Prerequisites
A portrait photo (PNG or JPEG) — clear, front-facing, good lighting
A
voice_id for the voice you want. Use GET /v3/models/audio/voices to browse voices.Step 1 — Create a Photo Avatar
Upload your photo and create a Photo Avatar withPOST /v3/avatars:
POST /v3/assets and pass "file": {"type": "asset_id", "asset_id": "RETURNED_ASSET_ID"} instead.
The response includes an avatar_item with an id — this is your avatar_id for video creation.
Step 2 — Generate the video
UsePOST /v3/videos with type: "avatar" and the Photo Avatar ID:
Step 3 — Poll for completion
Generation is asynchronous. PollGET /v3/videos/{video_id} until status is completed, then download video_url.
Motion and expressiveness
Photo avatars (avatar_type: photo_avatar) take a motion_prompt that directs body motion and hand gestures (e.g. “nodding gently”). On Avatar IV they also take expressiveness: high, medium, or low (default low). On Avatar 6, set engine.motion_expressiveness instead.
background, remove_background, voice_settings, and callback_url, is in the Create Video reference.
Using a preset Photo Avatar
You can skip avatar creation and use a public preset avatar instead:id from the response and use it directly as your avatar_id in POST /v3/videos.
