Custom Workout Clip Finder

This photo shows the landing page of the application allowing users to choose their preferences for workout video clips

Inspiration

Inspired by the inability to find great workout videos tailored to specific needs on YouTube without searching through dozens of videos to find the right clips, we decided to build an application that will allow you to customize what you are and aren't looking for in an application.

What it does

Users can simply chooses from drop-down lists what they would like to see and what they would like not to see in their workouts, and videos will be shown that, once clicked on, will play from specific timestamps that match the user's requirements.

How we built it

We built this application using the TwelveLabs API to index and search a library of supplied videos, OpenAI, Python, CSS and HTML to code the application, and Streamlit to design and build the application.

Challenges we ran into

We ran into challenges designing certain elements, ensuring high visibility for low vision users, and ensuring we had the right wording in order to pull the right video clips for users.

Accomplishments that we're proud of

We are proud to have gotten the project to the point where users can choose from the dropdown lists and see embedded videos that play from the specific timestamps that fit their needs.

What we learned

We learned more about the inner workings of python, how HTML and CSS can and cannot be integrated with Python, and the struggles of working with APIs and embedding indexed videos onto your own application.

What's next for Custom Workout Clip Finder

Next we would like to add more video clips that add a larger range of disabilities, injuries, or other workout obstacles so that more people can enjoy and benefit from the use of our application. We would also like to add the ability to bypass the drop-down boxes and write a custom search query, for those who either have extremely specific requirements or simply prefer to type their prompts.