Music Generation From Text Descriptions With Style And Instrumentation Control

via “style-conditioned music generation”

Meta's library for music and audio generation.

Unique: Implements dual-path conditioning where text and audio embeddings are processed through separate encoder branches before joint fusion in the transformer decoder, enabling independent control of semantic and stylistic information while maintaining generation efficiency.

vs others: Enables style control without requiring explicit musical parameters (tempo, key, instrumentation); more intuitive than parameter-based control and more flexible than simple style classification.