\n<\/p>\n
One feature added to Microsoft\u2019s AI Copilot in the Edge browser this week<\/a> is the ability to generate text summaries of videos<\/a>. But Edge Copilot\u2019s time-saving feature is still fairly limited and only works on pre-processed videos or those with subtitles, as Mikhail Parakhin, Microsoft\u2019s CEO of advertising and web services, explained. <\/p>\n<\/div>\n As spotted<\/a> by MSPowerUser, <\/em>Parakhin writes<\/a>, <\/em>\u201cIn 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\u2019t preprocess it yet – then it won\u2019t work,\u201d in response to a question.\u00a0<\/p>\n<\/div>\n In other words, on its own Edge Copilot doesn\u2019t so much summarize videos<\/em> as it summarizes the text transcripts of the videos. Copilot can also perform a similar function throughout Microsoft 365, including summarizing Teams video meetings<\/a> and calls<\/a> for customer service agents \u2014 and in both cases, the audio needs to be transcribed<\/a> first by Microsoft. Copilot on Microsoft Stream can also summarize any video, but again, it requires users to generate<\/a> a written transcript.<\/p>\n<\/div>\n The conversation started after designer Pietro Schirano posted<\/a> a screen recording of Edge Copilot summarizing a YouTube video about the GTA VI <\/em>trailer<\/a>. In this case, Copilot appeared to be doing its job perfectly. The user in the recording presses the \u201cGenerate video summary\u201d button in the Copilot sidebar, and mere seconds later, Copilot churns one out, complete with highlights and timestamps. <\/p>\n<\/div>\n Of course, many platforms, including YouTube and Vimeo, can automatically generate transcripts and subtitles \u2014 if users enable the feature. After The Verge<\/em> asked Parakhin on X if we could assume most publicly available videos (i.e. YouTube) weren\u2019t pre-processed, he replied<\/a>: \u201cShould work for most videos.\u201d<\/p>\n<\/div>\n Copilot is just the latest example of the generative AI race Microsoft is competing in with Google (and others). Last month, Google upgraded the YouTube extension<\/a> for its Bard chatbot to enable it to summarize the content of a video and surface specific information from it. Just this week, Google announced a major Gemini update that has its own issues \u2014 the company\u2019s editing may have misrepresented<\/a> some of the AI\u2019s capabilities in a demo, and it doesn\u2019t always have its facts straight<\/a>. <\/p>\n<\/div>\n