HeyGen Video Text to Video

HeyGen Video Text to Video turns a text prompt into a 5-15 second video at up to 2K resolution.
heygen/heygen-video/text-to-video

HeyGen Video Text to Video turns a text prompt into a 5-15 second video at up to 2K resolution.

Try the model

Playground

Open playground
Input
Describe the scene, action, camera and sound.
Additional Settings More

Customize your input with more control.

Output frame shape. Allowed values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
Output resolution. 1080p and 2k cost more. Allowed values: 480p, 768p, 1080p, 2k.
515
Output length in seconds (5-15). Range: 5 to 15.
Result
Example
  1. What would you like to do next?

    Open original

Saved example result. No new generation was requested.

Displayed run estimate: $0.18. Final charges follow the model’s billing rules below.

HeyGen Video Text to Video

HeyGen Video turns a text prompt into a 5–15 second video at up to 2K resolution.

Fields

FieldTypeDefaultNotes
promptstring, required—Scene, action, camera and sound.
aspect_ratio21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:1616:9Output frame shape.
resolution480p / 768p / 1080p / 2k768pOutput resolution; 1080p and 2k cost more.
duration5–155Output length in seconds.

Billing

Billed per output second: $0.02 at 480p, $0.036 at 768p, $0.06 at 1080p and 2k.

OutputPrice
5s, 768p (default)$0.18
5s, 480p$0.10
10s, 1080p$0.60
15s, 2k$0.90
Failed runs are not charged.

Prompting

  • Describe subject, action, camera move and light in order.

Limits

  • Clips are 5–15 seconds.

Also on SandBase

Other HeyGen Video endpoints: heygen/heygen-video/image-to-video, heygen/heygen-video/reference-to-video.