How to output audio of the other speakers into speech-to-text program

[AnanthShane]

I'm trying to implement a speech to text program on an entire zoom call. To do this, I need to pipe the output from the other speakers in zoom, and my own speech, into the program. The second step is doable for me. However, I'm not sure how to output the audio of the other speakers into my program. I tried using a virtual audio input but it didn't really work as zoom only has 1 audio output option. Any help on how to bypass this would be useful.

[RN · Accepted solution]

Hey @AnanthShane, what program are you using by chance? Assuming the speech-to-text program needs to be tied to output at the PC level settings to be recognizable to Zoom, however, I haven't tested so I'm not sure about the experience on the program.  

We do have Audio transcription for cloud recordings when recording to the cloud, when accessing the recording you'll see the Audio transcription -- you have the option to display the transcript text within the video itself, similar to a closed caption display.

Or, we do have live transcription within meetings, you can check out the Enabling or disabling closed captioning and live transcription services feature.

Let me know if the suggested above helped! 

[RN]

Hey @AnanthShane, just checking in on my reply! Was it helpful? If so great! Just don't forget to click that 'accept as solution' button, thanks!