HeyGen Video
HeyGen · AI videoHeyGen Video animates a still image into a 5–15 second clip with generated sound. The image is the first frame, so the clip opens on that picture.
On VidMachine, AI Video uses image-to-video at 768p. AI Influencer scenes use reference-to-video: the portrait, the scene's speech audio, and the spoken line written into the prompt. Both are 4 credits per second.
Key features and benefits
Image-to-video
Every clip starts from a still. Describe the motion in the prompt; the model keeps the opening frame and generates the movement and sound.
Fixed 768p
VidMachine always requests 768p. Other resolutions the provider offers are not selectable.
Reference-audio lip sync
AI Influencer clips send the portrait and speech audio as references, and append the transcript to the prompt so mouth motion follows the line.
Generated audio
Clips without a speech track include generated sound. Lip-sync clips follow the supplied audio.
Duration
Clips run 5–15 seconds. Shorter scene targets are raised to 5 seconds, and longer ones are capped at 15.
Technical specifications
ProviderHeyGen (HeyGen Video)
Primary inputsText prompt and a starting-frame image; lip-sync adds reference audio and the spoken line
Resolution on VidMachine768p
Aspect ratioFollows the starting frame
Duration5–15 seconds
AudioGenerated with the clip, or reference audio for lip sync
Pricing on VidMachine4 credits per second
Use cases and applications
Animate scene start frames into short motion clips for AI Video projects when you want the opening image held as the first frame.
Use it for AI Influencer talking-head scenes when you want lip sync from speech audio and the transcript in the prompt, at the same 4 credits per second.
Why this model
Pick HeyGen Video when you want image-to-video at a fixed 768p and a simple per-second price.
Compare the look with Hailuo 3 and other scene models in project settings before a long export.
What you should know
What resolution does VidMachine use?
768p only, at 4 credits per second.
Can I generate from a prompt without an image?
No. AI Video needs a starting frame, and AI Influencer lip-sync needs a portrait.
How long can a clip be?
5 to 15 seconds.
Can HeyGen Video do AI Influencer lip sync?
Yes. Influencer scenes send the portrait and speech audio as references and add the spoken line to the prompt. Pricing stays 4 credits per second at 768p.