40 background music tracks for $5.00: Sume music at 12.5 cents each
Sume music generation is $0.125 per audio, so 40 tracks cost $5.00 and 200 cost $25.00. Generate several takes per scene instead of one.
Sume lists music generation at $0.125 per audio. Forty tracks is 40 x 0.125 = $5.00, and a game with 12 levels and 5 takes each (60 tracks) is $7.50.
Takes per scene
Per-track pricing makes variety cheap. The table shows what take counts cost.
| Scenes | Takes per scene | Tracks | Cost |
|---|---|---|---|
| 8 | 5 | 40 | $5.00 |
| 12 | 5 | 60 | $7.50 |
| 20 | 3 | 60 | $7.50 |
| 40 | 5 | 200 | $25.00 |
Check the router
The public rate is a per-audio figure. The Music docs say Music 1.0 requests resolve through the Music Router, and the live price for any routed model is in GET /v1/catalog, so check it before a large run.
Worked example and checks
Selection is the real cost in generative music. If you listen to every take for ten seconds and keep one in five, 40 tracks give 8 usable beds for $5.00, or $0.625 per kept track. If you keep one in ten, the figure doubles to $1.25. Compute that number from your own keep rate before you decide how many to generate.
Music for video also needs a timeline pass to sit under speech. The Timeline render is $0.10 per output minute, so a 60-second ad with a generated bed costs $0.125 for the track and $0.10 for the render, $0.225 together, before any voice or footage.
What is not covered
It does not include a loop-point editor, stems, or licence paperwork. Listen to every take; price is not quality. Sume bills model and tool usage at the published rate on top of the plan fee, so the plan price is separate from every number in this post.
Sources
Related posts
More in Pricing
- 50 avatars for $47.50: Sume's creation fee is half a 10-second clip
Sume avatar creation is $0.95 each, so 50 avatars cost $47.50. A single 10-second Plus clip is $2.45 and a Standard one is $1.84, so creation is a small share.
- 7 Kling motion control clips of 12 seconds cost $13.23 on Sume
A week of seven 12-second Kling 3.0 motion control clips is 84 seconds, $13.23 at $0.1575 a second. Budget code, the reserve you need, and refunds.
- 72,000-character audiobook chapter on Sume TTS: $3.42 in 4 requests
Sume text to speech is $0.0475 per 1,000 characters with a 20,000-character cap per request. A 72,000-character chapter is $3.42 across four requests.
- 9-second voiceover with MiniMax H3 Max lip sync: $0.90 or $1.80
A 9-second line through MiniMax H3 Max lip sync on Sume costs $0.90 at 768p and $1.80 at 1080p. The 5 to 14.8 second window, the math, and a request.
Written by Sume