HeyGen Avatar 4 Image to Video

POST/v1/run

Heygen Avatar4 is HeyGen's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to heygen/heygen-avatar4/image-to-video.

Default: heygen/heygen-avatar4/image-to-video

Optional<string>prompt

The text the avatar will speak

stringimagerequired

URL of the image to animate. The image should contain a clear face.

Optional<string>audio

URL of an audio file for the avatar to lip-sync to. When provided, overrides prompt and voice.

Optional<string>aspect_ratio

Aspect ratio of the output video. 'auto' preserves the source aspect ratio when available.

Allowed values: 16:9, 9:16, 4:5, 5:4, 1:1, auto

Default: 16:9

Optional<string>voice

The voice ID to use for the avatar.

Default: Melissa

Optional<string>resolution

Video resolution preset.

Allowed values: 360p, 480p, 540p, 720p, 1080p

Default: 720p

Optional<string>talking_style

Talking style: 'stable' for minimal movement, 'expressive' for more animation.

Allowed values: stable, expressive

Default: stable

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: image-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "heygen/heygen-avatar4/image-to-video",
  "prompt": "Hey friends! Welcome to the GPU force podcast and today we are going to discuss about the rising GPU cost!",
  "image": "https://v3b.fal.media/files/b/0a90062c/A7EIviZqNxZ2HAs0yHeZ6_77a05b99-8588-4ffc-90aa-be7f9d34e9d3.png",
  "audio": "https://static.sandbase.ai/examples/input.mp3",
  "aspect_ratio": "16:9",
  "voice": "Melissa"
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/run_abc123 \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "run_abc123",
  "model": "heygen/heygen-avatar4/image-to-video",
  "status": "running",
  "outputs": []
}