Inspiration: We drew inspiration from the degrading eyesight of our grandparents that comes with their age. To be able to help with vision loss, especially when they are not fully comfortable on the internet, either. With this in mind, we aimed to develop a product that meets the needs of our modern society and enables us to bridge the gap between visually impaired individuals and interpreting images through text-to-speech technology.
What it does: Our product is a browser extension that allows visually impaired people to use a text-to-speech functionality to interpret images summarized by OpenAI’s API. We built a website to act as a demo and advertising for our extension, which provides a download link to the extension.
How we built it: We built our website with the help of MeDo, and for the extension, we used Manifest v nd GenAI.
Challenges we encountered: Some challenges we encountered include the format of images and how images were sent to the OpenAI backend. Along with this, we also had problems storing tuthepenAI API key.
Accomplishments that we're proud of: Overnight, we were able to create aa productthat emphasized something we were passionate about. Whether we win or not, this is an application that we will further develop to help our families.
What we learned: We learned how to use different applications to integrate into our application, but also what it takes to safely store an API key to keep in a running application that is published as a Chrome extension
What's next for DescribeIt: We want to have DescribeIt be integrated with other kinds of applications that allow it to help all kind sof disabilityes, like ADHD, dyslexia, and other disabilities that don't allow for smooth usage of the internet.
Log in or sign up for Devpost to join the conversation.