PG Music Home Forums General Discussion Off-Topic Suno - AI Music Generator

Uh... yeah... I have ACE Studio. It doesn't pronounce the English language very well. Perhaps if I worked on a track for two years...

Don't get me wrong, I like it for demos but IMO, it's just not very good yet.

The reading and checking is important, though, as AI sometimes gets things badly wrong.

I have to say this is the single reason I very seldom come here anymore.
It's been almost 2 months since my last comment.
And that was a question.
Mike H and Herb were kind enough to help me with answers from experience.
The last word is what I personally feel is important in taking advice from anyone.
Experience.

AI song generation is like anything.
I don't feel it's great on its own, but it's powerful in the hands of an artist.
Someone who takes the time to truly learn it as a skill.
Most of the opinions I've seen here are typically (to be clear, not always) from people who have very little experience with actually making songs using these technologies.
Damn, do they have strong opinions on it though.

You can keep arguing your opinions, but guess what?
They have virtually no impact on the outcome.
NONE of us really has much say in this that will change anything.
To me, it's wasted time taking you from actually doing something musically that CAN impact someone.
Your music!
Even if it's just for your own enjoyment.
And if you are able to move someone else emotionally by it, hey that's a bonus.
But arguing opinions is so much easier than actually making music.
People who can’t write a lick of music could come here and argue their opinions.

The things that are important to many musicians, many times, the listener doesn't know or even want to know.
They. Don't. Care.
In their world, they like the song or they don't.
They couldn't tell you if the thing filling the track out is a 12-string Martin or a marimba.
The best you will maybe get is "See, now that sounds gooood."
And I would take that over some in-depth explanation of how different BIAB is vs. a virtual instrument using MIDI vs. Udio pumping something out, any day.

So as far as my own results with AI, I think I've done decent with it.
My tests are simple.
Do I like how it turned out?
If yes, great.
If not, back to the skill board and learn from it.
It's sort of the same mentality as learning an instrument, mixing (which I still suck at), basically anything that is a skill.
That's life.

Debating and arguing is also a skill.
Yet, I have far from mastered that.
You may be in the same boat as me though if this is still going on like this.
In the two months I've mostly been gone, the same old rehashed opinions are still trying to be "proven."

I don't want to say where to spend your time, but many of you are so damn talented, it's a little disheartening to see you spending your time on things like this instead.
I hear and feel your songs.
I just wish there were more of them.

I hope none of this comes across as preachy.
That is NOT my intent by a long shot.
I just feel some of you are being called from your greatness for lesser things.

Chad, it's always good to see a post you've made in the forum. You always offer great insights and focus on music. Mike Halloran and Herb Hartley did such a good job answering your question about "bass shaker" amplifier there wasn't much to add to their responses.

I agree with you the forum atmosphere has changed. Perhaps the forum is more of a reflection of the society we live in than it was in times past. I don't know but I recognize there is a change. This ain't the friendliest forum on the internet any more.

Take care.

AI lies as well. I've had it do multiple choice questions on chapters of books the kids are supposed to read and it's not averse to making up stuff. One AI instructional course I did suggested to not ask more than 10 multiple choice questions at a time of AI as the quality drops. Having said that I just got one sight to give me simple sentences in the present tense using various verbs with translations into Cantonese and it churned out 150 in seconds. One website will look at your lesson plan activities (eg from AI) and critique it for positive and negative possible outcomes so that you can think more about the lesson plan or activities if necessary or not use it. Amazing stuff. I just use Suno to write a song to my wife for our wedding anniversary. Life saver!

One of the reasons I have been absent here. I've been working on music for several of the listings and in the agreement I signed, it says no posting online of anything that I submit to a project. Doing so risks my deal with the publisher. So....

I just signed a number of tracks to one of my publishers. When they sent out the 2025 first quarter music listings and cover sheet, there was a notification that if we hadn't already read and signed the new writer's agreement, that we would need to do that before submitting any new tracks.

There was a very specific and detailed section on the use of AI generated music and lyrics, saying do not use AI in any aspect of creating music. It actually went well beyond that however, by placing a prohibition on the use of the synth vocals in any submission.
Anyone who violates that section of the agreement is subject to being banned from the publisher and ALL of their music removed from the catalog.

It has to do with the copyright controversy or to say it more accurately, the lack of being able to legally copyright the music under the current US-LOC regulations regarding AI and copyright.

The comment in the body of the email advising everyone to be aware of the new section of the agreement essentially said if you are going to be a writer and composer of music, you should be able to write and compose without the aid of a machine....or else, why do it?

