Avatar video previews: test three holiday hook lines, render only one
Create three Sume avatar-video previews with different hooks, compare first frames, then call generate-video on the winner and keep its stills.
Preview first, pay for the full render once
Create one avatar-video preview per hook line, compare the first-frame stills, and call generate-video on only the preview you like. A preview generates the first-frame still stage without starting the full talking-video render, so you review composition before spending on the final render.
For a holiday campaign the variable is usually the hook. Three previews with the same avatar and scene but different script values show whether the framing suits each line, and only one goes to a full render.
The four routes
The preview resource has four routes. Create takes the same fields as an Avatar Video request: exactly one of script or video_inputs, plus optional product_image, scene, quality, aspect_ratio, title and captions.
| Route | Use |
|---|---|
| POST /v1/avatar-video-previews | Create a preview job |
| GET /v1/avatar-video-previews/:id | Read the resource; preview_image_url and scene_previews[] |
| POST /v1/avatar-video-previews/:id/regenerate | Refresh stills from the stored request |
| POST /v1/avatar-video-previews/:id/generate-video | Start the final render from the preview |
Create, then generate
Preview stills are never caption-burned. Captions set at create are stored and applied at generate-video. An empty body keeps the quality chosen at create; an optional quality overrides only the final render tier, and the preview stills are reused either way.
curl -sS -X POST https://api.sume.com/v1/avatar-video-previews \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: hook-a-001" \
-d '{
"avatar_handle": "sume_clawra",
"script": "I almost skipped this gift set, then I opened it.",
"scene": { "type": "prompt", "prompt": "Cozy living room, string lights" },
"quality": "standard",
"captions": { "enabled": true, "style": "punch" }
}'What can change after approval
Structural fields (script, video_inputs, avatar_handle, scene, aspect_ratio) still require a new preview, so lock them before you compare. Read resource_status for readiness and job_status for polling rather than the legacy status. If the stills are wrong but the request is right, regenerate keeps the same preview id and only starts a new preview-only job.
Sources
Related posts
More in Sume Avatar 1.0
- Avatar video price by length: 4, 15, 30, 45 and 60 seconds
What a Sume Avatar Video 1.0 clip costs at 4, 15, 30, 45 and 60 seconds on standard, plus and max, with and without a product image. Table from the rate card.
- Sume Avatar Video quality default: what plus costs vs standard
Omit quality and Avatar Video runs on plus, not standard. On 20-second clips that is $1.22 more each, or $122 over 100 clips. The arithmetic and a safe default.
- Azure photo avatar is 512x512; Sume avatar video is 720p
Azure's photo avatar renders head-only at 512x512 and 25 fps. Sume's avatar video offers 720p in five aspect ratios, from a prompt, traits or a photo.
- Azure avatar batch: 20-minute videos, 200 jobs, vs Sume
Azure's text to speech avatar batch API allows 20-minute outputs and 200 concurrent jobs per Speech resource. Sume avatar videos run 4-60 seconds per job.
Written by Sume