Systems and methods for computing latency introduced by media transcoding operations are described. In some embodiments, a method may include receiving incoming Real-Time Protocol (RTP) packets, each having time of arrival and a payload encoded with a first codec and receiving outgoing RTP packets, each having a time of transmission and a payload encoded with a second codec. The method may also include calculating a latency associated with a transcoding of at least one of the incoming RTP packets into at least one corresponding one of the outgoing RTP packets based upon a difference between the time of transmission of the at least one corresponding one of the outgoing RTP packets and the time of arrival of the at least one of the incoming RTP packets. In some cases, the incoming and outgoing RTP packets may be Voice-over-Internet Protocol (VoIP) packets.