Discussions

Hello,

Hola a todos,

I wanted to clarify—does the 4000-character limit apply specifically to the knowledge base entries

Hi, I am trying to create a streaming session with the Avatar Dexter_Doctor_Sitting2_public with voice ID: c089f9832fd04922b34b3d2f3661d113 using python API.

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: