Systems and methods are provided for device playback calibration. An example implementation involves a network device detecting, at a first time, a first audio content rendered by at least one first playback device. The example implementation also involves the network device detecting, at a second time, a second audio content rendered by at least one second playback device. The example implementation further involves causing, via the network device, determination of an equalization adjustment for one or more of the at least one first playback device and the at least one second playback device based on an analysis of the detected first audio content and the detected second audio content.