Discussions

Hello, it appears that when I embed an agent into my page, it has a tendency to cut the mic before I am done speaking, resulting in it NOT receiving my entire question, and as a result it does not answer the question I was trying to ask. This is frustrating for ME, and I imagine it'll be even more frustrating for our end-users. Is there a way to change the sensitivity of the .... silence detector? or whatever it is that's causing it to assume that the user is done talking?

how to use it in reactnative

While generating the video through DID api in response i am getting pending_url instead of result_url

Can we have expressions support as in /talks endpoints and also body and hands movements lilke in /clips endpoints in /agents endpoints. Like we can control on how would the agent will reply on some particular statements?
How to implement through api if this is possible.

Hello everyone, i am trying to build a Virtual Interactive Agent using python. Actually i am following the 4 steps guide in the "Talk Streams" section of the documentation. I have this issue in the step 4 "Create a talk stream" it returns me the status "started" and a video id. But when i try to see the created video in the AWS Bucket, it is empty his size is 1.0 B. This is my code for the new stream creation:

Can I insert props, such as letters of the alphabet, on my educational videos?

I'm able to share my agent with others via the link and they can interact with it but how can I view these interactions?

I would like to know the concurrency and video processing speed of accessing the enterprise customized API. I am looking forward to your reply！

I am using the demo code and I get choppy play back.
Meaning the agent cannot keep up with the audio, which makes things look "off".
What can i do?

I would like to develop my Chatbot on Dify. May I use D-ID Api as a tools on Dify? And D-ID be the avater to speech the content as I want.