Microsoft's Edge Copilot AI debuts video summarization feature, but with limitations

The time-saving feature comes with limitations, as it can only work with preprocessed videos or those that already have subtitles.

According to Mikhail Parakhin, Microsoft's CEO of advertising and web services, the summarization feature relies on preprocessed video data or existing subtitles and transcripts.

Parakhin clarified, "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." Essentially, Edge Copilot doesn't directly summarize videos but instead focuses on summarizing the text transcripts of the videos.

Copilot can perform a similar function across Microsoft 365, including summarizing Teams video meetings and calls for customer service agents. However, in both cases, the audio must be transcribed by Microsoft before Copilot can generate a summary. Additionally, Copilot on Microsoft Stream can summarize any video but requires users to provide a written transcript.

Copilot is just the latest example of the generative AI race Microsoft is competing in with Google other tech giants. Last month, Google updated the YouTube extension for its Bard chatbot to summarize video content. However, both companies face challenges in accurately representing their AI capabilities. Google's recent Gemini update, for example, was criticized for possibly misrepresenting information in a demo video.