Hello.
How can i get a meeting audio or transcript in live via any APIs?
I want to build a desktop app that can display the transcript from my Zoom call with all participants names. All the transcripts should be generated in live.
Which SDKs or APIs should I use?
Hi,
You would need to use the Meeting SDK to capture the raw audio. This raw audio stream can then be directed to a translation service or team for processing.
Then to deliver the translated text or audio to the end users, you could do it via websockets.
Cheers,
Harsh
Fario Consulting
Hello!
To get live meeting audio or transcript via APIs for a desktop app that displays the transcript from your Zoom call with all participants’ names, you have a couple of options. Since Zoom doesn’t offer direct API endpoints for accessing real-time transcripts, here’s what you can do:
-
Zoom Meeting SDK
You can use the Windows or Linux Meeting SDK to access raw meeting data, including meeting audio. You’ll be able to receive and process the raw audio stream in real time this way. Here’s an example Github repo that demonstrates how to access raw video and audio through the Linux Meeting SDK.
Many third-party transcription providers support streaming speech to text, so once you have the raw audio, you can stream it to the provider to receive real-time transcription, and then display it in your desktop app.
You should be able to get the names of participants through the ListMeetingParticipants API. -
Recall.ai
Another alternative is to use Recall.ai instead. It’s a simple 3rd party API that lets you use meeting bots to get raw audio/video from meetings and generate real-time transcripts in just a few lines of code.