In collaboration with Vonage team member, Talha Ahsan, Hamza has written an Attention Detection web application tutorial showing how to integrate the Vonage Video API with TensorFlow’s MediaPipe face detection model.
In Hector’s final post in his series on basic networking concepts used in WebRTC, he creates a video conference application and goes “under the hood” to understand all the networking that happens in order to establish a call using WebRTC.
Capitalizing on the considerable flexibility that the Amazon Chime SDK offers for customizing the UI, Marcell takes yet another step in our growing demo application: active speaker detection to identify who is talking and manipulate the user interface to favor that stream over the rest.
CPaaS platforms enable developers to quickly and easily integrate audio and video by leveraging WebRTC APIs built in under the hood. However, this layer of abstraction can make it difficult to make optimizations. What can you do to improve call quality and user experience in your WebRTC CPaaS application? Hamza offers some ideas and tests them with one of the more popular CPaaS platforms, the Vonage Video API.
