Reels run to 20 minutes; Sume's audio and caption limits to plan for
Instagram says Reels can reach 20 minutes but over 3 minutes is not recommended. The Sume Timeline audio, avatar and caption limits that matter at that length.
Instagram's Reels page says clips can add up to 20 minutes, but Reels over 3 minutes will not be recommended to new audiences (read 2026-10-03). Sume's Timeline accepts an audio spine of 1 to 1,800 seconds, so a 20-minute Reel fits. The tighter Sume limits are on captions: a standalone caption job covers videos up to 60 seconds, and inline avatar captions are rejected above 60 seconds.
Limit by limit
The numbers come from Instagram's Reels page and the Sume docs for Timeline, avatar videos and video captions.
| Where | Limit |
|---|---|
| Instagram Reels | Up to 20 minutes; over 3 minutes not recommended to new audiences |
| Sume Timeline audio spine | 1 to 1,800 seconds |
| Sume Timeline price | $0.10 per output minute, rounded up |
| Sume avatar video | 4 to 60 seconds per video |
| Sume caption job | Videos up to 60 seconds, up to 1,200 words |
What it means for a long Reel
For anything over a minute, cut the narration into pieces of 60 seconds or less, caption each piece, then join the captioned pieces in Timeline. A 10-minute Reel is billed as 10 output minutes, so $1.00 at the listed rate. Keep the 3-minute recommendation line in mind: Instagram's page ties reach to length, so a long cut is a choice about distribution, not a technical limit.
Sources
Related posts
More in Comparisons
- Kling 3 vs Seedance 2.5 vs Wan 3.0: 5-second 720p price on Sume
A 5-second 720p clip on Sume: Wan 3.0 $0.625, Kling 3 with audio $1.05 (audio off $0.70), Seedance 2.5 $2.889. List x 1.25 for every model.
- Midjourney alternative for product stills by API: what to send on Sume
Sume's image catalog has no Midjourney model. For product stills it lists reference-based edit models instead; here is which id fits which job, and how to test.
- Pocket TTS voice cloning: a wav in, and what Sume does instead
Pocket TTS clones from a wav file you pass to --voice, with consent rules in its model card. Sume's API takes voice ids, not audio. Here is the difference.
- Schedule a weekly AI video: Sume Scheduled, Hermes cron or API
Three ways to run an AI video on a weekly clock with Sume: a dashboard schedule, a Hermes cron job, or plain cron calling a Format. What each can and cannot do.
Written by Sume