Audio

Music Generation

Generating music from text, audio, or other inputs.

1
Datasets
5
Results
fad
Canonical metric
Canonical Benchmark

MusicCaps

Music generation evaluated on 5.5K expert-annotated music clips

Primary metric: fad
View full leaderboard

Top 10

Leading models on MusicCaps.

RankModelfadYearSource
1
MusicGen-Medium
4.892023paper
2
AudioLDM 2-MSD
4.472024paper
3
MusicLM
4.002023paper
4
AudioLDM-M
3.202023paper
5
AudioLDM 2-Full
3.132024paper

All datasets

1 dataset tracked for this task.

MusicCaps

CANONICAL
5results·fad
Top: MusicGen-Medium — 4.89

Related tasks

Other tasks in Audio.

Audio CaptioningAudio ClassificationAudio-to-AudioSound Event DetectionText-to-AudioVoice Activity Detection