Vocalis

Become a better public speaker!

Comment

Inspiration

As a student there’s always a presentation, meeting, or speech that we must get ready for. One of our team members was a debater in high school and they struggled with having an efficient and confident approach to their argument. They had too many uh’s and um’s that caused them to lose a few points. Additionally, following traditional methods of speech feedback (like asking your friend to listen to you) can be an inconvenient scheduling process. Your friend cannot be readily available to listen to your speech, and he/she may not even give you the brutally honest feedback you are seeking. Besides, there are only so many times another human will be willing to listen to your speech over and over again.

This is why we built Vocalis, an app that leverages artificial intelligence to help students enhance their speaking skills anytime, anywhere.

What it does

Vocalis is a web app that allows users to upload an audio file containing their speech. Using Symbl.ai, the web app then analyzes and generates insightful feedback for the user based on the uploaded audio. Not only does Vocalis generate a transcript of the user’s speech -- it goes even further by providing statistically sound analysis featuring metrics like the number of words per minute spoken by the user, the number of filler words used, etc.

How we built it

For our front-end, we were using: Next.js for our front-end/back-end framework, and Chakra UI for our front-end framework UI library. Framer motion for animation on our web app. Typescript for our language used for this entire web app.

For our Backend, we utilized Typescript. We also used the Symbl.ai API to generate the detailed analytics of the speech. We also used PostGreSQL as our database.

Challenges we ran into

Integrating the backend analytics with the frontend Lots of pesky issues with regards to the design

Accomplishments that we're proud of

Successful integration of the frontend and backend Aesthetically pleasing and easy-to-use UI Detailed and tailor-made speech analytics Unique project concept

What we learned

Learned how to work with the Symbl.ai API, specifically how to process audio files, retrieve raw analytics from the API, and extract useful insights from these raw analytics How to work with the Google Drive API for storing and retrieving audio files Sharpened frontend, full stack, and backend development skills

What's next for Vocalis

Ability to store audio files natively Ability to receive emails with analytics Finished meeting component for industry professionals

Built With

Share this project:

Updates