Preview an avatar scene before the full render

Synthesia's updates page lists, among its September 2026 improvements, individual scene preview with animated avatars. Sume's equivalent is the avatar video preview: it renders only the first-frame stills, lets you regenerate them, and starts the final video from the preview you approve.

What each side does

The Synthesia column is from its updates page. The two features are not the same thing: Synthesia describes previewing a scene with animated avatars, while Sume's preview is for composition and framing in the first frame, before any talking video exists.

The Sume preview flow

Create a preview with the same fields as an Avatar Video: exactly one of script or video_inputs, plus optional product_image, scene, quality, aspect_ratio, title and captions. quality defaults to plus. Poll the job like any generation, then read the preview resource for preview_image_url and scene_previews. Captions stored at create are applied only at generate-video; preview stills are never caption-burned.

Duration is the same window as Avatar Video: an estimated 4 to 60 seconds.

curl -X POST https://api.sume.com/v1/avatar-video-previews \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: preview-001" \
  -d '{
    "avatar_handle": "product_host",
    "script": "This is the new desk lamp, and it folds flat.",
    "aspect_ratio": "9:16"
  }'

curl -X POST https://api.sume.com/v1/avatar-video-previews/$PREVIEW_ID/generate-video \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: preview-001-final" \
  -d '{}'

Choosing the final quality

An empty body to generate-video keeps the quality chosen at preview create. An optional quality overrides only the final render tier, and the stills are tier-independent and always reused, so approving a preview does not lock your tier. Structural fields such as script, scene and aspect_ratio need a new preview.