Limitations with voice transcription


When working with voice transcription in Genesys Cloud, keep in mind the following limitations:

  • When a consult transfer is performed between agents speaking different languages, the voice transcription capability cannot determine that the language has changed. As a result, the transcription language does not change accordingly. For example, when a consult transfer is performed between an agent speaking EN-US (English) to an agent speaking ES-US (Spanish), the audio continues to be transcribed in EN-US (English).
  • When a consult transfer is performed and the customer is listening to music (without vocals), the music may be transcribed as filler words (for example, um, ah, and so on) and a Conference icon appears in the transcript even though the music is not a conference between multiple agents.
  • When the interaction is put on hold and the customer is listening to music (without vocals), the music may be transcribed as filler words (for example, um, ah, and so on) and an Agent icon appears in the transcript even though the agent is not talking.
  • In general, transcription of voicemail recordings is not supported. However, under certain scenarios where recording in the IVR is turned on and voice transcription is turned on, transcription of the voicemail may occur.
  • When an interaction is transferred to a queue,  the in-queue flow may not be fully executed prior to delivering the interaction to an available agent. As a result, if the in-queue flow attempts to change the language, the language change or switch may not take effect since the transcription flow may not have been executed prior to the transfer completing.
  • BYOC Premises post call voice transcription does not transcribe calls beyond a 10-hour limit.
  • BYOC Premises post call voice transcription requires dual channel recording.
  • BYOC Premises post call voice transcription of recordings is only supported with audio in the following formats: Opus, PCMU, PCMA or L16.

For more information, see About voice transcription.