Discussions

Hi, I started using the new sdk today. First of all, the heygen team has done a great job with reducing the latency of streaming.task api. However, it tends to speak random sentence after every 15 seconds, even if streaming.task api is in action?

I would like to generate a video with just the lip-syncing effect for my avatar. I have already created my avatar using My Avatar, and I want to use local audio files from my device to drive the lip movements. Could you please guide me on how to achieve this?

Just a quick question, the custom avatar created by me can be used by anyone or with my own api token from dashboard only?

In voice chat mode when a user speaks into the microphone, is it possible to retrieve the voice message in text so I can have it reflected in the UI?

I am using the SDK,

Hello, I'm encountering an issue while trying to use Streaming API. I've created an interactive avatar, but I'm unable to start a streaming session with it.
When I send a request to the

Dears,

I set up text mode (with task type REPEAT) with chatgpt and everything works well but I'm still trying to wrap my head around having the Avatar respond with the task type "Repeat" while still remaining in voice chat mode. I want the user to easily be able to communicate back and forth via microphone, its set up perfectly in voice chat Mode, but still have the avatar's answers be repeated by what comes back from chatgpt. Is there a way to do this?

Hi.