[HN Gopher] Suno Studio, a Generative AI DAW
       ___________________________________________________________________
        
       Suno Studio, a Generative AI DAW
        
       Author : debrisapron
       Score  : 65 points
       Date   : 2025-09-26 17:17 UTC (5 hours ago)
        
 (HTM) web link (suno.com)
 (TXT) w3m dump (suno.com)
        
       | thesparks wrote:
       | v5 is really good. I can't believe how much progress Suno has
       | made in such a short time.
        
         | Jordan-117 wrote:
         | I don't understand why their vocals are still so bad, though.
         | They always have this tinny, synthy vibe that's very
         | noticeable.
        
           | jjangkke wrote:
           | it doesn't interfere with my enjoyment of Suno 5's output and
           | enough for me to pay for it now.
           | 
           | Suno 6 should solve those issues.
        
       | recursive wrote:
       | I'm really curious how the traditional DAW features stack up
       | against the incumbents. A good DAW has a ton of features.
       | Developing a whole DAW from scratch just to add a "generate part"
       | button sounds like a lot.
        
         | lomase wrote:
         | The people using Sunno AI don't care about writing or mixing
         | music.
         | 
         | They don't need the same feature list.
        
           | recursive wrote:
           | The video seems to be trying to convince me that this is
           | totally targeted at actual musicians. But I guess maybe
           | that's how their target users imagine themselves?
        
             | themotherhucker wrote:
             | As an actual musician who doesn't have any troubles
             | creating my own melodies and timbres (both generated and
             | 'manually' created), its very obviously not targeted at
             | someone like me.
             | 
             | It seems similar to a Garage Band type of software, aiming
             | to entice people with little audio production experience
             | and give them an interesting sounding snippet they can play
             | back to friends.
             | 
             | For example, the only actual audio editing they displayed
             | was slicing and re-pitching (you can't even choose the
             | time-stretch algorithm), which is conceptually very simple
             | to understand.
             | 
             | There's no ability to actually edit dynamics or do very
             | accurate frequency adjustments that I can see from the
             | demos, so it's basically useless for anything I would want
             | to do.
        
             | lomase wrote:
             | As much as I think making AI music is the pinacle of
             | lazynes and instant gratification, in my opinion they are
             | actual musicians.
             | 
             | What I mean is that in a DAW you have a lots of tools that
             | don't make sense in AI context.
             | 
             | Like for example, people who use agentic workflows don't
             | need a Visual Studio license.
        
               | recursive wrote:
               | Well, music is art. Some of it is done for hire or
               | commission. Most code is written for an employer or
               | contract. Code written as art is an edge case.
               | 
               | For advertising jingles it makes some sense. For artistic
               | expression, like... what's the point?
        
               | lomase wrote:
               | If the act of creating this AI music provides joy to
               | them... I think they are artist
               | 
               | I used to release music that people listend to, but not
               | anymore, now the only joy comes from making it for
               | myself. Am I still an artist?
        
               | recursive wrote:
               | In my book, you are definitely an artist. Perhaps the
               | purest kind, not that it's a competition.
               | 
               | If the act of creating this AI music provides joy to
               | some, they should do it. I just have a hard time
               | understanding that.
        
         | input_sh wrote:
         | I can tell you exactly how any professional is gonna evaluate
         | this DAW: press Ctrl+F, type "VST", see 0 results, close the
         | page.
        
           | meowface wrote:
           | If they do add VST support I could see them becoming a
           | legitimate player. Without it it's definitely just a toy.
        
             | input_sh wrote:
             | They're never gonna let you upload and run your own
             | executable files to their infrastructure.
             | 
             | That + latency with MIDI devices is why every DAW-in-a-
             | browser is just a toy.
        
               | polishdude20 wrote:
               | You can get a vst to run locally and still work with the
               | browser.
        
               | input_sh wrote:
               | Okay, but why would you? What's the advantage of that?
               | VSTs are resource hogs (when you have like 10+ running at
               | once), not DAWs.
               | 
               | I somehow doubt a full-blown browser connected to more
               | than a couple of VSTs would be less of a resource hog
               | than doing the same in a DAW. On your computer. That you
               | own. In your house. Without like additional 50ms of
               | latency for the data to travel to the server and back.
        
               | recursive wrote:
               | I just assumed all the audio data would be local even in
               | a "browser DAW", so VST calls wouldn't go through a
               | network.
        
