Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating avatars based on physical sensor measurements. One of the methods includes receiving, by a second user device from a video streaming platform system during a video streaming session between a first user device and the second user device, an updated physical sensor measurement of the first user device. An updated graphical representation of an avatar selected by a first user of the first user device is generated by the second user device based on the updated physical sensor measurement of the first user device. The updated graphical representation of the avatar is presented by the second user device on a display device of the second user device during a video streaming session between the first user device and the second user device.