Systems and methods are provided for automatically selecting a mute function based on audio content. One example method includes receiving, at a first computing device, a first audio input and, from a second computing device, a second audio input.
Content of the first audio input and the second audio input is determined with natural language processing. Whether the content of the first audio input corresponds to the content of the second audio input is determined. A mute function is operated at the first computing device, based on the determination of whether the content of the first audio input corresponds to the content of the second audio input.