Four Music 1.0 takes for a 45-second explainer: $0.50 total
Generate four candidate music beds for a 45-second explainer on Sume Music 1.0 at $0.125 flat each, $0.50 total, with a seven-axis brief to narrow the takes.

Four candidate music beds for a 45-second explainer cost $0.50 on Sume, because Music 1.0 is $0.125 flat per generation regardless of length. The better lever than generating more is writing a brief with the seven axes the docs list, so take two is closer to take one than a random draw.
What Music 1.0 takes
Music 1.0 runs on Google Lyria 3.5, accepts a text prompt and optional image conditioning, and has no seed, temperature, guidance or duration parameter. Duration is steered in the prompt, for example by asking for a 45-second track or using section markers such as [0:00-0:15] Intro. New integrations are directed to the Music Router, which Music 1.0 routes through.
Because the price is flat, a 45-second ask and a 3-minute ask cost the same $0.125, and the length is not guaranteed. Listen to the result and trim the bed in your render.
| Takes | Arithmetic | Cost |
|---|---|---|
| 1 | 1 x $0.125 | $0.125 |
| 4 | 4 x $0.125 | $0.50 |
| 8 | 8 x $0.125 | $1.00 |
The brief
The docs name axes that stop generic output: emotion, genre or lineage, tempo as a number, key and mode, and so on. A brief for a software explainer could be: calm and curious, minimal electronic with soft piano, 92 BPM, D minor, no vocals, no spoken word, building slightly at 0:30. Exclusions go into the positive prompt, such as no vocals.
Change one axis per take. Four takes at 80, 92, 104 and 116 BPM tell you more than four rewrites of the whole prompt.
Using the winner
Pass the chosen bed to Timeline 1.0 as soundtrack, with gain_db to set the level, fade_out_seconds up to 10 and duck_db from 0 to 20 so it sits under narration. The render is $0.10 per output minute rounded up, so a 45-second explainer is one billed minute.
Total for four takes plus the render is $0.60. Keep the prompt you used with the file name so you can reproduce the feel in the next episode.
A practical note
Listening is the real cost. Play each take under the narration, not on its own, because a bed that sounds rich alone often fights the voice. Check the first five seconds, where the explainer's hook sits, and the last five, where the track must resolve or fade. If none of the four fits, change the brief rather than adding a fifth random take. Note which axis you changed, tempo or genre, and keep that note with the chosen file name so you can brief the next episode the same way.
Before you scale
Every price in this post is a Sume list price read from the public catalog on 2026-10-09, and the arithmetic is shown so you can redo it with your own counts. Rates can change, so re-read the catalog before a large batch and run a small test first. Sume bills the job's captured amount, and the job result tells you what was used, so compare the first run's receipt with your estimate before you scale the work to the full set.
Sources
Related posts
More in Use cases
- Game teaser in 15 seconds: H3 Max start and end frame for $1.50
A 15-second teaser from two key-art frames costs $1.50 on MiniMax H3 Max at 768p on Sume. The image_url and end_image_url body, the 1080p price and the checks.
- Gate announcements: 8 messages in four languages, 32 TTS jobs
8 gate messages of 220 characters in 4 languages is 32 Sume TTS jobs at $0.01045 each, $0.3344 total. Set language and a matching voice per job.
- Demand Gen Shorts 9:16 full-bleed image ads: make the stills
Google's September Demand Gen drop adds 9:16 full-bleed image ads in Shorts. Make a test set of vertical stills with the Sume Image API and review them first.
- Google Play preview video: check the YouTube URL in Python
Google Play wants a plain YouTube URL: public or unlisted, embeddable, ads off, no timecode. A short Python check, plus how to make the MP4 with Sume first.
Written by Sume