Example methods and systems provide automatic detection of companion mode for a virtual conference application in hybrid events. A client device joins a virtual event session via the virtual conference application provided by a virtual conference provider. During the virtual event session, the virtual conference application receives a first audio signal from an audio source at an on-site event and a second audio signal from the virtual conference provider. The virtual conference application determines a correspondence between the first audio signal and the second audio signal during the virtual event session. The second audio signal is muted in response to determining the correspondence.