Three-minute Shorts vs 60-second avatar clips: how to build one
YouTube allows Shorts up to 3 minutes, but a Sume avatar job tops out at 60 seconds. Three jobs plus a $0.30 Timeline join make 180 seconds for $33.42.
A three-minute Short is 180 seconds, and one Sume avatar video job covers at most 60, so you need three jobs and a join. On the standard tier that comes to $33.12 for the avatar plus $0.30 for the Timeline render, $33.42 in total.
YouTube's help page on three-minute Shorts, read on 2026-10-04, says square or vertical videos up to three minutes long are categorized as Shorts. Videos uploaded after October 15, 2024 fall under that rule. Nothing forces you to use the full three minutes, but longer scripts are now allowed.
Build it from three 60-second parts
The avatar video guide caps one video at 4 to 60 seconds and tells you to split longer scripts. Write three scripts of about 60 seconds each, submit three jobs with the same avatar and a 9:16 aspect ratio, then join them with a Timeline render. Timeline bills $0.10 per output minute, rounded up, so 3 minutes is $0.30.
| Tier | Avatar, 3 x 60 s | Timeline join | Total |
|---|---|---|---|
| Standard ($0.184 per second) | $33.12 | $0.30 | $33.42 |
| Plus ($0.245 per second) | $44.10 | $0.30 | $44.40 |
Where the seams show
Each job renders its own avatar take, so the person resets at each join. Write the scripts so each part ends on a finished thought, and use a short transition such as fade in the Timeline. Check the first test render on a phone before you spend $44.
If the content does not need a full three minutes, a single 60-second job costs $11.04 on standard and avoids the join. Length should follow the script and not the platform's ceiling.
Sources
Related posts
More in Comparisons
- Sume vs Argil: AI avatar video and video agents compared
Argil makes AI-avatar and story videos with a chat agent, Director; Sume is a video agent with a multi-model API. Avatars, API, pricing, and limits compared.
- Sume vs fal: a generative media API or a video agent platform
fal runs 1,000+ image, video, and audio models behind one API. Sume adds a video agent, Formats, and avatars to a multi-model API. How the two surfaces differ.
- HeyGen alternatives with an API: price units, limits, and fit
HeyGen alternatives with an API: Synthesia, Creatify, Argil, Arcads, and Sume compared by price unit, API shape, limits, and live vs rendered avatars.
- Sume vs Higgsfield: two video agents compared on API, MCP, and price
Higgsfield and Sume both put a creative agent over many video models. How their agents, APIs, MCP servers, plans, and billing differ, from each vendor's pages.
Written by Sume