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.
Comments
Yeah but unfortunately I'm a hobbyist. I can't pay for vocalists.
Or, used to hate AI… lol..
This seems more the “machine learning” type AI than it does some kind of general intelligence, LLM, or anything like that.
FWIW, LLM’s are of the machine learning ilk. They are not general intelligence software though it looks like that because of what happens when you apply machine learning on that scale with language. (It is also why in certain ways they get worse in certain regards as their own output becomes a a significant part of the corpus if trains on).
I love classical machine learning and deep learning for regression and classification, even general adversarial networks for generative AI to an extent, used as a tool rather than a means to an end, that end being "okay, generate a full song with all the instruments and vocals being generated by the GAN".
Disappointing from both the cost side and the cpu issues. The part of this that is said to run on GPU must be really needing a revision, if it hits the CPU so hard. Stuff that runs on GPU doesn’t even show on CPU meters
General AI doesn’t exist. LLMs are machine learning, it’s just the huge amount of data that makes it seem clever and accounts for the “long” part of LLM.
But that’s it, no intelligence, general or specific, although the guys wanting to get filthy rich quick need the bubble to keep growing, so they all keep promising AGI is just around the corner, but we’re probably never gonna see it in our lifetimes
I guess my point is, if they called themselves MicDrop ML instead of MicDrop AI people wouldn’t have the “AI is in the title so it’s evil” reaction. MicDrop ML is catchier too, imo.
I felt the same, tested it on desktop, and sadly, I have to report it won't fix poor singing. It sounded just as bad, but with a different voice.
🤣 I don’t know why this cracked me up.
Because this program only changes the timbre of your voice. It doesn't make your performance perfect. It completely captures your microdynamics, the dynamics of your performance, modulations, the duration of sung notes, imperfectly hit notes, and other nuances. I tried it too, but I didn't like hearing myself sing in someone else's voice. It was a very strange feeling. 😂. Even though I can sing, it sounded good overall. This program probably won't help someone who can't sing, and someone who can probably won't need it. But that's just my opinion, and it could be wrong. However, I did buy several instrument models separately. And I think that with tools the use of this application can be more effective.
All this fuss over fixing vocals. A good mute button is all I've ever needed for perfect results for my singing.
The rewards are great for those willing to invest the time to learn how to use this miracle tool rather than lazily expecting AI to do it for them.
Most likely, each voice or instrument model in this program will require an individual approach from the performer. Different instruments require different vocal techniques and styles. It's like learning to sing all over again.
This really is unusable with an M2 iPad. I was hoping maybe I could get something fun out of it but yeah it’s a no go.
I have an a16… is that weaker than an M1 or m2? Not really that knowledgeable about that kind of thing
I’m pretty sure any M-series is more powerful than the previous chips. This thing really was designed with an M5 in mind. It kept crashing on me, if it did load it crackled the entire time it wasn’t crashing, and any recorded audio wouldn’t play back.
I finally requested a refund 🤷🏽♂️
You would likely have to run this CPU hungry app as a solo instance that records the audio produced into loops for use in more traditional DAW workflows. I have an M1 iPad Pro and one instance uses above 50% DSP in AUM
With my usual settings. I increased the number of samples in AUM to 1024 and was able to use 2 instances in a complex AUM rig with synths that are needed to avoid actual Mic input (i.e. for singing input).
This is what I would like to know as well. Anyone know?
It processes your voice as the instrument
Ok thanks Mike. Locked into the system. Wonder when Midi Guitar 3 comes out?
I was about to post it too. Jakobs videos always put a fresh angle on things. I hadn't even considered trying this but now I am.
He states in the video that you need a host that can do multi processing so that might be why so many have problems with using it in AUM(?). Running it in Cubasis on a M1 iPad Pro is going so so.
@Cambler : What’s “MIDI Guitar 3”?
https://jam.live/products/MG3/
Thanks @Cambler
Good to know…that eliminates GarageBand!
I use it in AUM and drop the AUM sample rate settings to get more DSP headroom with this very hungry app. I also have played with buffer size and minimal latency settings.
I got 3 instances of MicDrop to run with Battalion, Pop Drummer, Outgrowth and some FX apps for reverb and panning on an M1 iPad Pro.
Another arroach would be to just load an instance and make recordings that can be loaded into a DAW similar to freezing Tracks on Cubasis on my 2016 iPad.
MicDrop can be driven by audio input (voice for example... Like you singing), or a synth input in AUM or by MIDI notes. I have only tried synth inputs so far. I can't start singing while my wife is watching TV but I'm eager to hook up a good mic and see what it sounds like... I bought all the vocalists so making a complete SATB choir will be fun. You can raise or drop by octaves so I'll have more vocal range than Maria Carey. This is the upside of AI's machine learning tech. The chips are fast enough to pull it off.
Do you have to buy voices or are there any available in the free version?