ViS

Inspiration

Conference talks can be a bit lengthy and boring, and other things too.

What it does

Takes a video and summarises its content into a few paragraphs of text.

How I built it

Google Cloud

Challenges I ran into

Figuring out how to grab a video from multiple sources, how to split the video into separate streams, transcode the audio stream into WAV and then summarise using NLP.

Accomplishments that I'm proud of

Finishing on time.

What I learned

Google Cloud Platform is rather simple to get up-and-running with, and it's very possible to build a distributed architecture quite quickly with it.

What's next for ViS

A great UI, maybe a bit of productionizing so that we can all start using this personally.

Built With

• google-cloud-functions
• google-speech-to-text
• python
• pytube