Discussions
Technical Inquiry: Face Selection & Speaker Isolation in Multi-Person Photos (v2 & Avatar 4.0)
Hello Engineering Team,
Avatar IV endpoint /v2/video/av4/generate always outputs video with background — no transparency support?
The generated video always contains a baked-in background.
We need to place the avatar video on top of another background video, but the output does not include any alpha channel or true transparency.
Finding and Installing Video Agent API + Claude Code Skill.
I watched this HeyGen video on LinkedIn but simply couldn't follow it; one of the critical steps was rushed or perhaps the speaker just assumed that viewers would know what to do. Anyway, this looks like a great skill if I can work it out. They key step that was missed/rushed in the video was to show where to actually locate and then copy/paste the skill. Is this located somewhere on HeyGen or do i have to go to some other site to access it? Sorry, I normally can follow these things - I know how to create a HeyGen API and how to install a Claude skill but this one had me stumped. So hope someone can help?? Thanks!
Tiranga Game login
Tiranga Game login safety begins with user awareness. Always download the app from verified sources and avoid clicking unknown links claiming instant access. Two-step verification, where available, adds an extra layer of protection. Taking simple precautions during login helps safeguard funds, data, and overall account stability.
Technical Issue: Persistent 40001 Error on v1/asset Upload Endpoint (Multipart/Form-Data Failure)
Subject: Technical Issue: Persistent 40001 Error on v1/asset Upload Endpoint (Multipart/Form-Data Failure)
Inconsistency in id returned from list api vs actually availability in the create video api - V2
I am using the Heygen API - https://api.heygen.com/v2 for video creation, on passing in the avatar id fetched from list api for v2 - most of the IDs give the following error -
can we generate thunbnail with hook ot caption via api
Hello HeyGen Support Team,
voiceChatTransport cuts Interactive Avatar off and injects messages we didn't specify
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?
Emotions via API
Hello Team!
I love your tool and how AI generates shorts with avatars. However I can not conceive how can I send emotions (pronunciation) generated with the AI like: