In a recent development, Google has introduced a new AI technology called MusicLM, which helps users generate music from text descriptions. With this new attempt, Google has enabled the technology to create outputs that were not possible before
Notably, Google isn’t the first to try generative AI for songs, as there have been other attempts, including Riffusion, an AI that composes music by visualizing it, as well as Dance Diffusion, Google’s own AudioML and OpenAI’s Jukebox.
Follow RPRNA on Google News
Even having various attempts none have been able to produce songs particularly complex in composition or high fidelity, because of the technical limitations and limited training data. That’s why Google is fearing the risks and has no immediate plans to release this new AI music from the text.
Join us on Telegram
This new AI technology has been able to create more complex songs, with elements that are more in line with traditional music composition. It will be used to generate music in any desired genre with the help of MusicLM’s vast training model and database consisting of over 2,80,000 hours of music.
- eg, “enchanting jazz song with a memorable saxophone solo and a solo singer” or “Berlin ’90s techno with a low bass and strong kick” a
However, MusicLM is not yet ready to be used, but it hints at a future where AI could play a larger role in the studio.