Changing Third-Party Captions Display?

[JRB]

Hoping for help on a question from a vendor I work with. They would like to use a third-party captioning service for live webinars, but are unhappy with the way the captions & live transcript display in Zoom when sent by the captioning service. With the Zoom AI captions, you get a nice long block of text between timestamps in the live transcript, and the caption box is centered on the screen, however, the AI often misses product names and industry jargon. When we tested with the live captioning service, the accuracy is better, but you get these small fragments of text between each timestamp in the live transcript, and short blocks of captions that pile up on the left side of the screen. Ideally, we would like to see the live captioner's output display the same way that the Zoom captions do.

Is there some parameter we can change in the API token that will increase the length of text being transmitted at once? Or is there something I can ask the captioning service to change on their end? I am unfamiliar with the terminology they might use, so appreciate anything that helps point me in the right direction. 

Many thanks!