[HN Gopher] Show HN: I made an AI that turn live lecture into st...
___________________________________________________________________
Show HN: I made an AI that turn live lecture into structured
notes,mind-maps,PDF
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
Author : pranav_harshan
Score : 12 points
Date : 2025-06-02 14:41 UTC (8 hours ago)
(HTM) web link (www.notorium.app)
(TXT) w3m dump (www.notorium.app)
| seany62 wrote:
| Great idea! Will it highlight parts where the professor says
| something like "this is important and will be on the exam...".
| All of the information on the exam (which dictates the majority
| of your score in the class at most US universities) must be
| conveyed to the student one way or the other (worksheets,
| lectures. etc.). A cool runoff would be an "AI Exam Prep" which
| guessed what would be on the exam, based on previous exams and
| where the info came from
| pranav_harshan wrote:
| Great point! Right now it doesn't flag "this will be on the
| exam" moments, but I've been thinking about it. Since we have
| the full transcript, detecting key phrases like that is
| definitely possible.
|
| Flashcards are on the way too -- and tying them to "likely exam
| content" would be super useful. Appreciate the idea!
| dansoto wrote:
| To take this further, allowing the user to define hot items
| or subjects might be better. For example, history tests often
| ask questions about when or where an event happened. Imagine
| if we could request that we want a list of dates and
| associated events.
| sfc32 wrote:
| Is it possible to see an example without signing up?
| dansoto wrote:
| This looks nifty. There is some confusion regarding the "Pro"
| plan.
|
| * 20 hours of recording time
|
| Is that 20 total hours for the month or one transcribing session?
___________________________________________________________________
(page generated 2025-06-02 23:01 UTC)