               | recursive wrote:
               | Didn't realize this was in a browser. That tells me all I
               | need to know.
        
               | lioeters wrote:
               | Coming soon: Suno Desktop (Electron version). "Look ma,
               | no browser!"
        
       | 80hd wrote:
       | I wasn't expecting to, but I got chills listening to some Suno
       | creations from artists who are clearly very talented at using
       | this new medium.
       | 
       | Much like those of us hammering away at LLMs who eventually get
       | incredible results through persistence, people are doing the same
       | with these other AI tools, creating in an entirely new way.
       | 
       | I'm sure Suno are working hard on this and these AI tools can
       | only come together as fast as we can figure out the UX for all
       | this stuff, but I'm holding out for when I can guide the music
       | with specific melodies using voice or midi.
       | 
       | For "conventional" musicians, we (or at least I) would love to
       | have that level of control. Often we know exactly what it should
       | sound like, but might not have session musicians or expensive
       | VSTs (or patience) on hand to get exactly the sound we want.
       | Currently we make do with what we have - but this tech could
       | allow many to take their existing productions to the next level.
        
         | patapong wrote:
         | That sounds really interesting. Would you mind sharing some
         | examples of such creations?
        
           | lomase wrote:
           | They will not.
        
             | meowface wrote:
             | They probably won't. And if they do probably everyone will
             | ridicule the songs. But maybe they will link the songs and
             | maybe at least half the repliers will say the songs
             | actually are good. I like rooting for the underdog.
        
               | lomase wrote:
               | Suno with its $125 million VC funding is everything but
               | an underdog my friend.
        
               | meowface wrote:
               | By underdog I meant the above HN commenter wanting to
               | prove to us that the AI-created songs he likes are
               | actually considered good by others.
        
               | lomase wrote:
               | I actually have listen to all the links people posted.
               | They are not that bad.
               | 
               | But when they say it can replace Pop music I can only
               | laugh. It is the most boring early 2000 RnB ever created
               | and it souns thin.
               | 
               | Any Aphex Twin model out there?
        
           | bogtap82 wrote:
           | I'm not the person you responded to, but these are some
           | examples from someone I know that had accompanying music
           | videos (actual video production) made for them:
           | 
           | Sunscreen: https://youtu.be/VBaWtOHPTZw
           | 
           | Purple Sunset Over Lake 2: https://youtu.be/lD7rSxPncs4
        
             | nadermx wrote:
             | These are terrible
        
               | bogtap82 wrote:
               | Thanks, I'll let them know.
        
           | architectonic wrote:
           | I enjoy this AI generated album https://open.spotify.com/albu
           | m/6C6PJzxkHctvk1ibKM2zMx?si=YgL...
        
           | pants2 wrote:
           | I'll share something! I really enjoy this artist @kant, it's
           | rap which isn't everyone's cup of tea but here's one of his
           | more approachable songs.
           | 
           | https://suno.com/song/07ab552c-1a76-43f4-a619-21a74e774dbd
        
           | cdrini wrote:
           | Not OP, but on the off chance you haven't seen this, I found
           | the suno explorer thing quite nice. Hitting random a few
           | times, I'll usually stumble onto something interesting. This
           | was the first demo I heard where some of the AI tunes gave me
           | goosebumps close to what human music does.
           | 
           | https://suno.com/explore/
        
       | nibblenum wrote:
       | i wonder what https://www.renoise.com/ would be like like this
        
         | pacifika wrote:
         | Well it has lua scripting so it just needs someone determined
        
       | chrisvenum wrote:
       | While I like using AI for assisting with repetitive programming,
       | I can't help but feel sorry for my producer and illustrator
       | friends who are now having to compete with generated tools.
       | 
       | Is it snobby of me to look down upon art that is created using
       | these tools as lesser because the human did not make every tiny
       | decision going into a peice? That a persons taste and talent is
       | no longer fully used to produce something and for someone reason
       | to me what is what makes the art impressive and meaningful?
       | 
       | Something about art with imperfections still feels exciting,
       | maybe even more so than if I see something that is perfect but if
       | I see an AI gen picture with 6 fingers, I just write it all off
       | as slop.
       | 
       | I am happy to allow my generated code to come from "training
       | data" but I see the use of AI in art, writing and music as using
       | stolen artists hard work.
       | 
       | I feel like as time goes on, I feel even more conflicted about it
       | all.
        
