How to produce 30 episodes for a YouTube Shorts series
Thirty Shorts episodes are thirty identical jobs. Use one template, one Timeline call per episode with its own key, and a $3.00 render fee at 60 seconds.

To produce 30 episodes for a Shorts series, fix the episode template first, then run the same job 30 times: one Timeline 1.0 call per episode, each with its own Idempotency-Key. If every episode's output is 60 seconds or less, each render rounds up to one minute, so the Timeline fee is 30 times $0.10, or $3.00, before the clips and voice that go into them.
The series fact is from the Made on YouTube post for viewers and creators, read 2026-09-29; for YouTube's series rules see the Shorts series rules page. Sume facts are from the docs pages under Sources.
What does YouTube say about series?
The post says Shorts are "organized into dedicated seasons and episodes, making it easier than ever to watch microdramas and series". The page was marked coming soon when read, so confirm you have the feature before you plan a season around it.
What should the episode template fix?
Decide once: length, shape, opening, and closing. Avatar videos for a recurring presenter run 4 to 60 seconds and default to 9:16 at 720p, so a 60-second ceiling keeps the same job shape from first episode to last.
| Item | Value |
|---|---|
| Avatar video length per clip | 4-60 seconds |
| Timeline output size (default) | 1080 by 1920 |
| Timeline fee | $0.10 per output minute, rounded up |
| 30 episodes of 60 s or less | $3.00 in Timeline fees |
How do I render all 30?
Import each episode's clips and voice into your workspace first, since Timeline takes only media.sume.com files. Then loop, putting the episode number in the key so a retry never creates a second render. The audio spine accepts 1 to 1,800 seconds, and the video list takes 1 to 200 slots.
for n in $(seq -w 1 30); do
curl -s -X POST https://api.sume.com/v1/timeline-1.0/render \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: series-s1e$n" \
-d "{
\"audio\": { \"url\": \"https://media.sume.com/artifacts/artf_demo/ep$n.wav\", \"duration_seconds\": 45 },
\"video\": [ { \"source_url\": \"https://media.sume.com/artifacts/artf_demo/ep$n.mp4\", \"start\": 0, \"duration\": 45 } ]
}"
echo
doneWhat if an episode fails or needs a fix?
Re-run only that episode. Give the corrected render a new key such as series-s1e07-v2, so it is a separate request from the first attempt, and leave the other 29 alone.`, so it is billed as the new render it is.
Keep the source clips and voice files for every episode until the season is published. Timeline reads only your workspace's media.sume.com files, and a fix usually means swapping one input and rendering again.
How do I check episodes before publishing?
Timeline has an unbilled /plan preflight, so run one on episode 1 and reuse its shape. Watch the first and last renders in full and skim the rest. Upload and season assignment happen in YouTube Studio; Sume does neither.
Sources
Related posts
More in Use cases
- YouTube vertical thumbnail size: 9:16 at 2160x3840
YouTube's thumbnail help lists 9:16 at 2160x3840 for vertical videos, 10 MB on mobile podcasts, and 16:9 at 3840x2160. Make one with GPT Image 2.5 on Sume.
- Skincare video ads with AI: three Formats, one packshot
Skincare video ads can be made with AI from a packshot: a model-and-product studio film, an application or texture demo, or a before-and-after with proof.
- Snapchat Spotlight monetization: 30-second videos and follower rules
Snapchat's Monetization Program page says Spotlight videos must be 30 s or longer to earn revenue, with 50,000 followers and view-time limits. Sume builds 30 s+
- AI model for product photos on Sume: Auto or a pinned id
Sume does not rank image models for product photos. Use sume/auto when any good result will do; pin a model id for repeatable, reference-driven shots.
Written by Sume