Gamer Jaws

Inspiration

We were inspired by the limited funcitonality of the normal text-to-speech softwares you could find online and their low compatability with video games.

What it does

What our project does is take a screenshot when you press a shortcut key designated yourself, which would then be sent to our AI, who would then analyze the image and give you information about your setting and allow you to make your choices and know your setting.

How we built it

We built it using some help from GitHub copilot while also using Python Flask for the backend with the API and using C++ for most of the frontend.

Challenges we ran into

One challenges we ran into, getting into the specifics, was parsing the raw JSON files. Raw JSON files include unnecessary clutter that would be said by our software, possibly making it harder for the user to understand what the software is saying or making the process unnecessarily long. We resolved this by creating an algorithm to extract the specific style of the JSON file it was outputting. Taking it out would leave only the text we wanted to be said.

Accomplishments that we're proud of

We're proud of what we did over this course of around 2 days. We had fun and enjoyed the process and we're overall proud of actually finishing the project.

What we learned

We learned that being in a team and collaborating is the best way to have fun, enjoy the process, and make new friends.

What's next for Gamer Jaws

In the future, Game Jaws wants to be able to expand our functionality by removing some barriers between the software and the user, and allowing the user to speak directly to the software, which would allow them to have real-time faster responses and to be able to know their setting better.