Loopy Pro: Create music, your way.
What is Loopy Pro? — Loopy Pro is a powerful, flexible, and intuitive live looper, sampler, clip launcher and DAW for iPhone and iPad. At its core, it allows you to record and layer sounds in real-time to create complex musical arrangements. But it doesn’t stop there—Loopy Pro offers advanced tools to customize your workflow, build dynamic performance setups, and create a seamless connection between instruments, effects, and external gear.
Use it for live looping, sequencing, arranging, mixing, and much more. Whether you're a live performer, a producer, or just experimenting with sound, Loopy Pro helps you take control of your creative process.
Download on the App StoreLoopy Pro is your all-in-one musical toolkit. Try it for free today.
Riffusion.com : Seems like I’m not the only one who had the whole text to audio AI idea thing… :)
update
Seems like I misunderstood his method. This isn’t text to speech audio. It’s text to the whole darn thing audio!
As in, his text prompts create the whole piece, or rather, pieces, which he then curates and assembles. That is: the free to use AI https://www.riffusion.com/ , takes the initial text prompt to create not just the vocal but the whole mix of instrumentation behind it too, out of the whole cloth of an AI imagined picture of the spectrogram of the music which never existed, reverse engineered into the real world from that picture.
Operating under the name ‘patten’ ( or ‘pattten’, he seems to use both), this av artist and lecturer at the London College of Communication has just released an album making extensive use of Riffusion to create a kind of post trip hop glitch. Twisting the imitate into New Forms, indeed. It’s fascinating stuff:
https://tidal.com/album/282288407
He’s leaning into AI generated video too:
Comments
This is the free, browser based tool he used:
https://www.riffusion.com/
I’ve had a go with it myself now. It’s fascinating. It creates sound from ‘hallucinating’ the spectrograms of the imaginary sounds you ask for, then turns the pictures of the spectrograms back into sound. So you are basically ‘sampling’ glitchy little riffs from music that never existed before, based on the seed you set and the text prompt you give it.. If nothing else, it seems like one way to get round the copyright problem besetting other AI musical approaches.
It’s clear from my own ten minutes dabbling with it that it has been more trained on mainstream pop and EDM rather than dark ambient (!) and it has a long way to go at the moment, like those first public iterations of Dall-e and Midjourney, but, just like the art AIs, repeated iterations can get closer and closer to a thing. And we all know how fast they evolved.
As patten has shown above, this iterative, curatorial, collaborative approach is an interesting way forward for artists to actively collaborate with AI, rather than have it just churn out ersatz not-very-good pop on its own
At the moment, if you like weird glitch, I’d say check it out, grab some clips, and see what you can do with them. I know what I’m doing this morning…
yes! theres another thread on the forum about riffusion. i cant wait for when AI music becomes as powerful as midjourney
Wow… You’re SO right about how quickly things progress. Is there a way to get the audio clips? I can feed the iPad audio out into a DA interface and grab it that way, but at short glance, I can’t see a “button” for saving what you’ve created.
There’s an on screen button which generates a shareable link, but I’m just screen capping it, and opening the vid into Koala.
I find listening to it noodle its way toward the prompt I gave it when the server is under strain fascinating. Like having another player in the room experimentally picking out notes and phrases, the act of creation in process.
Just wait until they cut out the human BIOS and go straight for harvesting thought patterns, that should really tax the servers, though for food you could say.
I‘d love to know, what William Burroughs would have made of this whole AI thing (damn you death) having experimented with computers as collaborators as early as the 60s, I think. This whole machine learning thing seems to me like an Über-cutup gone out of control cutting up itself again and again. Any Burroughs fans around?
At your service, @tyslothrop1
He was one of my earliest heroes, as I graduated from Vonnegut and Bradbury to … the darker meat. Wild Boys was my (horny, illicit) entry drug as a young gay teenager, and then I was all in from the relatively straight but sordid Junky to the Naked Lunch, The Ticket That Exploded, and all the rest of it. Came to love his dry as dust audio outings too. His own telling of The Junky’s Christmas on Spare Ass Annie for example became part of my own seasonal ritual, a necessary corrective to schmaltz which nevertheless manages to smuggle in some humanity too. And I love his reading of Star Me Kitten:
Not a very nice man, as his wife would have testified to if he hadn’t killed her and used the Burroughs fortune (later known as IBM) to avoid responsibility for the death, but one hell of a writer. He and Lovecraft both share that ‘judge the work, not the life’ quality.
Edit: wow cool, I can just remove stupid things I wrote, that felt smart at the time.
Same here