Introduction to Videopipe

An overview of the possibilities for you.

Videopipe is the Data Science video-AI pipeline, with the goal of automating tedious tasks using AI to leave you more room for creativity 🧑‍🎨, or otherwise enhance your creative process. Our pipelines includes tasks like marking midrolls, thumbnail selection, and automatic subtitling (amongst others), which are already actively being used in different parts of RTL!

⁠

Videopipe for Editors

🌟 Certain relevant features from Videopipe are now ready for use via your Avid Media Composer! You can drop in a video, and within minutes receive the output back in your dropbox. Read below for what we have for you 🥁

You can send us input for the following tasks:

⁠

Automatic Subtitles⁠

: Generating Dutch subtitles for videos.

⁠

Audio Splitter⁠

: Splitting audio into speech and music.

New features coming soon!

(Psst! Read more about the individual modules by clicking on the hyperlinks)

⁠

🔧 HOW DOES IT WORK?

After working together with the tech architecture team, there is now an export button from your media composer straight to our pipeline. Hence, you can send in videos to trigger the tasks and after a short time receive the output file back in your dropbox.

What does it look like?

On the right is an image showing your avid environment. You can send us videos via the “Send To Playback” button. Read more about this, and the usage of these features under

Automatic Subtitles⁠

and

Audio Splitter⁠

⁠

📞 Contact

For more information about Videopipe and to use it in your projects, please contact the Data Science team or ask in the Slack channel

#data-engineering-and-science⁠

. Do you have new ideas that you would like to see integrated in Videopipe? Let’s discuss it!

Want to print your doc?
This is not the way.

Try clicking the ⋯ next to your doc name or using a keyboard shortcut (

CtrlP

) instead.