Discussions

I am have integrated interactive avatar using streaming avatar sdk. How can I use sandbox for interactive avatar? Sandbox is available and configured in LiveAvatar product and we are still in the process of migration from interactive avatar to LiveAvatar.

I would like to generate a video using the talking_photo_id in the Create a Video API.
However, the documentation states that available talking_photo_ids should be retrieved from the following API:

Ready to carve up some serious powder without leaving your couch? Then grab your virtual snowboard and prepare for an adrenaline-pumping experience with Snow Rider 3D! This isn't your grandma's skiing simulator; it's a high-octane, trick-filled ride down treacherous slopes that will have you hooked from the first jump. Let's dive into everything you need to know about this surprisingly addictive free-to-play game.

Hi HeyGen Support,

I'm trying to generate AI avatar videos using audio of Haitian Creole speakers generated with ElevenLabs. I'm generating the AI avatar videos in HeyGen via make.com.

I'm using /v2/video/generate endpoint and trying to customize subtitles. When I send:

I created a video in your UI with b-roll. How can I get the same quality with API?

Hey Heygen Team,

Hello Admin Team,

We’ve been trying to track down the cause of increased latency for our non-US users. We went as far as setting up a new environment in another region for our application but found that the bottleneck seemed to be the avatar. While troubleshooting internally, we toggled the voiceChatTransport to “livekit” via the SDK’s createStartAvatar function and that seemed to immediately help significantly with latency, but the very first message we tell the avatar to repeat after the connection is established gets cut off and it starts speaking a different message we didn’t send. Is there a way we can have voiceChatTransport set to "livekit" without that undesirable message cutting off the text we asked the avatar to repeat?