In an example, a method for facilitating a remote conference comprises: receiving a digital video from a first remote computing device of a plurality of remote computing devices; receiving a first computer-readable audio signal from the first remote computing device; receiving a second computer-readable audio signal from the second remote computing device; operating a face identification machine to recognize a face of a first remote conference participant in the digital video; operating a speech recognition machine to 1) translate the first computer-readable audio signal to a first text, and 2) translate the second computer-readable audio signal to a second text; operating an attribution machine configured to 1) attribute the first text to the first remote conference participant recognized by the face identification machine, and 2) attribute the second text to a second remote conference participant; and operating a transcription machine configured to automatically create a transcript of the conference, the transcript including 1) the first text attributed to the first remote conference participant, and 2) the second text attributed to the second remote conference participant. In this example or any other example, the face identification machine is further configured to recognize, for each remote conference participant of a plurality of remote conference participants in the digital video, a face of the remote conference participant; the attribution machine is further configured, for each remote conference participant of the plurality of remote conference participants, to attribute a portion of the first text to the remote conference participant; and the transcript includes, for each remote conference participant of the plurality of remote conference participants, the portion of the text attributed to the remote conference participant. In this example or any other example, the transcript further includes an arrival time indicating a time of arrival of the first remote conference participant and a departure time indicating a time of departure of the first remote conference participant. In this example or any other example, the arrival time is determined based on a time of recognition of the first remote conference participant by the face identification machine. In this example or any other example, the transcription machine is configured to: recognize content of interest for the first remote conference participant; automatically recognize the content of interest in the transcript; and include within the transcript an indication of a portion of the transcript related to the content of interest. In this example or any other example, the transcription machine is configured, responsive to recognizing the content of interest in the transcript, to send a notification to a companion device of the first remote conference participant including the indication of the portion of the transcript related to the content of interest. In this example or any other example, the transcription machine is further configured to receive, from a companion device of the first remote conference participant, an indication of a digital file to be shared with the second remote conference participant, wherein the transcript further includes an indication that the digital file was shared. In this example or any other example, the transcription machine is further configured to recognize a portion of the digital file being accessed by one or more of the first remote conference participant and the second remote conference participant, and wherein the transcript further includes an indication of the portion of the digital file that was accessed and a time at which the portion of the file was accessed. In this example or any other example, the transcription machine is further configured to recognize, in the digital video, visual information being shared by the first remote conference participant, and wherein the transcript further includes a digital image representing the visual information. In this example or any other example, the transcription machine is further configured to recognize a change to the visual information, and the transcript further includes a difference image showing the change to the visual information and an indication of a time at which the visual information was changed. In this example or any other example, the transcription machine is further configured to recognize an occlusion of the visual information and to process one or more difference images to create a processed image showing the visual information with the occlusion removed; and wherein the transcript further includes the processed image. In this example or any other example, the method further comprises visually presenting a reviewable transcript at a companion device of a remote conference participant, wherein the reviewable transcript includes the difference image showing the change to the visual information and wherein the reviewable transcript is configured, responsive to selection of the difference image, to navigate to a portion of the transcript corresponding to the time at which the visual information was changed. In this example or any other example, the transcription machine is configured to transcribe speech of a first conference participant in real time, the method further comprising presenting a notification at a companion device of a second conference participant that the first conference participant is currently speaking and including transcribed speech of the first conference participant. In this example or any other example, the transcription machine is further configured to analyze the transcript to detect words having a predefined sentiment, the method further comprising presenting a sentiment analysis summary at a companion device of a conference participant, the sentiment analysis summary indicating a frequency of utterance of words having the predefined sentiment. In this example or any other example, the method further comprises a gesture recognition machine configured to recognize a gesture by the first remote conference participant indicating an event of interest, and wherein the transcription machine is configured to include an indication that the event of interest occurred responsive to detection of the gesture by the gesture recognition machine.