YouTube has been introducing a bunch of features in its app lately including player revamp, shorts, autoplay controls, etc. Recently, through a support page it conveyed that it will start testing new features for its player.
The new feature includes YouTube implementing chapters in a video automatically using machine learning. If you don’t know what chapters is, it is a feature that enables creators to segregate their video into different sections depending on their content.
This enables the viewers to quickly skip to the part in which they are most interested in and not have to find it by going through various time stamps. For this Video chapters to work, creators have to mention various time stamps from the video down in the description.
To make the process simple, YouTube is taking advantage of its machine learning tools. YouTube, through a support page states that, ‘We want to make it easier for people to navigate videos with video chapters, so we are experimenting with automatically adding video chapters (so creators don’t have to manually add timestamps). We’ll use machine learning to recognize text in order to auto generate video chapters. We’re testing this out with a small group of videos’.
Read More: Google is working on a rebranded version of ‘Phone by Google’ app, to be called Google Call
This means that the creators will now not have to enter time stamps in the description of their video and YouTube will be doing all the major work itself.
The new feature is available only to a small group of video creators and it will be intriguing to see the accuracy of the feature.
The company is also testing an easier way to add timestamps to videos. YouTube says that they are testing out an easier way to add a video timestamp tied to the exact moment you’re watching when commenting on a video.
Read More: YouTube will now quitely run ads on more videos without paying the creator
People in the experiment will see a new icon as they’rewriting a comment that they can tap to automatically add the current time of the video (without having to manually enter it themselves!). This is only available to a small group of users for now.