Our initial goal is to build something that can spread positivities among people, and something fun for people to use as well.
What it does
It reads sound from a file and analyzes the emotions implicated by the sound of the users. The panda's facial expression is going to change according to the category of the most significant emotion, and the users can see the detailed analysis of their emotions. When users express positivity when they are speaking, the score is going to increase.
How we built it
We use Android Studio along with IBM Watson Tone Analyzer and Google Speech APIs to implement our design.
Challenges we ran into
We had trouble enabling user to input their voices through microphones, because the APIs work mostly with high-quality audios such as those in the FLAC form.
Accomplishments that we're proud of
Our idea and UI design are very user-friendly and intuitive. We have designed something that bears positive social meanings and fun for people to use, which are our original goals.
What we learned
We have learned to make more efficient use of APIs through our development, and we have also enjoyed iterating on our design constantly to make it better.
What's next for Voice Panda
We are trying to fix the microphone problem, and want to add more deterministic features to better analyze input voices' emotions, such as the decibels and frequencies of the sound. Our main goal for the near future is to build a social interaction feature that enables users to interact each other online and spread positivity through this App (specifically, if one user says something positive to the other user, their score will raise together by a larger amount than they interact with their Apps alone). The panda will also grow as its growth point increases.