Abstract: An example method for priority-based scheduling of translation requests includes establishing first and second video meetings among a plurality of client devices. A computing device may receive, from first and second client devices, first and second translation requests associated with the first and second video meetings, respectively, wherein the translation requests identify first and second textual information, respectively. The computing device may enqueue the first textual information in a first queue, the first queue having a first weight and enqueue the second textual information in a second queue, the second queue having a second weight. The computing device may dequeue a first portion of the queued first textual information from the first queue and dequeue a second portion of the queued second textual information from the second queue. The computing device may insert the first and second portions into a translation buffer associated with a translation service.

Abstract: An example method includes executing a plurality of transcription and translation processes, each executed transcription and translation process associated with one of a plurality of input languages, each translation process associated with one of a plurality of output languages; hosting a plurality of virtual conferences, each virtual conference between a plurality of client devices exchanging audio streams; receiving, during one or more of the virtual conferences, requests from client devices to translate audio streams within the respective conferences; allocating, during the respective conferences and in response to the respective requests to translate, one or more transcription processes and one or more translation processes to the respective virtual conferences based on a source language being used in the respective virtual conference; providing, during the respective virtual conferences, one or more audio streams from the respective virtual conferences to the respective allocated transcription process;