Patent documents reveal that Microsoft is working on a new AI feature that creates images from live audio during meetings to make communication visual.

A picture is worth a thousand words: Microsoft seems to take this saying very literally. Microsoft has filed a patent for new AI technology that can convert live audio into images. The technology could be used, among other things, to provide images for Teams meetings.

The technical patent document explains how the system works. The AI ​​listens during meetings and converts the audio data into text for itself. Based on these text summaries, the model then generates images associated with the conversation. This all happens in real time so that the image reflects the content of the meeting as accurately as possible.

Seeing, hearing and speaking

Filing a patent does not automatically mean that Microsoft plans to make the technology available to the general public. The software giant sees this as a useful addition to video calls.

“When images are used to supplement verbal communication, they can help clarify concepts and make them easier to understand, which can be particularly beneficial for people who learn better with visual aids,” explains Microsoft, explaining the rationale for the technology.

New updates have already given Microsoft Copilot eyes and the ability to speak. Microsoft is looking for ways to make the AI ​​assistant relevant to everyone. This has been achieved with varying degrees of success: the number of Copilot users is increasing every month, but not everyone is convinced of its usefulness for their work, including Salesforce CEO Marc Benioff.