CassetteAI Music

CassetteAI makes long-form instrumentals: up to three minutes of music from one description, enough to score a video in one run.

CassetteAI generates instrumental tracks up to 180 seconds, the longest music output in the catalog. Describe genre, mood and instrumentation, set a duration, and get a track long enough to underscore a full video without looping.

Billing scales with output length, so a 30-second sting costs a fraction of a 3-minute score.

At a glance

  • Type: Instrumental music
  • Duration: 30–180 seconds
  • Input: Text description (genre, mood, instruments)
  • Pricing: Scales with output length

What it is best at

  • Up to 3 minutes in one generation, with no looping needed
  • Duration control matched to your edit length
  • Cost scales with length, so short stings stay cheap

What it costs

From 2 tokens ($0.02) per track; 4 tokens ($0.04) at the default settings.

SettingsTokensPrice
30 s2$0.02
60 s4$0.04
90 s6$0.06
120 s8$0.08
180 s12$0.12

Prices come from the live catalog at $0.0100 per token, the pay-as-you-go rate; subscriptions include tokens at a lower rate. The exact price is shown before you generate, and a failed generation is refunded.

Questions

Does CassetteAI generate vocals?
No, CassetteAI is instrumental. For songs with sung lyrics, use MiniMax Music; the two sit side by side in the audio picker.
How do I match CassetteAI music to my video length?
Set the duration control to your edit’s length (30–180 s), or generate long and trim on the timeline. Audio clips trim and fade like any other clip.
What does CassetteAI cost?
Billing is per output minute, converted to tokens and shown in the picker.