Skip to main content

heygen/video-1/reference-to-video

HeyGen Video 1.0 is HeyGen’s video generation model; reference-to-video combines images, video, and audio into 5–15 second scenes at 480p or 768p.

From $0.102/s

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • Output5s
    Man and dropper bottle combined from two reference images

    With two reference images, a man and a dropper bottle, the 9:16 test showed the man holding that bottle and used both inputs. Processing took about 158 seconds.

    • 21
    • 480p
    • 9:16
  • Output5s
    Cobbled hill ride from image, video and voice references

    One image plus a four-second video and audio produced a result that followed the video’s motion and scene closely without carrying over the image’s face. Avoid a dominant reference video when preserving the photo’s person matters.

    • 11
    • 480p
    • 16:9

This example starts at $0.102 per output second. The Playground updates the estimate when you change the settings.