Media inputs
Launch generation requests accept media as public HTTPS URLs in the exact fields shown by the live OpenAPI schema. You do not need to create a separate Sume asset before submitting normal Avatar 1.0, Avatar Video, face-swap, or caption requests.
Input URL fields
| Workflow | Field | Use for |
|---|---|---|
| Avatar 1.0 photo input | input.image_url | A reference photo for input.type: "photo". |
| Avatar Video product branch | product_image | An optional product/reference image. |
| Avatar Video scene photo branch | scene.image_url | An optional scene reference when scene.type: "photo". |
| Avatar Video scene background image | video_inputs[].background.url | Per-scene image background when background.type: "image". |
| Face swap (Beta) | video_url | Public HTTPS source video for face-swap. |
| Video captions | video_url | Public HTTPS source video to caption. |
Input image/video URLs must be fetchable public HTTPS URLs. Localhost, private-network URLs, non-HTTPS URLs, signed/private URLs, and mismatched content types are rejected before generation submission.
Avatar photo example
Use input.type: "photo" with a public HTTPS image_url (edit fields below as needed):
Create an Avatar 1.0 identity
POST /v1/avatar-1.0/generate
Required
Avatar Video product example
Create an avatar talking video
POST /v1/avatar-1.0/talking-video
Required
Omit quality to use the OpenAPI default plus.
Face-swap source video example
Create a face-swap job (Beta)
POST /v1/models/sume/avatar-face-swap/v1.0/runs
Required
Generated artifacts
Completed jobs can include artifact objects:
Sume mirrors generated outputs into Sume-owned media URLs before exposing them in public results. Integrations should store the Sume URL, not raw provider URLs. Signed upload/download URLs and private object keys are not part of the launch public API contract.
Trending videos returns public watch URLs for research; it does not mirror downloadable source files in the MVP.