Architecture that employs a signal (e.g., audible or inaudible sounds) to detect if endpoints of a communications session are sufficiently close to each other to induce echo, and then control (e.g., muting) is applied to one or more of the endpoints to prevent echo. The signals can be played and detected from the endpoints or a central conferencing component such as a multiple control unit (MCU). The MCU can provide support for legacy endpoints as well. When echo is detected, the offending endpoint(s) can be controlled to mute one or more onboard devices such as a speaker or microphone. The device(s) can be muted from a remote component or for a local component or locally by the endpoint user. A notification can be sent that notifies the endpoint user that the mute operation has been applied or should be applied to one or more of the local devices.