TextSavvy

GUI 1
GUI 2
Context Menu
Translation

Inspiration

The internet may feel seamless and accessible to us, but that’s not the case for everyone. For many people with disabilities, whether visual, auditory, cognitive, navigating websites can be frustrating, confusing, or even impossible.

Our childhood friend is dyslexic, and we wanted to implement something that could help people like him navigate their way through the internet.

Growing up, we had a childhood friend who was colourblind and dyslexic, and we saw how they struggled to read large bodies of texts online. Overall surfing the web was just not the easiest for them.

Being left out of something as essential as the internet, a space where we work, learn, socialize, and access services is more than an inconvenience. It’s exclusion.

It sends a subtle but powerful message: This space wasn’t made for you.

Digital accessibility isn’t just a feature. It’s a right. And it’s our responsibility to recognize that the privilege of smooth online access isn’t universal, and that's why we decided to do something about it.

Functionality

Our chrome extension TextSavvy is focused on improving user accessibility features on all websites. TextSavvy has the capabilities to adjust the font size, letter spacing, translate text, and text-to-speech with a simple click of a button. Additionally, we have a variety of fonts and support 10+ translation languages.

Furthermore, we have additional capabilities such as "Dyslexia Mode", which changes the font to Open Dyslexia and adjusts the font sizing and letter spacing to cater to individuals with dyslexia and improve their reading experience. We also have a "colourblind mode" to improve the user experience for individuals with colour-blindness by adjusting the colours on the webpages to be easily distinguishable.

Building Process

We built our chrome extension using Manifest V3. For our frontend, we used HTML/CSS, and Javascript for the backend. To implement our AI features, we used Cohere's LLM API and Web Speech API for text-to-speech.

Key Challenges

We really struggled with getting the Cohere API to connect with the chrome extension. It took us over 8 hours to properly establish a connection with chrome, and many more to make the simplification and translation parts work correctly and efficiently.

Accomplishments

Highlight and right click to translate/simplify/text-to-speech feature
How smoothly everything runs
Customizability
Intuitive, user-friendly, and user-accessible UI

What We Learned

How to connect with API's properly
How to navigate through numerous Git conflicts
How to build a chrome extension
How to stay calm under pressure
How to pull an all nighter
Need to have autosave on
The importance of user accessibility

What's next for TextSavvy

We are looking forward to implementing even more features to further improve user accessibility. Our next goal is to implement an image-text translation feature which will allow the user to translate texts on images into any language while maintaining the image format.

Additionally, we would like to: