Music Genre Detector with Mood, BPM & Key

Because genres are not a partition of music into boxes, and a tool that named one would be pretending otherwise. The boundaries were drawn by listeners, critics and record shops over decades, they overlap heavily, and a great many real tracks sit honestly between two — a song can be genuinely both indie rock and dream pop, and the argument about which is not a question the audio can settle. So the result is a ranked set with a confidence figure against each, and the interesting reading is the shape rather than the top line: three genres at similar scores means a track that borrows widely, while one at eighty and the rest far below means something that sits squarely in a tradition.

These two genres overlap musically (12-bar progression, blue notes, swing feel), and even experienced listeners disagree on borderline tracks. The model usually gets it right for clearly identifiable jazz or blues, but on jazz-blues fusion the top-3 list will list both and the percentages will be close. That gap itself is useful information.

Yes. The underlying model recognizes musical structure, not language. K-pop, J-pop, Russian rap, Arabic pop, Latin music, world traditional pieces all produce sensible genre, mood and instrument outputs.

The music model is downloaded on your first click ("Analyze track"). It is then cached by your browser for six months, so subsequent analyzes on the same device start instantly.

LAION CLAP (Contrastive Language-Audio Pretraining), the largest open-source music classifier available under the Apache 2.0 license. The text-side embeddings for every label are precomputed at build time, so your browser only loads the audio encoder.