Inspiration

The idea was to get summary and subtitles from audio files. We were curious about how powerful Gemini API was with extracting text from audio hence this project. Moreover, as college students we sometimes have to listen to audio for class hence this was a way to enable us to synthesize this information faster.

What it does

The web app takes a audio file and gets subtitles or summary from this audio file.

How we built it

We used react js for the frontend and Flask for the backend.

Challenges we ran into

We struggled with how to process the audio. We were contemplating on where to pass the file in memory of store it on the server. We trying store the file in memory but that did not work casue we can't pass the audio file to Gemini API.

Accomplishments that we're proud of

  • Process audio file correctly.
  • Store file on the server successfully
  • Spinned up a backend with Flask

What we learned

  • Learn about the Flask framework.
  • Learned how to successfully store files to a server
  • Learnt React JS
  • Learnt using Git and Github in more depth (especially making of pull requests and the different types)

What's next for Summary and Subtitles

  • Implement generating subtitles and summaries for Youtube videos
  • Convert this to a plugin for users to use
  • Implement an feature to describe videos in-depth for blind people.

Built With

Share this project:

Updates