Inspiration
After countless of hours wasted looking down at my phone when i'm supposed to be working, we've come to the realization that something needs to change. In comes Focal, to change the dynamic of your relationship between you and work.
What it does
Focal is a web-based app that uses your webcam to make sure you always stay focused and locked in. When you look away from your screen you will hear Focal talking to you and making sure you have the accountability to keep working. We used the Gemini API as backup verification of accuracy to make sure the voice doesn't bark at out incorrectly.
How we built it
We've used LiveKit to orchestrate audio input and handling. Overshoot was used to capture camera feed to analyze user attentiveness.
Challenges we ran into
Accuracy of user attentiveness wasn't the best initially, but by using Gemini we were able to increase accuracy.
Accomplishments that we're proud of
We have a functioning working product that checks if you're paying attention at your screen or not.
What we learned
We learned how to use voice models, voice frameworks, and video detection. We've never done a project like this but it encourages us to use LiveKit in future projects.
What's next for Focal
We hope to continue our learning and exploration in voice and video technology and the possibility into turning this into an application people would actually use.
Built With
- gemini
- livekit
- mongodb
- next.js
- node.js
- react
- typescript
Log in or sign up for Devpost to join the conversation.