Discussions

Ask a Question

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?

LiveAvatar Custom AI avatar

I’m looking into the LiveAvatar api for my new app idea and I’ve got a question about making/building my own live avatar.

Answered

Feature Request: Subtitle color customization fields in /v2/video/generate

Hi,

Answered

How to use photo avatar on model III engine?

I am having a hard time creating videos using avatar 3 model. My workflow is uploading a photo as an asset, but it doesn't seem to have the ID needed to create video using avatar 3 model. What're the api endpoints and workflow if I want to create videos using that model?

Answered

rate limits on /v2/video/generate endpoint?

Is any sort of concurrency / batch processing supported ?