Microsoft reveals Edge Copilot requires 'pre-processing' for video transcription

Microsoft’s Edge Copilot recently gained the ability to summarize YouTube videos, even if they lack timestamps. However, a recent tweet by Microsoft’s Mikhail Parakhin clarifies that the transcribing functionality relies on pre-processed video data or subtitles embedded within the video.

If a video hasn’t been pre-processed and doesn’t contain subtitles, Copilot cannot currently generate timestamps or summaries. This shows a limitation in the feature’s current implementation.

While Copilot’s ability to analyze and summarize YouTube videos, even without existing timestamps, is impressive, the pre-processing requirement suggests there might be hurdles to its immediate widespread usability.

This means that Users may encounter limitations in using Copilot’s video analysis features for videos that lack subtitles or haven’t been pre-processed.

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.

— Mikhail Parakhin (@MParakhin) December 7, 2023

The extent of the required video pre-processing process is uncertain, and Microsoft has not confirmed if Copilot will eventually support non-subtitled videos.

Apart from this limitation, it is a very handy tool. The ability to utilize video information has the potential to transform the way we engage with video content. Imagine scanning summaries, jumping to key moments, and gaining deeper insights from any video you watch.