Winner of the Maker Award HACKCWRU V 2018
This is a basic image to speech translator Chrome extension using Javascript and Google Vision API.
There are many applications that allow the blind to navigate the internet using text to speech; however, a large portion of the internet is still inaccessible to the blind due to the images.
We have developed a browser extension to solve this issue by intelligently generating and reading out descriptions of images on any web page. The program works by using Google's cloud vision API to find features about images, and then intelligently creating descriptions for them.
Could potentially teach people to read or pronounce things. Little kids could learn to associate images with labels.