Google’s new AI can generate music from text descriptions

Google researchers have developed an AI tool, MusicLM, that can generate high-quality music from text descriptions. It outperforms previous systems both in audio quality and adherence to the text descriptions, Google claimed in a research paper on Thursday. “We strongly emphasize the need for more future work in tackling these risks associated to music generation — we have no plans to release models at this point,” Google said in the research. The company’s future works may focus on lyrics generation, along with improvement of text conditioning and vocal quality, modeling of high-level song structure like introduction, verse, chorus, and modeling the music at a higher sample rate, according to the research paper.