MusicLM, a model generating high-fidelity music from text descriptions such as "a calming violin melody backed by a distorted guitar riff". MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task.

The model goes beyond creating short song segments. Google researchers demonstrated MusicLM's ability to expand existing tunes, whether hummed, sung, whistled, or played on instruments.

What about copyright?

Google researchers note the many ethical challenges posed by a system like MusicLM, including a tendency to incorporate copyrighted material from training data into the generated songs.

Source: https://techcrunch.com/2023/01/27/google-created-an-ai-that-can-generate-music-from-text-descriptions-but-wont-release-it/