Discussions

We are currently integrating your V2 Streaming API (using REST API calls and LiveKit for media) via a Node-RED backend orchestrator, and we're encountering an issue where the avatar is not speaking the text provided via the /v1/streaming.task endpoint. Instead, it seems to be reverting to a default conversational script For example when the prompt says "Your name is Aida, and you are a friendly assistant. Start every conversation with a robot joke" - instead of starting off with a joke, the avatar June_HR_public opens up with "That was a funny joke. I am June with HeyGen...". So its clearly taking these inputs as "user" input where it should be "assistant" text she is suposed to say.

Hi,

Hello,

Hi, I’m exploring the HeyGen API and was wondering: does it support generating avatars that can respond to real-time events or questions — similar to how ElevenLabs handles real-time audio generation? I’m particularly interested in whether continuous or reactive video generation (e.g., for dynamic conversations) is possible, or if HeyGen avatars are limited to pre-scripted videos. Thanks!

Hi,

I want to know in real time when an error occurs in heygen when using the heygen API.

Hello!

Hi guys, in the captioned videos I created with the old v3 creator, the captions were placed at the bottom of the video as expected. In the videos I created with the API using the template I created with the v3 template, it was placed at the bottom in the same way. But recently it started to put the caption in the middle of the video. Is there no way to solve this?

Hello everyone,
I've been integrating Heygen avatars with my custom backend solution and ran into an interesting problem that I wanted to share in case others are experiencing it.