Google researchers unveiled a new AI that creates music from text descriptions.  The new model, MusicLM, has outperformed other AI music generators in its audio quality.  MusicLM was trained on over 280,000 hours of music, making it able to create new high-quality song tracks of different genres and instruments. Users can also sing, whistle, or hum to build upon a melody. The model "generates music at 24kHz that remains consistent over several minutes," according to researchers. The system is based on Google's Transformer neural network architecture, which has been particularly useful in the AI fields of natural language processing and computer vision. Due to copyright issues, Google will not release MusicLM publicly yet.