could you please anyone help me to understand two-way real-time transcription flow using CVP , forking (google cloud ) , and how we take the transcribe from forking connector to display in desktop , is anyone did this integration on UCCE or UCCX platform , could you give some insights to start this , Many thanks!!!!!
Check out Cisco Live session BRKCCT-2009 from 2019. All related materials and additional work since then is posted here http://cs.co/cct2009. In the desktop transcription scenario, there is a sample test gadget that invokes the speech to text operation on the cloud service and retrieves results continuously over websockets.
Be mindful that this is all custom and experimental, sold as seen, no official support.