Video meetings are not made for everybody. In a perfect world, everybody could easily soak up every information, understand what is going on, and continue their day as expected. For someone like myself and others, reading what was spoken could give time to process the information. For someone like my daughter who has ADHD, she could quickly get back to following along after briefly being distracted for a moment.
What it does
This app is a typical video meeting service with separate rooms. Once a meeting starts and someone speaks, the transcription panel will record every spoken dialogue during a meeting and who spoke it using Azure Speech-To-Text AI service.
Once the meeting is done, the video and transcription can be downloaded so users can review their meeting afterwards.
How we built it
We built this with React in the front-end and ExpressJS in the back-end. GraphQL with Redis is the main front-end to back-end/server communication. Azure's Speech-To-Text AI is the star player to help convert spoken dialogue to text and those texts get saved on Redis so users could edit those texts to fix it further.
What's next for Video Meet
The website itself needs to be fully fleshed out. Once that is complete, I would love to add another feature for those that have a video already and want to have an auto transcribed created and editable to export.