         | nh23423fefe wrote:
         | You as a human chose to write this very common opinion and even
         | include writing errors like the following
         | 
         | > That a persons taste and talent is no longer fully used to
         | produce something and for _someone reason to me what is what_
         | makes the art impressive and meaningful?
         | 
         | Human output isn't sacred. yes this is snobbery, a useless
         | feeling of superiority.
        
         | jjangkke wrote:
         | Applying your logic, did you feel bad for seamstresses when
         | industrial revolution took off? did you feel bad for hardware
         | manufacturers in America when they were outsourced to China?
         | Art is also a form of labor and whoever can produce quality at
         | quantity wins. Idealizing art in some sort of religious
         | idolation is just plain silly. We haven't had the Picassos or
         | Mozarts or Oscar Peterson for quite some time now yet the world
         | is just fine. People play playlists in front of millions of
         | live crowd and get accolade for it vs real instruments. Times
         | change, technology change and art changes.
         | 
         | You either adapt or go hungry just like everybody else and art
         | shouldn't be exempt from the mechanics of supply and demand.
        
           | a456463 wrote:
           | I hear this but this is not the industrial revolution buddy.
        
           | chrisvenum wrote:
           | I almost agree with you that this is about quality, but I
           | still feel that the context in which art comes from
           | influences how I perceive it.
           | 
           | Take, for example, a track by Fontaines D.C., a band from
           | Ireland that writes extensively about the lived social and
           | political experience. Knowing where they are from and the
           | general themes of their work makes their tracks feel
           | authentic, and you can appreciate the worldview they have and
           | the time spent producing the art, even if it does not align
           | with your own tastes.
           | 
           | Trying to create something of the same themes and quality
           | from a prompt of "make me an Irish pop rock track about
           | growing up in the country" suddenly misses any authenticity.
           | 
           | Maybe this is what I am trying to get at, but like I said, I
           | feel some conflict about this, as I personally value these
           | tools for productivity
        
             | chrisvenum wrote:
             | Saying that, maybe a DAW experience makes what can be
             | created more personal
        
         | raincole wrote:
         | > Is it snobby of me
         | 
         | Yes. But aesthetic taste and snobbery usually go hand in hand.
        
         | acureau wrote:
         | I feel the same, including code. I cannot justify it. I can
         | easily counter my own arguments. Still, the further we automate
         | human thought and creativity the worse it makes me feel. I am
         | disappointed that so many are content with mediocre imitation.
        
       | jjangkke wrote:
       | What's special about Suno 5 is that the songs are actually good
       | to listen to in place of professionally produced songs. For
       | example, my favorite genre is new jack swing and there is a very
       | limited number of this genre as it was briefly popular during the
       | 90s. Now I have an endless supply of it and you can't tell that
       | its AI produced anymore. Sure to an expert they might be able to
       | detect it but for consumers its just as good as spotify playlist.
       | 
       | This is the first time I'm actually paying for generated AI
       | content because the value I get is immense. I really think we are
       | headed towards and over supply of content where there will be
       | more stuff to read, watch, listen with very real value in all of
       | them.
       | 
       | This spells out the inevitable change in the labor market for
       | content creators. There will always be value for human created
       | content and some will make more money but it will always have the
       | AI generated content generation competing with it to the point
       | where it will be hard to stay ahead and eventually people will
       | stop caring.
       | 
       | Case in point, I see some comments being snarkish towards Suno
       | but for as a consumer I could care less if you put your soul and
       | years into producing art vs the one I can get a lot of today and
       | now especially when there is virtually no difference in quality.
       | 
       | Truly an amazing accomplishment from Suno team, and probably the
       | first time I've subbed to a music service after decades of
       | downloading mp3s, hunting down new songs to listen to on Youtube.
       | Suno 'steamified" this process and while I will use youtube to
       | discover new genre, I am spending now most of my time in Suno,
       | listening to endless amount of the exact sound I am looking for.
        
         | lomase wrote:
         | What's special about Suno 5 is that the songs are actually good
         | to listen to in place of professionally produced songs.
         | 
         | This is a big big lie.
        
           | neom wrote:
           | Rather than call it a lie, I think it would be more fair to
           | say in this instance it's a matter of taste/perspective.
           | Personally, I enjoy listening to Suno songs.
        
             | lomase wrote:
             | Personally I enjoy listening and smelling my own farts.
        
