Avatars

Create an avatar

Makes a reusable avatar: from one portrait photo (type: photo), or a digital twin from 15–600 s of footage of one person speaking (type: digital_twin — the voice is cloned from the same footage; the person must also record the provider's consent statement, see POST /v1/avatars/{id}/consent). Asynchronous: the execution finishes when the avatar is trained. Billed once per avatar; every video made with it is billed on its own. Needs your consent declaration (consent).

Billing: Per avatar created (photo avatar / digital twin) · Rate limit: 5/min · Asynchronous

post/v1/avatars

Request

  • Base URL: https://apihub.co.il
  • URL: https://apihub.co.il/v1/avatars
  • Auth: HTTP bearer

Headers

Idempotency-Keystring

Replay-safe: the same execution is returned instead of charging twice

X-Tagstring

Group calls into one job (e.g. one video) — see GET /v1/usage?tag=…

x-wait-msinteger

Wait for the job inside this call (ms)

Request body

namestring required

Your name for the avatar

type'photo' | 'digital_twin'

photo = one portrait photo · digital_twin = 15–600 s of footage of one person speaking (clones the voice too)

image_urlstring uri

photo: a clear, front-facing portrait (jpg / png)

video_urlstring uri

digital_twin: the training footage (mp4 / webm, 15–600 s, one person facing the camera, speaking)

consent_idstring

A consent you recorded before (the dashboard records one when you tick the box)

Response

Completed (or 202 while processing)

idstring

Execution id — stable across internal retries; use it with GET /v1/executions/{id}

status'pending' | 'processing' | 'completed' | 'partial' | 'failed' | 'cancelled' | 'timeout'
operationstring
tagstring nullable

Your X-Tag, if sent

created_atstring date-time
completed_atstring date-time nullable
outputobject

Operation result (see each operation). While a Studio render is processing: stage (queued · transcribing · downloading · preparing · cleaning_voice · mixing_audio · rendering · finishing), phase (the engine's: download · prepare · voice · audio · encode · qa · upload, or null), progress (a percent, 0–100) and progress_fraction (0–1), eta_seconds (seconds left, never below 0) and estimate_seconds

errorstring nullable

Changes

No recorded changes to this operation across all 2 revisions of this API.