Discussions

I’m using the avatar generation API. I added a caption, but the caption in the video is incomplete compared to the spoken content. When I check the “Edit Caption” section on the HeyGen dashboard, the full caption appears correctly, but the caption in the video is missing parts. Could you please help me check this?

Hey folks! I've been trying to create avatars with voiceovers and it all worked great until yesterday every video ended up having the last two seconds just white blank screen. I tried to add another scene with text to the script but still at the end of my VoiceOver the avatar disappears. I also tried several of my looks and it all turned out the same way. I really need your help there, I tried everything...

Hi since this data is available form the list avatars in avatar group endpoint, can we add the other side.

Hi there,
I am using the heygen streaming-avatar 2.0.10 library in VoiceChat mode when working with an interactive avatar in React.
I have a problem with voice recognition which is as follows.
For example if I say the following text: “I'm sure that speaking aloud helps you.”
As a result of recognition I get in : “Iam surethat speaking aloudhelps you.”
This problem is quite often repeated in a conversation.

Hi Heygen team,
We've noticed a change in behavior with the avatar speech output. Previously, setting the language parameter to "no" in the createStartAvatar API call resulted in proper Norwegian speech output. However, recently, the same configuration results in the avatar speaking Danish instead.

When we start to create avatar request, I try pass the "knowledgeId" . The avatar session is started but it does not start with the the prompt that we have set it in heygen labs. Please advice how to configure the avatar with the prompt when the session is started. Below is the request.

I don't always get the STREAM_READY event which is a problem.

Hi there

What script can I implement to mute the microphone or that it doesnt respond to spoken text only the typed?

For my interactive avatar, I use the SDK to obtain transcribed text of what the user and avatar say.
If USER_TALKING_MESSAGE does not fire, AVATAR_TALKING_MESSAGE will not fire. In other words, even if the avatar is speaking, the transcribed text will not be output unless the user speaks. I would like to transcribe what the avatar says even if the user does not speak.