While closed captioning (auto-generated or not) is an available option on YouTube, it is not accessible for every video (ex: older videos). Some people prefer to have captioning on, whether they are learning a language, are hard-hearing, or just prefer to read subtitles along with the video. Others may be situated in loud environments, or maybe they left their earbuds at home; either way, they want to know the contents of the video they want to watch. That's where the video transcription idea came in -- so you can watch your video through words.

What it does

This app takes a video file (.mp4) as an input and generates a text file of the transcribed video.

How we built it

Watch as Words was built using C#, the Microsoft Bing Speech API, and Visual Studio.

Challenges we ran into

We struggled a lot with implementing the API and we had a lot of issues with the GUI.

Accomplishments that we're proud of

It works!!!!

What we learned

Neither of us knew C# nor did we have experience with implementing APIs prior to this hackathon; after thorough research, it is safe to say that, as a group, we definitely have a lot to take away.

What's next for Watch as Words

The next steps would be to move it to the web, and possibly add in a feature to take YouTube links as an input. Some other great add-ons would be to have the option to send the transcript to an e-mail address.

Share this project: