Partner onboarding: one avatar clip per module, not one long video
Split reseller training into 20-45 second Sume avatar clips, one per module. A 20-second Standard clip is $3.68, and you re-render only the module that changes.
Train channel partners with one avatar clip per module, 20 to 45 seconds each, and not one long video. Sume accepts avatar scripts that estimate to 4-60 seconds, so the format forces the right shape, and when a price list or process changes you re-render one module. A 20-second clip costs $3.68 at Standard, $4.90 at Plus, or $11.00 at Max (no product image).
Why modules beat a master video
Partner programs change constantly: margin tiers, deal registration steps, brand rules. A 15-minute master video is wrong in one place within a quarter, and nobody wants to re-cut it. A module per topic can be replaced independently, linked from the partner portal by name, and watched at the moment a partner needs it.
| Module | Length | Plus cost |
|---|---|---|
| Welcome and program tiers | 30 s | $7.35 |
| Register a deal | 25 s | $6.13 |
| Use the brand kit | 20 s | $4.90 |
| Request support | 20 s | $4.90 |
| Get paid, payouts | 30 s | $7.35 |
Authoring rules
Write each script for one action, with a single named place to click. Keep prices and dates out of the clip when they change monthly; point to the portal page instead. Use the same avatar across modules so partners recognize one guide; an avatar is created once and reused by handle. Review the first frame with a preview before the full render, and set aspect_ratio to 16:9 if the clips sit on a portal page.
import json
MODULES = {
"register-deal": "To register a deal, open the Deals tab, choose New deal, and add your customer's company name.",
"brand-kit": "Download the brand kit from the Resources page. Use the logo files as they are, without changes.",
}
for slug, script in MODULES.items():
body = {"avatar_handle": "partner_guide", "aspect_ratio": "16:9",
"quality": "plus", "script": script}
print(json.dumps(body))Keeping them current
- Keep a table: module slug, script, version, review date,
avatar_video_id, and where it is embedded. - When one fact changes, edit that script, create a new preview, approve, and render only that module.
- Use captions for training; partners often watch in an office or on a train.
- Render with Standard while drafting, then re-render the final at a higher tier. A preview's stills are tier-independent, so approving then changing quality does not need a new preview.
Limits
A clip also cannot answer a partner's question. Keep a contact or chat link beside every module.
Sources
Related posts
More in Use cases
- Check that a recorded ad says the required disclaimer: STT words
Transcribe an ad with Sume STT, match the disclaimer in words[], and fail the check if it is missing or starts in the last seconds. Python, 1 cent per minute.
- Check an AI thumbnail stays readable at 320x180 with a Pillow sheet
Generate a 1280x720 thumbnail with GPT Image 2.5, then shrink it to 640x360, 320x180 and 160x90 side by side to catch tiny text and weak contrast.
- Check prices survive translation before burning live-selling captions
A live-selling caption with a wrong price costs a $0.20 re-burn and a customer. Compare the digits of each source and translated cue with a ten-line check.
- Child's drawing to a picture-book page with GPT Image 2.5
Turn a child's drawing into a polished picture-book page: host the scan at a public HTTPS URL, pass it as a reference, and ask for 4:3. Code and Sume prices.
Written by Sume