Makes sense to me.

Sounds familiar.

I'm using some AI tools but only for knocking out demos where the tools do save time and are worth the money.


Exactly!

I posted on this thread back in January. I have since spent a lot of time with Suno Ai. On Thursday May 29th my Album "My Friend Parky" will be available on 100+ streaming platforms (if you search your favorite site with my name - David Rabinow- you should be able to find it. It is about 40-50% Ai. I'm very proud of the work.
This is going to be long, Bear with me.

I have Parkinson's Disease and for the last year and a half I've been writing songs about Parkinson's. And the abum is definitely targeted at people with experiences with PD. As my diseased has progressed my skills have diminished fairly sharply. Since I'm a guitarist I'm am most concerned with how I play on a recording, but I just can't play the way I used to.

I stumbled onto Ai music while I was starting to record some of the songs. I created a voice clone on Ace Studio from my voice and then altered it to be something that doesn't make me cringe. My plan was to record my singing into Ace Studio and then edit in a very midi like format. Unfortunately Ace Studio seems to have a lot of difficulty with English and the results were awful.

Then I found Udio and Suno. They're pretty similar, but Suno allowed me to use my voice clone. My original plan was to create songs in Suno and then splitting the tracks in one of the many Ai stem splitters on the market and then recreate them in my home studio. But because of my limitations the results weren't very good.

I started using more and more of the Suno stems. In the end most of the drums are from Suno. Drums have always been a major obstacle for me. I've never been able to program or write drums so I have relied on BIAB for drums most of the time. EZ Drummer and Logic Session drummer have never worked for me. Suno's drums are MUCH better than BIAB with one huge exception. The sound quality of the cymbals is awful. But the drums are much better at fills and accents and breaks and al the stuff that you want your drummer to do.

Suno, and all the other Ai music is at an infant stage - actually probably more like a three year old - because it doesn't really do what you want it to do. Typically, I take my lyrics and input them into suno and uploaded an audio clip of me singing the first 30 seconds of the song. I add a bunch of prompts (which take a while to understand) fo Genre, BPM, Time signature, and descriptors for mood. In the lyrics I put in prompts for verse, bridge, chorus, etc. But also performance prompts, i.e., soft voice, harmony, rising intensity, pause, and such. Then I hit create and in about 30 seconds I have two versions of my song. In a few very rare cases, I've gotten what I wanted the first time. Suno doesn't take direction very well. And sometimes I have to run thirty or forty versions before I get what I want.

But here's the cool part. Sometimes Suno's ideas of how my song should sound is better than my own ideas and opened up new directions. After a couple of weeks I started to think of Suno as being like the guys in my band from a previous lifetime. And then eventually I started to think of Suno as a collaborator.

In the end I was able to cull 11 songs and make the album. A critical listen will expose all the flaws in Ai music. But you won't hear them in a casual listen. When the prompts and lyrics overcome the Suno engine it spits out little artificacts. I have done my best to erase them with Melodyne, but the artifacts are often imbedded in the actual note. I'm pretty sure Izotope Spectral Editor could do the job but that's out of my price range. But for me a lot of the artifacts are there.

As to the ethics of using an engine that is trained on using samples from artists without attribution or renumeration, I have to say that as a blues guitarist I was very good at regurgitating what I learned listening to B. B. King, T-Bone Walker, Buddy guy, Mike Bloomfield and dozens of others. In some circumstances that only appears as influence while at other times I WANT to sound like B. B. King. And, Suno claims to have hired and or payed musicians to train their engine.

As far as Ai being some kind of cheating, I have to disagree. We all use tools to make music. But what if, like me, you don't have the skills to play music, but you have something to say and you want to say it musically. In the early days there will be a lot of awful Ai music and some of it will be on the top of the charts. Eventually I believe that the true talent will rise to the top.

It seems possible to me that the next George Gershwyn or John Lennon could be someone who is disabled in some way but now has the ability to express their genius talent they were born with. I don't love B B King because of his technical skills (although if you look on youtube yo can find some examples of him really shredding), I love him for they way he expresses himself.

And finally, a lot of us are using Ai tools in our music workflow. I use many Izotope products, almost all of them use Ai within their features. I've been using EZMix for years and the latest version uses Ai expensively. Ai is here and it's not going away. You can ignore it for now but eventually you'll have to embrace it. I hope that PG Music is looking at how they can integrate Ai in BIAB. There may be a perfect song creation program that's half BIAB anf half Suno. Who Knows?

Thanks for reading