         | tummler wrote:
         | What a dystopian and depressing outlook on the valuation and
         | enjoyment of art. Truly hope you're an anomaly.
        
           | a456463 wrote:
           | Couldn't agree more. Instead of seeking out people making
           | that art, we are now leaving "art" or human expressive
           | emotion to random noise and paying for it.
        
           | meowface wrote:
           | I simultaneously feel repulsed by AI music and "art" and yet
           | am totally open to being captivated by AI music if I really
           | feel something is musically better than almost any human-made
           | music I've heard.
           | 
           | I just haven't heard anything that isn't "slopful" yet. If I
           | do, I will still feel weird about it, but I'm a big believer
           | in the value of "aesthetic objects in themselves", so I am
           | eager to find something I do actually like.
           | 
           | Even just knowing something was drawn or composed by an AI
           | will negatively taint my opinion from the start, but I'm
           | still open.
        
             | lomase wrote:
             | I do love generative music. I don't care if you get your
             | notes from a markov chain a shif register a LLM or your
             | brain.
             | 
             | The problem with AI music is that is just sounds like shit.
        
               | meowface wrote:
               | Right. That's pretty much my stance.
               | 
               | I don't totally discount the position that the human
               | "soul" is what makes art art and all that, but I still do
               | think something can be very enjoyable and good without
               | being created by a sentient entity, in theory.
        
         | smt88 wrote:
         | I've had some fun with Suno 5, but the songs absolutely don't
         | replace well-made human music. They're much more formulaic and
         | over-produced. They're usually forgettable. People I play them
         | for can always tell they're AI produced.
        
           | zubzubi wrote:
           | I find it depends how you generate it. Asking Suno to make
           | covers of uploaded recordings tends to give much, much better
           | results than asking it to cook a song from scratch. There are
           | still quite a few tells that it's AI-made but it's not bad at
           | all, at least in my experience so far.
        
           | XenophileJKO wrote:
           | Currently for me, in the type of music I have enjoyed from
           | v4.5+. V5 of their model is a regression.
           | 
           | I was very impressed with v4.5+ that I could get quite good
           | songs evocative of Devo, Yeah Yeah Yeah's, Metric, etc.
           | 
           | Version 5 is currently harder (or I haven't figured out a
           | way) to generate this kind of chopped/produced sound. It
           | doesn't follow complex style definitions and tends to
           | generate songs that are too slow and "smoothed" over.
        
         | tbeseda wrote:
         | > as a consumer I could care less if you put your soul and
         | years into producing art vs the one I can get a lot of today
         | 
         | a quantity over quality argument with regard to art is wild.
        
           | wilg wrote:
           | people just start liking things if there is a lot of it
        
         | CollinEMac wrote:
         | > I really think we are headed towards and over supply of
         | content where there will be more stuff to read, watch, listen
         | with very real value in all of them.
         | 
         | We're already here with human created content.
        
         | pandaxtc wrote:
         | > as a consumer I could care less if you put your soul and
         | years into producing art vs the one I can get a lot of today
         | and now especially when there is virtually no difference in
         | quality
         | 
         | as a fellow consumer I care a lot actually
        
       | sandoze wrote:
       | Before AI there was a general consensus that creative areas (eg.
       | Cities) were becoming a homogenized experience. A Starbuckization
       | if you will. I can't help but wonder what gets lost when using
       | tools like this.
        
         | jckahn wrote:
         | Culture
        
         | cdrini wrote:
         | It's unclear to me whether it will result in more homogeneity,
         | as a result of prompts being a coarse medium that results in
         | the AI choosing what it's seen to fill in the rest, or less
         | homogeneity, as a result of more people with non-mainstream
         | tastes being able to create music aligned with their niche that
         | otherwise wouldn't exist due time/money restrictions. I think
         | the latter seems a bit more likely, but time will tell.
        
           | jsheard wrote:
           | There's not really any need to speculate when this has
           | already played out in other mediums - would you say that the
           | proliferation of LLMs has led to an explosion of novel and
           | interesting works of fiction, or just an explosion of cookie-
           | cutter slop ebooks?
        
             | cdrini wrote:
             | I would say too soon to tell. There has been an uptick in
             | ebook slop, but I'm not sure if it's impacted the
             | homogeneity of literature, because I don't think anyone is
             | reading ai ebooks. It's not enough for it to exist to
             | impact culture, it has to be being consumed.
             | 
             | Music is a uniquely interesting case, since music has a
             | much lower barrier of entry to consume.
        
