If you've been keeping tabs on your Microsoft Edge news, you'll know that Microsoft announced that Edge Copilot will gain the ability to summarise videos for you. No longer do you need to skip through videos to find the part you want; now you can ask Copilot to do it for you. Now, Microsoft has clarified how Edge Copilot works, and it appears that the feature requires a video to be pre-processed before it can summarise it for you.

Microsoft explains how Edge Copilot's transcription feature works

As reported on MSPowerUser, Microsoft explained on X that Edge Copilot's transcription feature "depends on the video." When asked what that means, it stated the following:

As such, it appears that users won't be able to ask Edge Copilot to summarise any video they please. The video in question must either be processed before the request or contain pre-written subtitles, which may limit how much Edge Copilot can help you.

Microsoft has yet to explain what it means by "pre-processing" a video, or how long it takes to process a video. As such, it's hard to tell if this limitation will severely affect users or not. If it manages to process videos quickly enough, users may not realistically come across a video that Edge Copilot can't sum up.

It does appear that AI isn't quite at the point where it can be fed a video and quickly surmise what it's about without any pre-preparation. However, given how Microsoft is going all in with Copilot (including boosting it with GPT-4 Turbo), it may be a matter of when, not if, AI can watch videos for you.