When a professor uploads an image of text, whether it's a page of a book or their handwritten notes, it is not accessible to those who are visually impaired. At the University of Washington, students with visual impairements often come to UW staff with academic materials on which they can't use text-to-speech, and these staff members type up the documents by hand for each individual student.

Now with A11y Text, these students can upload all of their academic materials as PDFs, JPGs, or PNGs and download versions they can use in a simple text file. Try it out!

Built With

Share this project:


posted an update

Main features of A11yText Version 1.0

  • combines OCR and Handwriting, adding a toggle button to switch between the two
  • makes uploading from both online url and local sources compatible with both analysis types
  • PDFs can both be analyzed with OCR and Handwriting
  • downloaded files are logically named for easy organization
  • adds a text box to see current status of the text conversion
  • improves UI to be more intuitive and seamless
  • removes unused code
  • adds documentation

Log in or sign up for Devpost to join the conversation.