Microsoft’s Edge Copilot AI can’t really summarize every YouTube video

One function added to Microsoft’s AI Copilot within the Edge browser this week is the power to generate textual content summaries of movies. But Edge Copilot’s time-saving function remains to be pretty restricted and solely works on pre-processed movies or these with subtitles, as Mikhail Parakhin, Microsoft’s CEO of promoting and internet companies, defined.

As noticed by MSPowerUser, Parakhin writes, “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,” in response to a query. 

In different phrases, by itself Edge Copilot doesn’t a lot summarize movies because it summarizes the textual content transcripts of the movies. Copilot may carry out an identical operate all through Microsoft 365, together with summarizing Teams video conferences and requires customer support brokers — and in each instances, the audio must be transcribed first by Microsoft. Copilot on Microsoft Stream may summarize any video, however once more, it requires customers to generate a written transcript.

The dialog began after designer Pietro Schirano posted a display screen recording of Edge Copilot summarizing a YouTube video concerning the GTA VI trailer. In this case, Copilot gave the impression to be doing its job completely. The consumer within the recording presses the “Generate video summary” button within the Copilot sidebar, and mere seconds later, Copilot churns one out, full with highlights and timestamps.

Of course, many platforms, together with YouTube and Vimeo, can mechanically generate transcripts and subtitles — if customers allow the function. After The Verge requested Parakhin on X if we might assume most publicly accessible movies (i.e. YouTube) weren’t pre-processed, he replied: “Should work for most videos.”

Copilot is simply the most recent instance of the generative AI race Microsoft is competing in with Google (and others). Last month, Google upgraded the YouTube extension for its Bard chatbot to allow it to summarize the content material of a video and floor particular data from it. Just this week, Google introduced a serious Gemini replace that has its personal points — the corporate’s enhancing could have misrepresented a number of the AI’s capabilities in a demo, and it doesn’t all the time have its details straight.

Parakhin has been candid concerning the varied levels of Copilot’s evolution on social media. While on a airplane on Tuesday morning, the machine studying professional posted on X: “Adding ability for Edge Copilot to use information in videos – on a flight.”