AI-generated blues misses a human touch — and a metronome

AI-generated blues misses a human touch — and a metronome

Suno will happily sing you a tune. | Image: The Verge / Shutterstock

I heard a new song last weekend called “Soul Of The Machine.” It’s a simple, old-timey number in E minor with a standard blues chord progression (musicians in the know would call it a 1-4-5 progression). In it, a voice sings about being a trapped soul with a heart that once beat but is now cold and weak.

“Soul Of The Machine” is not a real song at all. Or is it? It’s getting harder to say. Whatever it is, it’s the creation of Suno, an AI tool from a startup of the same name focused on music generation. Rolling Stone said this song’s prompt was “solo acoustic Mississippi Delta blues about a sad AI.” And you know what? I doubt I’d glance askance at it if I heard it in a mix of human-recorded Delta blues tunes. The track is technically impressive, fairly convincing, and not all that good.

I spent 10 years or so as a semiprofessional or professional musician, onstage at least four nights a week. For some of that time, I played in a genre called Western Swing. Bob Wills is the most famous example of the style, but some very smart people have argued that more of his credit should go to Milton Brown, who drew more directly from early blues and swing acts like The Hokum Boys (which featured Big Bill Broonzy) or Bessie Smith. I preferred to play more like Milton Brown.

I’ve played the basic chord progression from “Soul Of The Machine” — and variations of it —countless times. So, when I say that the chords meander in nonsensical ways, it’s because I’ve also wandered in this style. Playing with the rhythm and structure is supposed to build tension and release it, and this song doesn’t do that. For contrast, notice the difference in the way Mississippi John Hurt smartly plays with the rhythm in “It Ain’t Nobody’s Business,” using tricks like dragging out pauses or singing sections on a different beat than you’d expect.

But when I tried to play my guitar along with “Soul Of The Machine,” I couldn’t stay on tempo. The song just steadily winds down, like a steam engine creeping to a stop. Bad tempo or weird chord changes aren’t wrong or bad on their own — nothing is definitively wrong or bad in music — but people who struggle with rhythm don’t just slow down like that. Instead, their tempo rises and falls. And when they make weird chord choices, it’s because they like how it sounds. AI doesn’t have such motivations.

Suno’s model might eventually make music that doesn’t have the quirky artifacts — like the dragging tempo or weird chord changes — that draw attention to its algorithmic core. But not making mistakes is only part of what it needs to do to compete with human music.

As a musician, performing for a live audience was necessary for making money and becoming a known quantity. But we also needed to be good. Doing it well means reacting during a show, lingering on part of a song when the crowd loves it, or switching the setlist up on the fly. When we were at our best, we formed something like a symbiosis with our audience for a few fleeting moments or sometimes for a whole set. The best performers can make that happen almost at will. (I was not one of those performers.)

It’s hard to imagine Suno or anything like it ever being able to pull that off. So I don’t expect it to be a straight-up replacement for live music, which is one of the most important parts of the medium, anytime soon. But that’s only one part of the package, right? Before we get to a robotic band drawing people to a dance floor or making folks cry in an auditorium, AI needs to transcend the parlor trick of imitation and start demonstrating an understanding of what moves people.

Suno co-founder Mikey Shulman told Rolling Stone that the relationship with listeners and music makers is currently “so lopsided” but that Suno can fix that. He said Suno’s goal isn’t to replace musicians but “to get a billion people much more engaged with music than they are now.” The company’s founders “imagine a world of wildly democratized music making.” That’s an idea that people often float for AI art as well. It sounds like a friendly, lofty goal, and I get the appeal — it’s not all that different from what made Neo learning Kung Fu through a neck plug in The Matrix such an attractive idea. No, Suno won’t instantly teach someone how to make music, but if you want to make a blues song and you’ve never picked up a guitar, “Soul Of The Machine” could make that feel almost within reach.

But I always get stuck on that word: democratized. Rolling Stone was paraphrasing Suno in that instance, but plenty of AI art proponents have used the word “democratizing” while extolling the benefits of creating text or art through an algorithmic proxy, and it carries this unsettling implication that, somehow, creative people are gatekeeping the creative process.

Even if that were true, it’s not very clear that Suno could help with that. It’s questionable whether tools like it are anywhere close to making the leap, on their own, from digital facsimile to human-style creativity.

Image created with ChatGPT by Wes Davis / The Verge

AI image generators have the same problems with details, like the image above, where I tried to get ChatGPT to give me something like Mike Mignola’s Hellboy. As a teenager, I would pull Mignola’s comic pages as close as my eyes would let me so I could soak up the details. Here, the details make it worse, not better. My enjoyment crumbles when I see quirks like a missing foot or a jacket morphing into the fake Hellboy’s arms.

I’m sympathetic to the desire to use AI to make up for any shortcomings I have as an artist, but every time I hear talk about democratizing creativity, I can’t help but picture someone arguing with one of these gatekeepers when they could just walk around them by simply doing creative things.

That’s not to say you won’t find people trying to gatekeep art, but I’ve found there are more artists offering help and encouragement than demanding my bona fides before I can join their ranks. You could sum up many artists’ attitudes with this quote from songwriter Dan Reeder: “You can make a mess of the simplest song, and no one will laugh at you. And if they do, they can blow me, too, ‘cause no one should laugh at you.”

“And then it can take two months to have 15 images produced.”

None of this is to say AI needs to replace creativity outright to be useful. I wouldn’t argue if you told me you thought Dustin Ballard’s “There I Ruined It” AI voice parody songs — which work because of his impressive singing ability and musical understanding — are art. And as The Verge’s Becca Farsace showed in a December video, Boris Eldagsen spends months on AI-generated artwork that shows how his “promptography” can create thought-provoking work.

In both cases, AI isn’t used as a shortcut to creativity. Instead, it enhances the ideas they already had and may even inspire new ones. If anything, they reinforce the idea that if you want to create something, there’s only one way: just be creative.