MAGNeT Medium 30s
Non-autoregressive MAGNeT checkpoint for 30 seconds of music.
Models
The named models and versions behind AI music tools.
113 results
MAGNeT Small 10s
Non-autoregressive MAGNeT checkpoint for 10 seconds of music.
MAGNeT Small 30s
Non-autoregressive MAGNeT checkpoint for 30 seconds of music.
Melodia v3
Latest Treblo song-generation model offered in the consumer product and as a preview API model.
MERT v1 330M
Self-supervised acoustic-music representation checkpoint for downstream MIR tasks.
MERT v1 95M
Self-supervised acoustic-music representation checkpoint for downstream MIR tasks.
Meta EnCodec 32 kHz (MusicGen checkpoint)
Neural audio codec checkpoint trained for MusicGen tokenization.
MiniMax Music 2.6
MiniMax model for original song, instrumental and cover generation exposed through product and API.
Moises-Light
Resource-efficient band-split U-Net architecture for music source separation developed by Music AI researchers.
Mubert AI Music API v3
REST API for text-to-music track generation, streaming, similarity and stem-level editing.
MuQ Large MSD Iter
Released MuQ-family checkpoint for music representation and retrieval.
MuQ-MuLan Large
Released MuQ-family checkpoint for music representation and retrieval.
Mureka O2
Current Mureka reasoning-oriented music-generation model released with V7.6.
Mureka V7.6
Current Mureka generative-music model released alongside O2.
Music Flamingo 8B
NVIDIA/UMD audio-language model for full-song understanding, reasoning and lyric transcription.
music2latent
Sony CSL Paris model for general-purpose latent audio compression.