In an effort to keep up with the AI race, Microsoft has been scrambling to add new features to its various Copilot tools. Earlier this week, Microsoft Edge Copilot AI received an update that added a useful feature that allowed it to generate text summaries of videos. Not only that, the feature also lets users ask the Copilot questions about the video. The feature is similar to the one Google Bard received a couple of months ago where, through its YouTube extension, it could do similar things. But it appears that just like Google Bard, Microsoft Edge Copilot is also limited in its functionality and can only summarize videos in specific conditions.
A clarification of its limitations comes from an X post by Mikhail Parakhin, CEO of advertising and web services at Microsoft. He said, “In order for it to work, we need to pre-process the video. If the video has subtitles - we can always fallback on that, if it does not and we didn't preprocess it yet - then it won't work”.
It was first reported by MSPowerUser and the article explains the transcription functionality of the Copilot relies on pre-processing videos or the availability of subtitles or closed captions. The latter is easy to understand, but pre-processing here, in simple terms, means the video needs to be transcribed by Microsoft ahead of time for the AI tool to work.
This is similar to the transcription feature in MS Teams, where Microsoft has access to the audio and video files and processes them through a different software technology. In the case of the Microsoft Edge Copilot trying to summarize a video, if it has been picked up by Microsoft for pre-processing, then the AI tool can access the data through the cloud and provide a summary, but otherwise, it cannot.
Thi
Read more on tech.hindustantimes.com