               | sandoze wrote:
               | My thought to who you replied to exactly. Am I going to
               | invest several days to read an AI slop novel? No. But I
               | will take several minutes to read a blog post and likely
               | have read many that were AI generated or assisted.
        
       | tummler wrote:
       | Suno is moving toward becoming a browser-based DAW that happens
       | to use AI. There are already more capable and established DAWs,
       | and I see no reason they can't implement AI into their
       | workflows-- in a more precise manner, where it's actually useful,
       | instead of wholesale as a gimmick. Many are already doing this.
       | So I don't understand where Suno is going with any of this.
       | 
       | It either needs to be: 1. So easy anyone can press a button and
       | magically get exactly what they want with perfect accuracy and
       | quality. 2. So robust and powerful it enables new kinds of music
       | production and super-charges human producers.
       | 
       | This is neither. And I don't buy Suno's argument that they're
       | solving a real problem here. Creative people don't hate the
       | process of creating art-- it's the process itself and the
       | personal expression that make it worthwhile. And
       | listeners/consumers can tell the difference between art created
       | with intent and soul, and a pale imitation of that.
        
         | raincole wrote:
         | All you said is very reasonable.
         | 
         | But then you look at image gen. The established one, namely
         | Adobe, are surprisingly not winning the AI race.
         | 
         | Then you look at code gen. The established IDEs are doing even
         | worse.
         | 
         | I don't rule out the possibility of music being truly special,
         | but the idea of "established tools can just easily integrate AI
         | right" isn't universally true.
        
           | tummler wrote:
           | The innovator's dilemma is real. IMO none of the big DAWs are
           | well-positioned to capitalize on AI, but that doesn't mean
           | they couldn't.
           | 
           | I'd argue music generation is different from image or code
           | generation. It's closer to being purely art. Take image
           | generation for example. Most of the disruption is coming from
           | competition with graphic design, marketing,
           | creative/production processes, etc. The art world isn't up in
           | arms about AI "art" competing with human art.
        
             | leobuskin wrote:
             | It does mean. The switch from writing "applicable" software
             | to creating cutting edge AI is almost impossible. The
             | parent comment makes great examples, we can add to that
             | list JetBrains (amazing IDEs, zero ability to catch up with
             | ML), for example. It's a very different fast-paced
             | scientific driven domain.
        
           | danielvaughn wrote:
           | Agreed. The problem with being an incumbent in this era is
           | that much of the existing UI/UX assumptions are based on the
           | idea of manual manipulation. We're so early that foundational
           | assumptions are still up for debate, and for large companies
           | like Adobe, there's just no way they'd be able to move at the
           | required pace to keep up. Heck I'm at a company that's less
           | than 2 years old, with less than 20 people, solely devoted to
           | AI, and it's still hard for us to keep up.
           | 
           | What Adobe and others ought to be doing is setting up
           | internal labs that have free reign to explore whatever ideas
           | they want, with no barriers or formality. I doubt any of them
           | will do that.
        
         | jsheard wrote:
         | > It either needs to be: 1. So easy anyone can press a button
         | and magically get exactly what they want with perfect accuracy
         | and quality. 2. So robust and powerful it enables new kinds of
         | music production and super-charges human producers.
         | 
         | Don't forget the secret third option - facilitate a tidal wave
         | of empty-calorie content which saturates every avenue for
         | discovery and "wins" purely by drowning everything else out
         | through sheer volume. We're at the point where some genAI
         | companies are all but admitting that's their goal.
         | 
         | https://www.hollywoodreporter.com/business/digital/ai-podcas...
        
           | Gigachad wrote:
           | That seems to be the purpose. It doesn't have to sound that
           | good to the listener. It's just made to extract dollars from
           | Spotify when you flood the platform with so much slop that
           | some of it starts getting played by users who just let the
           | machine pick the next song.
        
         | zubzubi wrote:
         | Yes I'm already doing this manually with Reason. I'll compose
         | something that's quite bare bones, export the audio and run it
         | through Suno, asking it to cover and improvise with a specific
         | style, then when I have something I like, I split that into
         | stems, import some or all of these to Reason and then
         | reconstruct and enhance the sound using instruments in Reason,
         | mostly by replaying the parts I like on keyboard and tweaking
         | it in the piano roll. Often I get additional inspiration just
         | by doing that. Eventually I delete all the tracks that came
         | from Suno stems when I've finished this process.
         | 
         | That way I get new musical ideas from Suno but without any
         | trace of Suno in the final output. Suno's output, even with the
         | v5 model, is never quite what I want anyway so this way makes
         | most sense to me. Also it means there's no Suno audio
         | watermarking in the final product.
        
