Project Info

Texty Bear

Devpost

Inspiration

Life is tough and sometimes you don't have time to watch full lectures. Texty Bear allows you to still learn that information in a fraction of a time.

What it does

By submitting a YouTube lecture URL, Texty Bear will automatically look for key points within the lecture and create notes just for you!

How we built it

We utilized the PyTube python package and AssemblyAI to parse YouTube files into notes for our backend. For our front end, we used Flask to incorporate Python scripts into our HTML.

Challenges we ran into

This our our first Hackathon so there are many challenges :). Here are some of our major ones: Git version control Trouble learning the Flask package and how it interacts with HTML Tight deadlines with little project experience(skill issue) It's very cold here... Had to pivot from our original idea as it wasn't feasible to do ##

Accomplishments we're proud of

Cute website aesthetics Learned new packages and libraries Fixed many bugs :) Gaining real-life experiences with working in a team and with tight deadlines ##

What we learned

Learned Flask AI is easier to use than I thought... I finally fixed my Python virtual environments :D ##

What's next

Allow users to upload both media files and YouTube URLs Use and train our own model to take better, more concise notes Continue improving UI/UX of our website Optimize Youtube data parser and API calls

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • HTMLIn code
  • PythonIn code
  • FlaskClaimed

3 of 4 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

16 KB

Source files

9

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars