Google’s new AI tool turns text into Music: Details

The tool was trained on a dataset of 280,000 hours of music to learn to generate coherent songs for descriptions. “MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes,” says a research paper published by Google.

According to a report by TechCrunch, Google fears potential risks associated with the tool and has no plans to release it. “We acknowledge the risk of potential misappropriation of creative content associated to the use case. We strongly emphasize the need for more future work in tackling these risks associated to music generation,” the co-authors of the paper wrote.

It must be noted here that Google is not the first company to work on generative AI tools. There have been similar attempts in the past. Riffusion, OpenAI’s Jukebox andGoogle’s one AudioML are some examples.

Google’s MusicLM comes with multiple features like Audio Generation From Rich Captions, Long Generation, Story Mode, Text and Melody Conditioning and Painting Caption Conditioning. The AI can also detect various musician experience levels, places, epochs, accordion solos and generation diversity.

In another news, the tech company will reportedly set stricter measures when it comes to outdated apps being installed on new devices, suggests a newly listed code. Android 14, as per a GSMArena report, will not allow even sideloading apps that target older versions of the OS. At present, Google doesn’t allow newly listed apps on Google Play to target Android versions older than 12. However, they can still sideload older software.