Discussions

It's speaking in english and is especially bad with 3, 4, 5, 6, 8 and 9

As title, I send a phrase which is generated using my LLM model, and ask avatar to speak accordingly. But what the avatar speaks doesn't follow the text completely.
I wanna build an avatar interface having avatar and message on it, so i want the text to be exactly same as speak.
I'm using the following voice id (Chinese voice):

I upgraded my subscription and now the trial token I was using just before that suddenly breaks. I checked and the token didn't even change. What's wrong and what should I do?

Hi there ,
I want integrate the same video player that can basically stream the video and audio.I want to integrate the both audio and text input.I dnt want the customize avatart creation right , and plz tell me how i can achive using streaming api. The next js demo does not include the voice input and its very deprecated and legacy. Is there any latest one.

I'm trying to create a video using this api and I want to add a background image. I have added
images from url extension jpg, png
tried to upload it to google drive and made it publically accessible

I cloned the github. Pasted my open ai key, it keeps erroring with Error talking to AI.

I want to test in multiple environments (dev and QA) and realised that I will need to reuse our HeyGen API key. This means that I need to register multiple Webhook endpoints. Each environment will have their own secret produced by the webhook API.

I'm planning to develop with Streaming avatar api, and I'm testing it using trial token.
I made the quality parameter high, but is this avatar 1080p supported?

I'm using the streaming avatar and when i try to send a task it gives me this error
{
"code": 500,
"message": "something wrong in server"
}
everything seems fine so I'm not sure what's causing it

Uncaught TypeError: debugStream is not a function
at peerConnection.oniceconnectionstatechange (StreamingAvatarApi.js:533:1)