From what I’ve read, Jigasi provides a transcription service but it uses Google’s service. I would like to use captions generated by a program on my end. For simplicity, you can assume that there are at most two participants. Is there a way for me to interface with Jitsi or Jigasi so that I can send my generated captions and have them displayed on the video conferencing environment?
P.S. I’m very new to Jitsi so apologies if the questions are confusing.