Tenant Notice Video With Captions: AI Avatar for Property Managers

A property manager's tenant notice as a captioned avatar video: scene script, caption option and 60-second cap, request JSON, and Sume cost by quality tier.

4 min readSume
All posts

Notices about water shutoffs or lobby work get ignored as text. A short Sume Avatar 1.0 clip with inline captions can reach tenants who watch on mute. Total length stays between 4 and 60 seconds, and inline captions are limited to 60 seconds as well.

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?

Add a captions object to the request, e.g. enabled with style slam and language auto, as shown in Generate avatar video. Scene counts below use the 2.8 words per second estimate.

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

Scene plan and estimated seconds (read 2026-10-05)
SceneSpoken lineWordsSeconds
what"Water will be shut off in Building B on Thursday..."177
prep"Please fill a few containers the night before, a..."156
who"Questions? Call the office, and we'll follow up ..."114
Total4317
POST https://api.sume.com/v1/avatar-1.0/talking-video
{
  "avatar_handle": "front_desk_host",
  "aspect_ratio": "9:16",
  "quality": "standard",
  "captions": { "enabled": true, "style": "slam", "language": "auto" },
  "video_inputs": [
    { "id": "what", "voice": { "type": "text", "script": "Water will be shut off in Building B on Thursday, between nine in the morning and noon." }, "background": { "type": "prompt", "prompt": "Bright, plain room, locked-off camera, soft daylight" } },
    { "id": "prep", "voice": { "type": "text", "script": "Please fill a few containers the night before, and avoid running the dishwasher that morning." }, "background": { "type": "prompt", "prompt": "Bright, plain room, locked-off camera, soft daylight" } },
    { "id": "who", "voice": { "type": "text", "script": "Questions? Call the office, and we'll follow up the same day." }, "background": { "type": "prompt", "prompt": "Bright, plain room, locked-off camera, soft daylight" } }
  ]
}

What does it cost?

The plan above comes to 17 seconds, inside the 4 to 60 second window. At Sume's per-second rates (no product image), one render costs $3.13 on standard, $4.17 on plus (the default when quality is omitted) and $9.35 on max. Creating the avatar is a separate one-time $0.95; later clips reuse the handle.

Avatar Video, no product image, 17 seconds (rates read 2026-10-05)
QualityRate per secondOne clipTotal (1 clip)
standard$0.184$3.13$3.13
plus$0.245$4.17$4.17
max$0.55$9.35$9.35

What happens if captions fail?

Per Sume's docs, a caption failure is a soft failure, so the avatar video can still complete without them. Check the finished clip. A standalone caption job is $0.20 for up to 60 seconds if you want to add them afterward.

Spell out numbers and times as words in the script, because captions follow the spoken text.

What will it not do?

It will not replace a legally required written notice. Treat the clip as a courtesy alongside it.

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

Sources

Related posts

More in Use cases

All Use cases posts

Written by Sume