Discussions

Ask a Question

My video generation is currently stuck and not proceeding.

My video generation is currently stuck and not proceeding. It created a chat plan, and when I clicked “Proceed,” it showed an error. Since then, it has been stuck on “Agent is working” for over an hour, and nothing is happening. It was just a 90 or 100 seconds video.

`fit` parameter ignored for video backgrounds in /v2/video/generate

The fit parameter on video backgrounds is being ignored in the Create Avatar Video V2
API (POST /v2/video/generate). A landscape video used as background in a 720×1280
(portrait) video is always cropped/zoomed to fill the frame, regardless of the fit
value. This was working correctly last week.

how to auto-fit photo to 9:16 frame (cover crop) like the website does?

Hi,

Liveavatar is not getting connected using Livekit plugins

Hi Team,
Heygen Liveavatar is not getting connected using Livekit plugins. Earlier the avatar used to connect for the first time and not get connected from the next conversation. But now it is not getting connected.

Bugfix - Important - Voices changed on HeyGen API

Hello,

FULL mode custom LLM — agent not calling base_url endpoint

I’ve configured FULL mode with a custom LLM via llm_configuration_id. My OpenAI-compatible endpoint works correctly (tested streaming and non-streaming). Sessions create successfully, the agent appears in the LiveKit room, and I see lk.agent.events and lk.transcription — but my endpoint receives zero HTTP requests.
LLM Configuration ID: 7899c80f-fab1-40c8-87f7-e57e5e1bc115
Avatar ID: 0930fd59-c8ad-434d-ad53-b391a1768720
base_url: [My Supabase Edge Function URL -- Happy to share privately]
Session creation body:

Regarding credit rights

If I have 200 credits in my creator membership, how many credits do you give in the monthly pro membership?

API Video requests take long time

Why does API requests (under pay as you go) to generate Avatar III videos take so long. For example, my <10s audio with avatar id request takes more than 5-7 mins. Can you suggest improvements or help debug?