MusicLM
MusicLM is an AI model developed by Google Research that generates high-fidelity music from text descriptions. It produces 24 kHz music consistent over several minutes, outperforming previous systems in audio quality and text adherence. MusicLM also supports transforming whistled or hummed melodies according to text descriptions. The MusicCaps dataset, containing 5.5k music-text pairs with rich descriptions, is publicly released for future research.