Google’s new AI tool, called MusicLM, was trained on a dataset of 280,000 hours of music and will have the potential for going beyond song clips to generate songs from existing melodies, which could be sung, whistled or hummed.

However, TechCrunch reports that Google currently has no immediate plans to release MusicLM. The new tool is capable of generating songs of "significant complexity", which range from “enchanting jazz song with a memorable saxophone solo and a solo singer” to “Berlin ’90s techno with a low bass and strong kick.”