Back to glossary

Generative Music

Music composed by an AI model from a text or mood prompt, rather than recorded or licensed from a catalog.

Generative music is composed by an AI model from a prompt — a mood, genre, tempo, or reference track — rather than recorded by musicians or licensed from a stock library. It can be generated to an exact duration, which matters when a music bed needs to land precisely at a video's length.

Like other generative audio, it sits alongside licensed and stock options rather than replacing them outright — the right choice depends on how specific the mood and instrumentation need to be.

See also: Waveform, Audio Ducking.

Put these ideas into motion.

Download

Frequently asked questions

Generative music is composed by an AI model in response to a prompt — a mood, genre, or reference — rather than being recorded by musicians or licensed from a stock catalog.

It can be tailored to an exact duration and mood on demand, and sidesteps the licensing and search overhead of browsing a stock library for the right cue.

Ready to tell your story?

Describe an idea and watch the agent animate it — on your Mac, in minutes.