If you have played with ChatGPT, you know how impressive (and scary) AI can be. ChatGPT can generate almost anything you ask for, using prompts as simple or complex as you can think of. Well, Google has figured out how to do the same thing. But instead of spitting out poetry or computer programs, Google’s AI can create music and preview it.current work.
Google’s AI, called MusicLM, is designed to generate minutes of high-quality music based on text prompts. AI music isn’t necessarily new, but the company claims its program produces more accurate tracks for the first text prompt. When Better quality than the previous model. A big claim, of course. But Based on these previewsthey may live to suit them.
The first batch shows how MusicLM generates music from rich captions, similar to how OpenAI’s ChatGPT generates famous responses from user requests. Google can feed MusicLM with captions like: “The main soundtrack for an arcade game. It’s fast-paced and upbeat, with catchy electric guitar riffs. The music is repetitive and memorable, but contains unexpected sounds like cymbal crashes and drumrolls.” ” and the AI will process the tracks that meet these criteria.
My personal favorites in this section are the songs generated from “funky productions with strong, danceable beats and prominent basslines”. A catchy melody from the keyboard adds a layer of richness and complexity to the song,” on page two. Stardew Valley.
where is the uncanny valley TRUE However, it is always included when Google asks MusicLM to produce vocals. Many of Google’s examples here include AI voices, some sound “computer-like” for lack of the right word, and others sound a little too close. Listening with full knowledge that the voice is 100% artificial can be a little disturbing. Google even commissioned his MusicLM to create a rap track, and let’s be honest, “rap” is eerily real.
G/O Media can earn commissions
health
The Lyma Supplement
10 ingredients. One super-supplement.
Lyma makes the next generation of supplements—peer-reviewed and formulated to unlock your potential.
If you really want to be creeped out, scroll down to the “Text and Melody Conditioning.” Here, you can hear a series of voices and instruments doing their best with different melodies, and the results are wild. The very first option sees MusicLM humming “Bella Ciao,” and it sounds way too good. Side note: The “Tribal drums and flute” version is giving White Lotus.
We also have “Long Generation,” which produces five-minute long tracks from short descriptions, like “melodic techno” or “relaxing jazz.” But things get really interesting with “Story Mode.” Google feeds MusicML multiple captions, and the AI adjusts the song based on the given caption. It starts with 15 seconds based on “time to meditate,” before the caption switches to “time to wake up.” The music smoothly changes in tune, as if it was starting up a new verse, with some creepy vocals to boot.
Creepy vocals aside, it’s fascinating to see the AI alter the song without having to change the song. For the most part, it incorporates the new caption into the song, without feeling like you’re jumping into a new tune altogether. It’s particularly impressive with the third example, which sees the AI jump from “pop song” to “rock song” to “death metal song.” While “rock song” doesn’t particularly sound like rock, “death metal song” is simply fantastic. I imagine AI Death will be a big hit with metal heads.
Another interesting experiment Google did was feed MusicLM descriptions of famous paintings to see what music it would produce. If you ever wanted to know what Vincent Van Gogh’s “The Starry Night” would sound like as a song, well, now’s your chance. It’s also fascinating to click through how MusicLM generates specific instrument and genre sounds. The electric guitar is on point, as is “British Indie Rock,” complete with a dramatic turn at the end of the preview.
There’s more to explore from this limited preview of MusicLM, too, from “Accordion Solos” to comparing different results from the same prompt. Google also published a 15 page research article If you’re interested in reading more technical details about the system, visit MusicLM. We hope the company will open up a beta for you to try it out, but browsing through these samples is the next best thing.
[[[[V.Erghe]