After ChatGPT, another representative of AI, Google has developed artificial intelligence MusicLM that can generate high-fidelity music.

CTOnews.com January 28 news, after ChatGPT, music may be the next important frontier of AI content generation.

On January 27, local time, Google released the results of its research on AI model MusicLM, which can generate any type of high-fidelity music from text descriptions. However, due to copyright issues, the researchers did not release MusicLM to the public.

"We stress that more needs to be done in the future to address these risks associated with music generation-we have no current plans to release models."

CTOnews.com warns that this is not the first AI music generation tool in human history. Both Google's AudioML and OpenAI's Jukebox project have solved this problem, but MusicLM has a huge model and training database (280000 hours of music) to produce music with greater diversity and depth.

As a result, artificial intelligence can not only identify and fully integrate the genres and instruments you want, but also write tracks using abstract concepts that are difficult for ordinary machines to grasp.

For example, if you want to create a mix of dance music and reggae music, requiring the tune to be "empty and otherworldly" and evoke "surprise and awe", MusicLM can help you quickly achieve it, even creating melodies based on buzzing, whistling or painting descriptions, and stitching multiple descriptions together in story mode to create the DJ or soundtrack you want.

Of course, like most AI, MusicLM has some unsolved understanding problems, and some of its works sound strange, even the human voice is difficult to understand.