Readdit

Inspiration

We wanted to create a device that would help deaf people communicate in real-time with others.

What it does

It transcribes and labels speakers in conversations.

How we built it

We integrated a python backend with Rev-AI, flask, and HTML/CSS/JS. The python backend continually listens to the conversation and performs speech-to-text conversion and detects the speaker, while the frontend listens for data sent by the backend.

Challenges we ran into

It was difficult to interface the backend and frontend, and also to work with the Rev-AI API, as the python version used generators, and so it was hard to interface the library with other parts of our code.

Accomplishments that we're proud of

We're proud that we were able to fit all the pieces together and create a working MVP.

What we learned

We learned a lot of new things, i.e. sockets.

What's next for Readdit

We would like to improve the voice recognition aspect, as well as add more features to personalize the product and improve the UI.

For judging: table C4

Built With

• css
• flask
• html
• javascript
• mfcc
• python
• rev-ai
• sklearn