Driving School Lesson Reminder as an AI Avatar Video: Cost

No-shows cost a driving school real money. A short reminder video from Sume Avatar 1.0, 4 to 60 seconds, can set expectations for a lesson in a friendly, repeatable voice.

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?

Cover what to bring, where to meet and the cancellation rule. Counts use 2.8 words per second, 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": "bring", "voice": { "type": "text", "script": "Your lesson is tomorrow. Please bring your learner permit and wear flat shoes." }, "background": { "type": "prompt", "prompt": "Bright, plain room, locked-off camera, soft daylight" } },
    { "id": "meet", "voice": { "type": "text", "script": "We'll meet you at the front of the school, ten minutes before your start time." }, "background": { "type": "prompt", "prompt": "Bright, plain room, locked-off camera, soft daylight" } },
    { "id": "late", "voice": { "type": "text", "script": "If you need to cancel, tell us at least twenty four hours ahead." }, "background": { "type": "prompt", "prompt": "Bright, plain room, locked-off camera, soft daylight" } }
  ]
}

What does it cost?

The plan above comes to 16 seconds, inside the 4 to 60 second window. At Sume's per-second rates (no product image), one render costs $2.94 on standard, $3.92 on plus (the default when quality is omitted) and $8.80 on max. Across 200 lesson reminders, that is $588.80, $784.00 and $1760.00. Creating the avatar is a separate one-time $0.95; later clips reuse the handle.

Can the cost scale with a busy school?

If every learner gets the same reminder, render once and send it to everyone: you pay for one render, not one per learner. The last column of the table is a worst case in which each of 200 reminders is its own render.

Reuse one clip per standard message. Per-learner variants multiply the cost by the number of variants.

What will it not do?

It will not confirm bookings or listen to a learner's replies. It is a fixed clip.

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