Day-in-my-life Reel from 12 clips: one Timeline render and its cost

A 48-second day-in-my-life Reel from 12 clips is one Timeline 1.0 render: twelve video[] slots of 4 seconds, a silent spine, and a music bed. At Sume's listed rates the render itself is $0.10, because Timeline bills $0.10 per output minute rounded up, and a music generation is $0.125. Importing the clips costs more than the cut does.

Instagram's Reels guide (read 2026-10-03) calls 15 to 60 seconds the sweet spot for tutorials, day-in-my-life clips and most creative formats. Metricool's roundup (read 2026-10-03) reports that Instagram's iPhone First Draft tool trims pauses from multiple clips into an editable rough cut and works with day-in-the-life content. If you edit outside the app, this is the same shape of job.

The slot plan

Twelve clips at 4 seconds each is 48 seconds, so audio.duration_seconds is 48. Slot start values are on the spine, video[0].start must be 0, and later starts must increase. Each slot can carry its own source_in and duration, so you do not need to trim first: point the slot at the original clip and say where to start inside it.

Silent spine plus a bed

Timeline needs an audio spine to set the length. With no voiceover you can declare audio: { mode: "silence", duration_seconds: 48 } and add the music as a soundtrack: a url, a gain_db, loop if the track is short, and a fade_out_seconds of up to 10. The duck_db option needs a real spine, not silence, so leave it out here. Generate the bed with the Music Router: music takes no duration field, so put the length in the prompt, for example "a 50-second track", and check the artifact before you place it.

{
  "audio": { "mode": "silence", "duration_seconds": 48 },
  "soundtrack": { "url": "https://media.sume.com/artifacts/artf_demo/bed.mp3", "gain_db": -6, "fade_out_seconds": 3 },
  "video": [
    { "source_url": "https://media.sume.com/artifacts/artf_demo/c01.mp4", "start": 0, "duration": 4, "source_in": 1.2 },
    { "source_url": "https://media.sume.com/artifacts/artf_demo/c02.mp4", "start": 4, "duration": 4, "source_in": 0.5,
      "transition": { "type": "fade", "duration": 0.25 } }
  ]
}

What it costs

These are list prices read from Sume's catalog and docs on 2026-10-03; confirm live numbers with GET /v1/catalog.

What Sume does not do

Sume does not detect the best moment in a clip or remove pauses automatically; you choose source_in and duration yourself, or find the moments with video inspect sentence segments if the clips have speech. Slots shorter than 0.2 seconds are refused, and more than eight adjacent fades in a row need a hard cut inserted, as the Timeline 1.0 reference says. Stills inside a slot are static holds. A clip shorter than its slot is padded or looped with a warning, not a failure, so read warnings[] in the result.