Transcription presentation of communication sessions

A device comprising:

• a first network port configured to obtain audio captured by a local device, the device and the local device being located within the same structure;
• a second network port configured to direct, while the audio is captured by the local device, the audio to a transcription system and to obtain transcript data from the transcription system, the transcript data including a transcription of the audio generated by the transcription system and the transcription system obtaining the audio only from the device;
• and
• a display configured to present the transcription while the audio is captured by the local device.

One or more non-transitory computer-readable media configured to store instructions, which when executed cause a device to perform operations, the operations comprising:

• obtaining, at the device, audio captured by a local device, the device and the local device being located within the same structure;
• directing, from the device while the audio is captured by the local device, the audio to a transcription system, the transcription system obtaining the audio only from the device;
• obtaining, at the device while the audio is captured by the local device, transcript data from the transcription system, the transcript data including a transcription of the audio generated by the transcription system;
• and
• presenting, by the device while the audio is captured by the local device, the transcription.