The video call mode takes advantage of omni models, so you're able to use your camera to provide context to the model.
For example, you can start a video call, and ask it to create a 3D model of an object you’re holding. The voice coordinator agent will snap a picture of the video feed, then create a worker, which will work on the 3D model in a VM according to the image.
For example, you can start a video call, and ask it to create a 3D model of an object you’re holding. The voice coordinator agent will snap a picture of the video feed, then create a worker, which will work on the 3D model in a VM according to the image.