Discussions

The face swap feature is not currently available through HeyGen's API as it has been deprecated with no plans for future support.

In interactive avatars, the avatar's speech can be obtained as a string from the "StreamingEvents.AVATAR_TALKING_MESSAGE" event. However, this string can be obtained before the avatar actually speaks. Is it possible to obtain the string as soon as possible in real time along with the avatar's actual speech？

Is there a way to use the Zoom Meeting function with an own LLM, or do I have to do my own implementation with the zoom api?

Is it possible to use an interactive avatar with its own knowledge base directly on HeyGen's website and extract the conversation to an external database?

I'm currently running a custom web app that integrates the Heygen Interactive Avatar SDK (deployed via Vercel), used on an NVIDIA Shield Pro (Android TV). The avatar loads and responds as expected, but I’ve run into a specific issue with Bluetooth audio:

I'm experiencing an issue with the HeyGen API where my video generation requests reach approximately 97% completion before failing. Here's my setup and what I've tried:

How can I speed up session loading, it takes too long to start new session, also it looks like it starts 2 sessions because of the slow loading. How to slove this?

The connection with a OpenAI Assistent works perfect in "type mode". When I add speech to text it returns to the basic "Heygen information". Does anyone have a suggestion as to what the problem might be?

After sending task to avatar to chat or repeat i want to get response as text to show in my view, i know there's possibility to do that in StreamingAvatar SDK but i want to do it with Streaming API because i use LiveKit in iOS.

Does Heygen provide Knowledge base creation API, since our team want to create knowledge base programmatically?