Three different videoconferencing systems for supporting multiparty, remote conversations are described and evaluated experimentally. The three systems differed by how many participants were visible at once, their spatial arrangement, and control over who was seen. Conversations using these systems were compared to same-room (Experiment 1) and audio-only (Experiment 2) conversations. Specialized speech-tracking equipment recorded the on-off patterns of speech that allowed objective measurement of structural aspects of the conversations, such as turn length, pauses, and interruptions. Questionnaires and interviews also documented participants' opinions and perceptions in the various settings. Contrary to expectation, systems in which visual cues such as selective gaze were absent produced no differences in turn-taking or in any other aspect of the structure of conversation. In fact, turn-taking was unaffected even when visual information was completely absent. Overall, only the same-room condition showed any significant differences from any other condition; people in the same room produced more interruptions and fewer formal handovers of the floor than in any of the technology-mediated conditions. In this respect, the audio-only and video systems examined in these studies were equivalent. However, analyses of participants' perceptions showed that participants felt that visual access in mediated conversations was both important and beneficial in conversation. Further, there were indications that the particular design of the different video systems did affect some aspects of conversational behavior, such as the ability to hold side and parallel conversations.