Minutia

Automated Minutes Taker for Meetings

Comment

Inspiration

We have all attended a lot of meetings in our lives. What if we could keep track of it all and the action items. What if we could see the contribution of each person. What if we could track everyone's mood throughout the meeting. This is what Minutia meant to do.

What it does

It automatically transcribes and analyses the meetings (both face-to-face and online). It also provides the mood, contribution levels and action items for each meeting.

How we built it

Frontend

React and material-ui were used to create the user interface.

Database

We used Firebase as our real-time database. This is due to the real-time requirements of the app. Using Firebase saved a lot of time and added useful functionalities.

Transcription and NLP

Transcription was done through Google Speech to Text API. The audio is recorded from the frontend application is sent through to the API. NLP is used to analyse the mood of the conversations as well as actions and other attributes.

Challenges we ran into

The most challenging aspect of the project was being able to get consistent and accurate results from Speech to Text API. At the end, we decided to increase our threshold so that it would take more time to process but at least the results are more accurate and consistent.

Accomplishments that we're proud of

We're proud that we have been able to create an mvp in 24 hours that is able to to solve a real business problem in today's society.

What we learned

We learned to use new components libraries for React. We also tried various NLP APIs to find the best one for our use case.

What's next for Minutia

Support multiple languages. Have a native app to enhance user experience.

Share this project:

Updates