Bots and avatars are separate entities.
An Avatar is the visual/media representation of a bot or agent. An avatar can have images, video, and audio content associated with emotions, actions, and poses. An avatar integrates with our Text To Speech API, and the HTML5 Speech API to simulate talking.
We just updated our web API to better support avatars. You should be able to query, create, and edit avatars using the web API the same as our other entities.