How to create Zoom App with Recognise AI

How can I create Zoom App for recognise people faces and emotions? Can I get other peoples cameras data using Zoom Apps, Camera Mode? Or I must create OWN site with Zoom SDK?

@emotioniq Hope you will be fine.

You need to build Zoom Bot that will join inside the meetings & provide you meeting Video Data at real time. Then you can process/recognise that & send results back to your app.

For more you can connect me here. (WhatsApp)

Thx! But, how I can create meeting bot inside the zoom app?

@emotioniq You need to create two separate apps one is Zoom Apps App and another meeting SDK by following Zoom docs.

If you need already working bot source code then connect to me (WhatsApp).

Thanks

And another question. Can I do this using Zoom Meeting SDK for Web? Or I need to use Windows/Linux SDK

@emotioniq create Meeting SDK App and then use that app creds to native meeting sdks.

E.g Windows, Linux or macOS

There are distinct pros and cons when using the Windows/Linux SDK. By utilizing the Linux SDK, you will be able to deploy the bot to a Docker container.

@emotioniq

Here is the demo how to capture images from the zoom meeting for processing the emotions using ML/DeepAI at real time.

Thanks

@emotioniq, happy to share how to build a meeting bot

Here are the steps:

  1. Spin up a server. We recommend AWS, GCP, or Digital Ocean.
  2. Use either the Linux Zoom SDK to launch an instance of the Zoom client.
  3. Once you have the Zoom SDK launched, and use the Raw Data functionality to extract the video and audio streams.
  4. This will return the video in I420 raw frames and audio in PCM 16LE raw format, so you’ll need to encode the audio and video yourself afterwards.
  5. Once you have one instance of this working, you’ll need to scale this across several servers if you want to run multiple bots simultaneously, which is required to have bots for multiple meetings.

Finally, another option is Recall.ai. It’s a simple 3rd party API that lets you use meeting bots to get raw audio/video from meetings and interact with participants without you needing to spend months to build, scale and maintain these bots.

Let me know if you have any questions!