Snapchat Spotlight needs 6 seconds: avatar clips that start at 4
Snap's Public Profile API takes Spotlight videos of 6 to 60 seconds, but Avatar 1.0 plans from 4. Plan scripts at 6 seconds or more and probe before posting.
A Sume Avatar 1.0 video can be as short as 4 seconds, but a Snapchat Spotlight posted through the Public Profile API must run 6 to 60 seconds. Write the script for at least 6 seconds of speech, then check the real duration before you post, because a 4 or 5 second hook clip fits the avatar window and misses the Spotlight window.
What does the Snap page say about Spotlight and Story lengths?
Snap's Profile Asset Management page lists separate video constraints per surface. Spotlights take MP4 video of 6 to 60 seconds at no less than 540x960 pixels. Stories take MP4 at 5 to 60 seconds with the same minimum resolution. A Spotlight also needs a description of up to 160 characters, which can include hashtags, and a locale such as en_US.
| Surface | Duration | Minimum resolution | Result states |
|---|---|---|---|
| Spotlight | 6 to 60 seconds | 540x960 | SUBMITTED, LIVE, REJECTED |
| Story | 5 to 60 seconds | 540x960 | SUCCESS, ERROR |
| Avatar 1.0 clip (Sume) | 4 to 60 seconds planned | 720p output | completed, failed |
How long is a Sume avatar clip, really?
The Avatar video docs say scripts and multi-scene plans are accepted when Sume estimates the target duration at 4 to 60 seconds inclusive. The word is estimate: the final file length follows the rendered speech, not your arithmetic. A script that Sume estimates at 6.0 seconds can still render shorter.
Output is 720p today, and aspect_ratio defaults to 9:16, which matches Snap's vertical requirement. 720p in 9:16 is 720x1280, comfortably above the 540x960 floor.
How do you stay safely above 6 seconds?
- Aim for an estimated 8 seconds, not 6, so a short render still clears the minimum.
- Use a multi-scene
video_inputsplan and add avoice.type: "silence"beat with aduration; silence beats count toward the planned total, which the docs say must stay in the 4 to 60 window. - Probe the finished clip with video inspect and compare
probeduration with 6 seconds before the post call. - If a render lands at 5.8 seconds, regenerate with a longer script instead of padding in a video editor.
What does the probe call look like?
Video inspect reads one clip on media.sume.com and is unbilled for the probe. Pass frames: false for probe facts only. The submit defaults to sync mode and waits up to 30 seconds.
curl -X POST https://api.sume.com/v1/video-inspect \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: spotlight-probe-001" \
-d '{
"video_url": "https://media.sume.com/artifacts/artf_demo/talk.mp4",
"frames": false
}'What Sume does not cover
Sume does not post to Snapchat in the docs I read. You still handle Snap's upload steps: the page describes AES-256-CBC encryption, chunking above 32 MB and a 1 GB maximum. Snap's own guidance on AI-generated Spotlight content is a separate question; see the earlier post on it before you plan a channel around avatar clips.
Sources
Related posts
More in Sume Avatar 1.0
- Sume Avatar API: canonical routes vs the legacy model-run aliases
Which Avatar 1.0 endpoint should a new integration call? The canonical /v1/avatar-1.0 routes, with the legacy aliases kept for compatibility. All paths listed.
- Tavus Memory Stores vs Sume: personalizing avatar video per person
Tavus PALs now keep persistent memory per participant. Sume avatar videos are one-shot renders, so personalization is in the script you send. Here is the split.
- Introducing Sume Avatar 1.0
Sume Avatar 1.0 is a multi-agent orchestration system as a single avatar model.
- Avatar Face Swap API (Beta): apply an avatar face to a video
Avatar Face Swap 1.0 is a Beta Sume endpoint that applies a ready avatar's face to a short public source video. Required fields, limits, and polling.
Written by Sume