Full-Stack • 2024
EchoLens
A Chrome extension prototype that turns a selected image into a generated description and speech audio.
My Role
Built the extension and Flask integration with two teammates.
Team Size: 3 people
Problem
Images with missing or incomplete text descriptions can be difficult to access using assistive tools. The prototype explores an image-description workflow in the browser.
Approach
Connected a JavaScript extension to a Flask backend, which describes a selected image with a vision model and returns text-to-speech audio.
Impact
Demonstrated an image-to-audio interaction during a team hackathon build. Accessibility benefits and description accuracy were not established through a user study in the supplied evidence.
Technologies
JavaScriptChrome ExtensionsPythonFlaskVision ModelsText-to-Speech