Real time transcription with Web SDK

I’m looking for solutions for enabling real time transcription on Zoom. Specifically, it needs to work along with the Web SDK and there needs to be an exposed API for the same.

There seems to be Marketplace apps which is supposed to enable it, like (this is the one which seems best on paper with live transcription, note taking, etc). But it is not evident how it can be integrated with Web SDK on that page. Nor there is detailed info on the Zoom blog.


  1. Can be integrated with the Web SDK and are any APIs available?
  2. Are there any alternative ways to enable real time transcription with Web SDK?

Hey @harrysmsn,

Currently the Web SDK does not support custom transcription out of the box.

You could possibly get the audio streams from the requests and transcribe them that way.


Thanks for the info @tommy.

1 Like

Happy to help! :slight_smile:


I am also interested in this …

  1. Zoom - do you have a sample API for requesting only the audio file for a certain meeting ?
  2. Since the websdk does not have this out of the box - what is the preferred way to connect transcription with my custom app … and route the request to Otter and get the transcript response

Any examples here - would be extremely helpful

Hey @preyashs,

Currently the only out of the box way to do this is the closed caption endpoint:


Hey Tommy, curious why the documentation here says the Web SDK supports closed captioning Real time transcription with Web SDK

Hey @rahul2,

Apologies for the confusion, the Web SDK does support the Closed Caption feature, but not in the sense of this threads topic, to get audio streams for real time transcription unless you are using the closed captioning api.