24 videos for 8 markets: the music and render line is $3.40
A campaign of 8 markets x 3 lengths (15, 30, 59 s) needs 24 renders at $0.10 and 8 beds at $0.125. $3.40 against $5.40 for a bed per video; footage excluded.

A campaign of 24 videos (8 markets, each in 15, 30 and 59 seconds) costs $3.40 for music and assembly on Sume if you generate one bed per market and reuse it across the three lengths: 8 x $0.125 = $1.00 for beds and 24 x $0.10 = $2.40 for renders. That is $0.142 per video and excludes the footage and voice.
The 59-second ceiling matters because YouTube blocks a Short over one minute that carries an active copyright claim (read 2026-10-08), and a render of 60 seconds or less bills one minute on Timeline 1.0, so every cut in this plan sits in the cheapest billing tier.
Three plans compared
The question is how many beds to buy. Music 1.0 is a flat $0.125 per generation, and Timeline renders are $0.10 per started output minute. All 24 videos are 59 seconds or shorter, so each render is 1 minute.
| Plan | Beds | Renders | Arithmetic | Total | Per video |
|---|---|---|---|---|---|
| One bed for the whole campaign | 1 | 24 | 1 x $0.125 + 24 x $0.10 | $2.525 | $0.105 |
| One bed per market | 8 | 24 | 8 x $0.125 + 24 x $0.10 | $3.40 | $0.142 |
| One bed per video | 24 | 24 | 24 x $0.125 + 24 x $0.10 | $5.40 | $0.225 |
Which plan to pick
Choose by what changes between markets. If the markets differ in language only, one bed works: the Timeline soundtrack field takes one URL plus gain_db, loop, fade_out_seconds (up to 10) and duck_db (0 to 20), so you can reuse the same file under eight voices and duck it per market.
If the markets differ in taste (for example a faster tempo for one region), one bed per market is the plan. The brief for each bed changes the genre family, the tempo and the lead instrument, as the Music 1.0 page suggests for contrasting scenes, and the cost is $0.875 more than the one-bed plan.
A bed per video is only worth it when each video needs its own music, which is rare in a localisation run. It costs $2.875 more than the one-bed plan, more than the whole 24-render bill.
Notes on the setup
The 15-second version needs the 59-second bed to end cleanly: set soundtrack.fade_out_seconds (the docs cap it at 10 seconds). The render's own length is audio.duration_seconds, so a longer bed does not lengthen the video. Check the first 15-second render by ear before you queue the other 23, since a render is $0.10 and a re-roll of the whole batch is $2.40.
Tag every bed with the market code through the metadata field. The Music docs say Sume stores it on the job and does not send it to the provider.
Sources
Related posts
More in Pricing
- 2,400 voice notes of 25 seconds: Sume STT $24.00 direct, $11.20 joined
2,400 clips of 25 s are 1,000 minutes. One request per clip bills the 1-cent minimum, $24.00; joining 20 per file first costs $11.20. Read 2026-10-08.
- 25-day Black Friday countdown series: 6-second clips cost $21.52
Twenty-five daily countdown clips, 6 s of Omni Flash 720p each with a voiceover and one shared music bed, cost $21.52 on Sume ($22.70 with the 5.5% fee).
- A $25 cap on Omni 4K: six 10-second clips and the leftover
With $25, Gemini Omni Flash 1.1 at 4K gives six 10-second clips ($22.50) and $2.50 left, enough for two more 3-second 4K clips. The reserve math on Sume.
- Real estate listing voice-overs: 25 homes at 700 characters
25 listing narrations of 700 characters cost $0.385 on MAI-Voice-2.1, $0.263 on Flash, and $1.00 on Sume TTS as 25 jobs. See the batched figure.
Written by Sume