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.

4 min readSume
All posts

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.

Example module set and cost at Plus, no product image (Sume pricing, read 2026-10-05)
ModuleLengthPlus cost
Welcome and program tiers30 s$7.35
Register a deal25 s$6.13
Use the brand kit20 s$4.90
Request support20 s$4.90
Get paid, payouts30 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

All Use cases posts

Written by Sume