Get Live Transcription with Zoom Video SDK UI Toolkit for Real-Time AI Analysis

I’m using the Zoom Video SDK UI Toolkit for a meeting application and have already implemented Zoom Cloud Recording. Now, I want to get live transcription (in English) of speakers during the meeting in real time so I can send it to my backend for AI analysis. I need this transcription as a live stream or event, not after the meeting ends. However, I cannot switch from the UI Toolkit to the full Video SDK. Is live transcription supported in the UI Toolkit? If not, is there any workaround to capture live audio and transcribe it using a third-party service? Has anyone implemented something similar?

2 Likes

Hi @LulzSec Which platform of the UItoolkit are you using?

I’m using the Zoom Video SDK UI Toolkit for Web (React)

Gotcha! For the Web UIToolkit, you can specify ‘caption’ in the featureOptions and that will enable Live Transcription and Translation. At the moment, it does not have support for subscribing to the specific Video SDK listeners.

1 Like