12 listing photos into a 60-second tour: $7.60 with Omni and Timeline

A 60-second tour from 12 listing photos costs $7.60 on Sume at 720p. That is twelve 5-second Gemini Omni Flash 1.1 clips at $0.125 a second ($7.50) plus one Timeline render at $0.10 per output minute. At 1080p the same tour is $11.35.

The Omni clips are the whole bill. Timeline only joins them, so the render adds a dime however many clips you stack, up to 200 video slots.

The arithmetic

Omni accepts 3 to 10 seconds in 16:9 or 9:16 at 360p, 720p, 1080p or 4K. Five seconds per room is long enough for one slow push-in. Twelve rooms at five seconds each is exactly 60 seconds, which Timeline bills as one output minute.

How the job runs

Each clip is its own asynchronous job. Submit with an Idempotency-Key, poll /v1/jobs/:id/status, then fetch /result. Pass the listing photo as the first frame so the room is the one you photographed. Once all twelve are ready, send their URLs as video[] slots to Timeline with audio.mode set to silence, or with a music file.

Timeline needs audio.duration_seconds to set the output length, so set it to 60.

Mix in stills

Timeline also accepts stills in video[], as static holds. A floor plan, an exterior shot or a price card can sit between the clips at no model cost, because only the render is billed. Set the slot duration for how long it holds, and use fit: contain so a floor plan is not cropped.

That cuts the clip count too. Ten room clips and two stills is $6.25 of Omni at 720p for the same 60 seconds.

What Sume does not do here

Sume does not check that a generated clip still matches the real room. A model can add a window, move a cabinet or smooth a flaw, and a buyer will notice. Review every clip against the photo before it goes on a listing, and drop any clip that changes the property.

Narration and music are separate jobs and are not in the $7.60. Walkthrough audio from text-to-speech is billed on its own line.

Rates are the Sume card on 2026-10-07. Read pricing_skus from GET /v1/videos/models before you budget, because the live card wins over this page.