Transcribe meetings live in order to process the text into a server


Hoping I’m writing this question in the right category.

How can I transcribe text from a live meeting (like does) or any other transcribe app on here?

I basically want to create a live-translator application which transcribes what the people are saying, the words are sent to a translator API we use and it gets live returned to the user.

Would a Zoom application fit my needs? Is what I’m asking above even possible? I was thinking of building a browser extension that would record the audio stream, process it as text, send it to the API, have it returned as translated text but I’m still researching on that and trying to see if there is an easier method.

Would really appreciate any answers on this topic, thank you!

Hey @an4rei,

You have two options at the moment, you can use the Closed Caption API, or use the Cloud Recording API, which returns the recording files after the meeting.


Thanks for the quick answer @tommy

Closed Caption API sounds like something I’d use but I want to create something that doesn’t require user input(get the caption URL) and so on. My idea is to create something on the go, exactly as an app would be.

Also, you provided me the way to send captions to the livestream, but not to actually receive and process the audio from the stream(in order to transcribe it and later translate it through an API) and then return the user the translated caption.

I’m hoping you got my question.

  1. I want to create an App that you install and it goes ahead and process any audio from any meeting the user is in. By processing I mean transcribing voice to text in order to translate it later
  2. I want the App to interact with a 3rd party server that would receive the transcribed text, it would translate the text and return it as live caption to the user.

Are these 2 possible with an App or do I have to go ahead and improvise with browser extensions?

Thank you!

Hey @an4rei,

This is possible with the second flow I mentioned. You can use the Cloud Recording Completed Webhook and Cloud Recording API to get access to the recording files, and then translate them how you wish.

@tommy that’s the thing, I want them to be transcribed live(during the meeting), not after the meeting has ended. I’ve researched more and found out that they all(the transcribing apps) record the audio of the actual meeting that’s being broadcasted through the speakers with their own microphones and the extension/web page deals with the live audio stream.

Thanks for the help!

1 Like

Hey @an4rei,

Gotcha! Yeah your best bet is to see how the current apps are doing it! :slight_smile:


This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.