Discussions

I have a question. Using your API, I can upload my own photo, video, and voice to create an avatar video using my input text. My question is: I noticed that you provide some predefined sample avatar videos through the API. These sample avatars are speaking a default script like, "Welcome to the new era of video creation with Heygen..."

I want to integrate heygen avatar with gcp dialogflow CX to crate humanize chatbot , can anyone help me with steps for this ?, chatgpt is not giving all steps. I tried to find solution but no luck.

I uploaded an asset, created an avatar group, created a look, trained the avatar and confirmed it was successfully trained, but when I pass the avatar ID to video generate API it fails every time with:

I saw that videos can take up to 3 days to be produced but then why if i create a new video it's processed immediately while the older are not progressing?

Hi

Is there a way to indicate in the script that I want a longer pause between words. For example, if there is a new topic in the script, can i insert something to indicate that there should be a longer pause?

I create a Video with the API

Hi,
If it's possible to get streaming avatars in an image format. Could anyone provide more information on this?

Hello I am using interactive avatar SDK, in my experince I dont want the avatar to listen when user sound is low, like it is too senstive to listening when people are speaking around me even in low level, I dont know if this feature available but I used my own volume analyzer and I can get user volume level, all I need is not allow avatar to listen or speak when user volume is less than 40%, I treid stop listening but it didnt work.

Feedback - please could the share URL be added as part of the details returned from the retrieve video elements endpoint.