Providing audio and/or video content from one user to a second user within an environment are described. An electronic device can receive conversational content from one user and determine that it is directed to a second user. The second user can be determined to be within another location of the environment (e.g., a different room of a house) and identify the capabilities of devices within the other location. Play back of the conversational content can then be performed using the identified devices within the other location.