Video inspect on Sume: 8 stills at 768 px and the fast seek option
Sume video inspect returns 8 mid-bin stills at a 768 px long edge by default, up to 24 stills, and a fast seek mode that can land one GOP early.

By default Sume video inspect returns the probe and 8 mid-bin stills with a long edge of 768 pixels. You can ask for 1 to 24 stills with frames.at[] or frames.fps (up to 2), raise max_edge up to 2160, or send frames: false for the probe alone. The source can be up to 1800 seconds. The numbers come from Video inspect, read 2026-10-06.
What does the seek option change?
seek picks how each still is found.
| `seek` | Behavior | Use it for |
|---|---|---|
precise (default) | Decodes to the accurate instant | Explicit at[] instants |
fast | Uses the keyframe at or before the instant, never later; up to about one GOP early | A quick look at a long clip |
What else does it return?
The default mode is sync and waits at most 30 seconds, then returns 200 with the result or 202 with a queued job. With transcribe: true it runs Sume STT at $0.01 per audio minute, and a clip with no audio track returns inspect_source_has_no_audio. Read probe.has_audio first with a frames: false call.
- Stills are durable
media.sume.comimage artifacts. - Probe and stills are billed by their Modal compute; transcription adds its per-minute rate.
- For an accurate frame at the source size use video frames.
Sources
Related posts
More in Media tools
- AI video upscaler API fields: factor 1.1 to 4 and fast, standard, pro
The Sume Video Upscale request takes upscale_factor from 1.1 to 4, duration_seconds from 1 to 30 and an enhancement_tier. What they do and cost.
- Voiceover longer than your clips: Timeline pads, loops, 0.5 s rule
If the voiceover outruns your clips, Sume Timeline still renders to audio.duration_seconds: short sources pad or loop, and coverage may stop 0.5 s early.
- Why a voiceover on an AI video clip never lip-syncs
Video models do not lip-sync to TTS or a later voiceover. Per Sume's docs a talking face comes from Fabric, H3 Max Lip Sync or an avatar talking-video job.
- Public URL or media.sume.com: which Sume media tool takes which
Sume video trim and timeline accept only media.sume.com URLs from your workspace. Captions and video upscale take a public HTTPS URL. Import first.
Written by Sume