Google has created an impressive bot that can create music of all genres based on text prompts. However, the company has no plans of releasing it for various legal and ethical reasons. The system is called MusicLM. It is not the first of its kind but is the most advanced of all.
Suggested read: Google Might be Secretly Developing an Answer to AI-Based Text
Research paper
Google researchers describe the system as, “a model generating high-fidelity music from text descriptions such as ‘a calming violin melody backed by a distorted guitar riff.'” The research paper further states, “We demonstrate that MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melodies according to the style described in a text caption.”
The study suggests that people can enter descriptions such as “Berlin 90s techno with a low bass and strong kick,” or “enchanting jazz song with a memorable saxophone solo and a solo singer” and get results about the same. Samples of such music have been shared on Google’s GitHub blog site.
Competition
Google made the move of developing MusicLM to counter the popularity of OpenAi’s ChatGPT which is on the rise since its release. Google is also speeding up the process to launch 20 new products and a new version of Google Search with an integrated AI chatbot.
Google’s plan
However, as already mentioned Google is not ready to release the program, at least not yet. The co-authors of the research paper wrote, “We acknowledge the risk of potential misappropriation of creative content associated to the use case.” They added, “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.”
Also read: Google Pins Hope on AI Tech to help Read Medical Prescriptions
The study shows that about 1% of the music developed by the bot already exists pointing toward copyright infringement issues. There are other limitations as well about this technology. The researchers wrote that they plan to work toward “modeling of high-level song structure like introduction, verse, and chorus.”