Hardware Store DIY Tip Video With an AI Avatar: Cost per Clip

A hardware store can post a weekly tip in a consistent voice without scheduling an employee. Sume Avatar 1.0 renders each tip as a scripted clip of 4 to 60 seconds with the same reusable avatar.

Prices are from Sume's API pricing page and the request shape from Generate avatar video, both read on 2026-10-05. The avatar must exist first: Create new avatar accepts a prompt, a profile or a photo.

What should the script and scenes look like?

One tip per clip: the problem, the fix, the tool. Counts below use the 2.8 words per second estimate, rounded up per scene.

The seconds column is Sume's planning estimate of ceil(words / 2.8) per scene, not a measured render time.

POST https://api.sume.com/v1/avatar-1.0/talking-video
{
  "avatar_handle": "front_desk_host",
  "aspect_ratio": "9:16",
  "quality": "standard",
  "video_inputs": [
    { "id": "problem", "voice": { "type": "text", "script": "A dripping faucet wastes water and keeps you up at night." }, "background": { "type": "prompt", "prompt": "Bright, plain room, locked-off camera, soft daylight" } },
    { "id": "fix", "voice": { "type": "text", "script": "Turn off the supply valve, remove the handle, and replace the worn washer." }, "background": { "type": "prompt", "prompt": "Bright, plain room, locked-off camera, soft daylight" } },
    { "id": "tool", "voice": { "type": "text", "script": "You'll need an adjustable wrench and a washer kit, both in aisle six." }, "background": { "type": "prompt", "prompt": "Bright, plain room, locked-off camera, soft daylight" } }
  ]
}

What does it cost?

The plan above comes to 14 seconds, inside the 4 to 60 second window. At Sume's per-second rates (no product image), one render costs $2.58 on standard, $3.43 on plus (the default when quality is omitted) and $7.70 on max. Across 52 weekly tips, that is $133.95, $178.36 and $400.40. Creating the avatar is a separate one-time $0.95; later clips reuse the handle.

Does a repeating series stay on brand?

The avatar handle is created once at $0.95, and reuse is the point. Each clip then costs only its seconds, so a weekly series is predictable: 52 clips at the length above is the last column of the table.

Safety steps matter. Include them in the script; the avatar will not add warnings you did not write.

What will it not do?

It will not demonstrate hands-on work or answer a shopper's question. It reads one script per render.

Scripts for Avatar Video should be English; Sume's guidance is that non-English speech breaks caption alignment.