Kickstarter Update Video With an AI Avatar and Product Image
Use an avatar to present a crowdfunding update with a product_image: script, seconds, request fields and Sume cost with and without the product image rate.
Backers expect updates, and a founder is not always free to film one. A Sume Avatar 1.0 clip with a product_image lets a consistent presenter introduce the product in 4 to 60 seconds. The product image changes the rate, so the math below uses both.
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 product_image (a public HTTPS URL) to the request and keep the script to one message. Scenes use Sume's 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 | Spoken line | Words | Seconds |
|---|---|---|---|
| news | "Backer update: the first production run of the L..." | 16 | 6 |
| what | "Here's the final finish, a matte graphite shade ..." | 13 | 5 |
| next | "Pledge managers go out next Tuesday, so check yo..." | 11 | 4 |
| Total | 40 | 15 |
POST https://api.sume.com/v1/avatar-1.0/talking-video
{
"avatar_handle": "front_desk_host",
"aspect_ratio": "1:1",
"quality": "plus",
"product_image": "https://example.com/lumo-lamp.jpg",
"video_inputs": [
{ "id": "news", "voice": { "type": "text", "script": "Backer update: the first production run of the Lumo desk lamp has shipped to the warehouse." }, "background": { "type": "prompt", "prompt": "Bright, plain room, locked-off camera, soft daylight" } },
{ "id": "what", "voice": { "type": "text", "script": "Here's the final finish, a matte graphite shade you voted for last month." }, "background": { "type": "prompt", "prompt": "Bright, plain room, locked-off camera, soft daylight" } },
{ "id": "next", "voice": { "type": "text", "script": "Pledge managers go out next Tuesday, so check your email then." }, "background": { "type": "prompt", "prompt": "Bright, plain room, locked-off camera, soft daylight" } }
]
}What does it cost?
The plan above comes to 15 seconds, inside the 4 to 60 second window. At Sume's per-second rates (with a product image), one render costs $2.91 on standard, $3.87 on plus (the default when quality is omitted) and $8.70 on max. Creating the avatar is a separate one-time $0.95; later clips reuse the handle.
| Quality | Rate per second | One clip | Total (1 clip) |
|---|---|---|---|
| standard | $0.194 | $2.91 | $2.91 |
| plus | $0.258 | $3.87 | $3.87 |
| max | $0.58 | $8.70 | $8.70 |
How much does the product image add?
On the public rate card read on 2026-10-05, a product image adds a small per-second increment: standard $0.184 becomes $0.194, plus $0.245 becomes $0.258, and max $0.55 becomes $0.58. That is a difference of $0.01 to $0.03 per second, so it is small next to the tier choice.
Add the field "product_image": "https://..." next to avatar_handle. Per Generate avatar video, media fields must be fetchable public HTTPS URLs.
What will it not do?
It will not guarantee the avatar handles the product exactly as shipped. Check the rendered frame against your real product and use a preview first. It also cannot answer comments from backers live.
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
- Kitchen gadget UGC demo: 15 seconds on Seedance 2.5 with references
Make a 15-second UGC-style kitchen gadget demo on Seedance 2.5 using a product photo and a voice clip as references: prompt, limits on Sume, and cost at 720p.
- Knitwear flat-lay to a moving on-model ad: three colorways for $5.92
One flat-lay, three colorways: three $0.0835 on-model image edits, then three 5 s Seedance 2 clips at $1.89. $5.92 on Sume, plus the check to run between.
- Landscaping yard transformation clip: Seedance 2.5 first+last frame
Send the muddy yard as first_frame and the finished lawn as last_frame to Seedance 2.5 on Sume: 8 seconds at 16:9 is $2.15 at 480p, $4.62 at 720p.
- Licensed voices only: what an ad team checks before take one
Microsoft says MAI-Voice-2 synthesizes only authorized, licensed voices. Here is the rights checklist to run for any AI voiceover, and what Sume's docs cover.
Written by Sume