Description
Researchers at American tech giant Google have created an AI that can generate minute-long pieces of music from text prompts, and can even transform a whistled or hummed melody on other instruments, similar to systems like DALL-E that generate images. based on written instructions. The Verge, an American technology news site, via TechCrunch. According to the outlet, the model is called MusicLM, and while you can't play with it, the company has uploaded a bunch of samples it produced using the model. ALSO READ: Have you ever wondered what the historical rulers of India looked like? These AI-generated images will blow your mind
The examples are impressive. There are 30-second snippets of what sound like actual songs created from paragraph descriptions that prescribe a specific genre, mood, and even instruments, as well as five-minute tracks spawned from one or two words like "melodic techno." ". "
The demo site also features examples of what the model produces when asked to generate 10-second clips of instruments like cello or maracas, eight-second clips of a certain genre, music that would fit a prison break, and even what a beginning pianist would sound like compared to an advanced player. It also includes renditions of phrases like "futuristic club" and "death metal accordion," reported The Verge.
ALSO READ: Why this institute in Bangalore restricted the use of ChatGPT for students
MusicLM can even simulate the human voice, and while it seems to get the overall pitch and sound of vocals, there's one quality that's definitely wrong.
According to The Verge, AI-generated music has a long history stretching back decades; there are systems that have been credited with writing pop songs, copying Bach better than a human in the '90s, and accompanying live performances.
