Following its Worldwide Developer Conference (WWDC), Apple held its Platforms State of the Union for developers. In it, the Cupertino company outlined ‘Spatial Personas,’ a Vision Pro feature that leverages machine learning to create photorealistic avatars of users during FaceTime calls
The Vision Pro headset is set to curate tailored first-party app experiences. One of these supported apps includes Apple’s FaceTime. As shown during WWDC, users can set up a FaceTime call with others much like they would with their iPhone. However, the Vision Pro version is due to support Spatial Personas.
In the Platform State of the Union video, Apple explains that the headset will support a feature enabling users to “break out of the familiar FaceTime tile and feel more present like they are gathered in the same physical space.” As shown in the video, users will appear as life-like virtual avatars. This tile will feature a transparent background, which will help create an immersive illusion.
Spatial Personas are said to be able to dynamically match hand and facial movements. Whether you’re speaking to a family member or interacting with a colleague on a work call over FaceTime, those real-world movements and gestures will be represented. 3D volume and depth are also attributed to personas.
Apple hopes Spatial Personas can be paired with Vision Pro’s SharePlay functionality. It appears as though the company aims to help build tools to make Vision Pro more immersive with collaborative features during SharePlay sessions.
Apple’s Spatial Personas is still in development and will be available later this year. Vision Pro is expected to launch exclusively in the U.S. in early 2024 for $3,499 USD (roughly $4,702 CAD).
Stay up to date on all of the news coming from WWDC 2023 here.
Image credit: Apple