Voice content transcription during collaboration sessions

摘要

A method, computer program product, and system for voice content transcription during collaboration sessions is described. A method may comprise receiving an indication to provide one or more real-time voice content-to-text content transcriptions to a first collaboration session participant. The one or more real-time voice content-to-text content transcriptions may correspond to voice content of a second collaboration session participant in one or more collaboration sessions including the first collaboration session participant and the second collaboration session participant. The method may additionally comprise defining a preference for the first collaboration session participant to receive the one or more real-time voice content-to-text content transcriptions corresponding to the voice content of the second collaboration session participant in the one or more collaboration sessions including the first collaboration session participant and the second collaboration session participant based upon, at least in part, the indication.

主权项

1. A method comprising:
receiving, via one or more computing devices, an indication to provide one or more real-time voice content-to-text content transcriptions to a first collaboration session participant of a plurality of collaboration session participants, the one or more real-time voice content-to-text content transcriptions corresponding to voice content of a second collaboration session participant in one or more collaboration sessions including the first collaboration session participant and the second collaboration session participant, wherein each of the plurality of collaboration session participants selects, via a graphical user interface, which of the other plurality of collaboration session participants displayed on the graphical user interface to receive the one or more real-time voice content-to-text content transcriptions for; defining, via the one or more computing devices, a preference for the first collaboration session participant to receive the one or more real-time voice content-to-text content transcriptions corresponding to the voice content of the second collaboration session participant in the one or more collaboration sessions including the first collaboration session participant and the second collaboration session participant based upon, at least in part, the indication; applying, via the one or more computing devices, the preference to a first collaboration session including the first collaboration session participant and the second collaboration session participant and to each subsequent collaboration session including the first collaboration session participant and the second collaboration session participant, wherein the preference is applied to each subsequent collaboration session based upon, at least in part, participants of the subsequent collaboration; providing, via the one or more computing devices, a first real-time voice content-to-text content transcription to the first collaboration session participant during the first collaboration session including the first collaboration session participant and the second collaboration session participant, the first real-time voice content-to-text content transcription corresponding to first voice content of the second collaboration session participant in the first collaboration session, wherein the first collaboration session participant only receives the one or more real-time voice content-to-text content transcriptions for each participant of the plurality of participants that the first collaboration session participant selected via the graphical user interface: and indicating to the second collaboration session participant in the first collaboration session via a pop up interface appearing on the original graphical user interface that the first collaboration session participant in the first collaboration session has requested transcription of the first voice content of the second collaboration session participant.