I want to analyze the audio of video calls. Specifically, I want to transcribe audio into text and perform natural language processing stuff on it.
Also, I want to be able to know when & how much each person is talking.
Question
Can I do what I want to do using Video SDK?
get row audio
perform analytics such as transcription on the audio
know when & how much each person in the call is talking
“Raw Video / Audio Data Available in Android, iOS, Windows, macOS”
Does this mean I do NOT have access to the raw video/audio data when using Web SDK?
It looks like I have access to the “stream” but doesn’t that mean I have the access to the audio?
I am not an expert in web development. Kind answers without the assumption of understanding of the advanced topics in the web development world would be very helpful.
So by row I actually meant real-time audio data. Meaning that I want to do something with the audio data, during the meeting, real-time. (just like Otter.ai transcribe the conversation real-time).
Can I do that with Web SDK? Or is it only possible with Desktop SDK? Thanks!
(Also, if it is only possible with Desktop SDK, can I do it with Angular/React for frontend/ django for backend, not objective-C or swift?. Asking because the example for macOS SDK only come with objective-c and swift. Thanks!)