Hello @治猷 張
Thanks for using Microsoft Q&A. I think you are mentioning two questions, one is Face API limitation, the other one is about analyze faces in real time video/ stream.
For the first question, you need to apply for access or you can not run the API even you have input some data in it. Face service access is limited based on eligibility and usage criteria in order to support our Responsible AI principles. Face service is only available to Microsoft managed customers and partners. Use the Face Recognition intake form to apply for access.
I apologize for all inconveniences.
For the second question, the doc you are looking at is not the official product document, please refer to the offcial doc part about how to perform near-real-time analysis on frames taken from a live video stream. And there is an exampe - https://video2.skills-academy.com/en-us/azure/cognitive-services/computer-vision/how-to/identity-analyze-video?source=recommendations
I hope this helps! I will highly recommend you to apply for access and then have a try on this example.
Regards,
Yutong
-Please kindly accept the answer if you feel helpful to support the community, thanks a lot.