AI avatar without a photo: Sume props input (age, sex, ethnicity)

If you have no photo of a presenter, create the avatar from text. Sume's POST /v1/avatar-1.0/generate accepts three input types: a prompt that describes the person, props for structured traits, or a photo for a reference image. The props input is the one for an app that already holds profile details. The docs' example sends ethnicity, sex and age (Create new avatar).

The props request

A top-level avatar_handle names the avatar and an input object carries the type. The docs' example reads:

• avatar_handle: product_host
• input.type: props
• input.ethnicity: Asian, input.sex: female, input.age: 28

Prompt or props?

Use prompt when you can describe the person in a sentence. Use props when the traits come from your own data and you want the request to be the same shape every time. Neither needs a public image URL; only the photo type does, and it must be a fetchable public HTTPS image.

After the create job

Each request creates a job. Poll GET /v1/jobs/:id/status until it completes and read the result, then pass the returned handle to Generate avatar video. Use an Idempotency-Key on the submit so a retry returns the original job instead of a second charge.