Inspiration
As a team we started with the assumption that it was difficult for non-native English speakers to fully understand a lecturer while they speak. To bridge the language barrier, we create a website that seamlessly translates and returns the spoken words into text for users to better understand.
What it does
By selecting the speech-to-to-text button, a user can speak and the text will appear on screen. Then the text will be saved directly on the page.
How we built it
We built this webpage using HTML for the front end and built the Speech to Text application in Javascript Using Web Speech Recognition API for the backend.
Challenges we ran into
Time constraint. Connecting backend to frontend.
Accomplishments that we're proud of
Getting the api call to run and translate our words was a huge win. Additionally, communication in our group was highly effective and made the whole project a joy to work on, with all the pieces moving smoothly together. Lastly, building out the account capabilities so the user is able to save the documents that have already been translated.
What we learned
We received hands-on experience utilizing an API and learned a lot about the different functions that the speech recognition API has to offer. We also learned more about the full stack development necessary to merge the front and backend components.
What's next for LazyLad
We plan on expanding this tool to transcribe other languages.
Log in or sign up for Devpost to join the conversation.