What inspired us?

If you are a non-native speaker getting an english medium education, you are 3 times more likely to drop out. We set out to change that. Language should never be a barrier to learning.

What did we learn:

We became cognizant of the fact that your socio-economic status directly impacts your education outcomes. We want to bridge that gap using AI and computer vision.

Challenges we faced

  1. Working with computer vision and making it cross-language and cross-input type were one of the hardest challenges
  2. Incorporating OCR and text-to-voice for a variety of languages was an interesting challenge to solve

How does it work?:

  1. Provide skim and detailed summaries of text, pdfs, docx, images, and voice in any language to aid students with their quest to learn
  2. Provide AI generated visual learning tools to help children learn languages or topics.
  3. Provide a mini-podcast where you can listen to what you are learning.
  4. Provide object detection computer vision tools for younger children to help them learn about the world around them
  5. Completely language and age customizable.

How can I use it?:

  1. Upload textbook/notes/book in any format and get a skim or detailed summary with images and voice to aid learning.
  2. Upload recording of lecture to get a skim or detailed summary with images and voice to aid learning.
  3. Learn a new language visually by getting labeled images

Built With

Share this project:

Updates