcard mode — so you can actively review and retain the key points from your lectures.
Tech Stack:
- Transcription: Whisper
- LLM: Open source model via Groq
- Frontend: Next.js + Tailwind + shadcn/ui
- Backend: Firebase
Why Groq?:
Speed and consistency. Fast enough to generate full notes right after class ends.
Would love your feedback:
- What other visual formats or study modes would help?
Thanks!
– Pranav
