FAQ / Video & Stream Moderation

How does Video Moderation work?

Our Video Moderation solution is entirely automated. There are no humans in the loop, meaning that no Human Moderators will be used to view and rate your videos. This is important to achieve a very quick turn-around times, high scalability while guaranteeing privacy.

With Video Moderation, you simply submit a video to our API along with the list of content you want to flag. Our API will then start consuming this video and look for any objectionable content.

Our API will analyze the video in near real-time and use our state-of-the-art detection models to detect and describe any unwanted content. Once such content has been found, the API will provide you with a description so you can easily find where such content was found in the video and also know exactly what the API found.

Depending on your needs, you can then fetch moderation results in different ways:

  • directly in the request response, if your video is short enough
  • through a call-back mechanism, meaning that our API will send moderation details and alerts to your own servers
  • by polling our API for moderation results

Please head to the documentation for more details on those options and on the callback format and conditions to trigger a callback.

Did you find this page helpful?

We're always looking for advice to help improve our documentation!

Let us know what you think