           | tummler wrote:
           | This is similar to what I do. There are all kinds of useful
           | ways to incorporate AI into the music production process. It
           | should be treated like a collaborative partner, or any other
           | tool/plugin.
           | 
           | It shouldn't be a magic button that does everything for you,
           | removing the human element. A human consciously making
           | decisions with intent, informed by life experience, to share
           | a particular perspective, is what makes art art.
        
       | wartywhoa23 wrote:
       | Degenerative art in full swing.
        
       | bitbuilder wrote:
       | As someone who's both a software engineer and music producer its
       | been really interesting to watch the parallel progression of the
       | AI advancements in both areas, as well as my own sentiments
       | towards those advancements.
       | 
       | I've always been pretty bullish about using LLMs to help with
       | coding. My comment history here should verify that. I just
       | thought it was insanley cool tech, and I found I was
       | rediscovering the joy of programming when I could delegate out
       | all the tedious crap I could never get myself to do. Side
       | projects that had languished for years were finally getting
       | somewhere near "done". I also found in many cases it was actually
       | smarter than me, finding cleaner and more elegant solutions to
       | problems than I ever would have. And that was great!
       | 
       | The first time I played with Suno though, it was all so
       | different. I felt deflated. What was the point in making music if
       | a robot could do it better? Yes, the first models were crap, but
       | the writing was on the wall. Music is all about pattern
       | recognition and repetition after all, why wouldn't the robots be
       | great at it? I suddenly knew how all those visual artists felt
       | once the image models started rapidly improving.
       | 
       | So it's been interesting try to disect why I thought coding
       | models were great, and creative models... well, depressing.
       | 
       | Part of it in my case was because being that guy who made cool
       | music was always part of my identity, a part of me I was proud
       | of. Coding, not so much. Don't get me wrong, I've had some pretty
       | big career achievements that I'm very proud of, and I love
       | coding. But at the end of day, the lines of code written were
       | just a means to an end to making something cool.
       | 
       | Which brings me to the other reason I think I was so much more
       | positive about LLMs: the application I was bringing to life with
       | the help of an LLM still very much felt like "mine". Yes, maybe
       | the tedium of writing a bunch of boilerplate was being delegated,
       | but the idea, the architecture, the UX, were still all mine. So I
       | was building something I could still feel proud of.
       | 
       | But typing a prompt into a box and getting a song back? Nah,
       | that's not really mine. It's no different than shouting an idea
       | to a musical improv musician and getting a song back. Maybe you
       | gave them a cool idea, but the song isn't yours.
       | 
       | Which brings me full circle back to this new Suno DAW
       | announcement: this is absolutely incredible. I've only skimmed
       | the announcement so far, but I feel like this brings AI song
       | generation firmly back into the court of how I'm using LLMs to
       | code: letting AI take care of the boring shit, and letting me
       | focus on the composition.
       | 
       | I've only really ever produced electronic music of various
       | varieties, and I have so many uncompleted songs whithering on the
       | vine because I wasted a week of time flipping endlessly through
       | patches, tweaking them, trying to find "that sound" in my head
       | that I could never bring to life, then eventually getting sick of
       | the song and saying fuck it.
       | 
       | And in my experiments with Suno, I found it was actually crazy
       | good at matching a "sound" I described, I just wished I had a way
       | to compose my own song based on the sounds it generated. And now
       | here it is.
        
         | BrokenCogs wrote:
         | It's human nature to want to feel like we've accomplished
         | something. AI generaters like Suno, where all you have to do is
         | type in a prompt and you get the final result, take that sense
         | of accomplishment away from us.
         | 
         | However, if we start working on a project where we're assisted
         | by AI, for example, we're making a game where the sprites are
         | generated by AI or the background music is generated by AI, but
         | the overall game is still directed by humans, that sense of
         | accomplishment stays.
         | 
         | But at some point we're going to reach the stage where the
         | entire game can be generated in high quality, at the same level
         | as humans. What then?
        
       | ewuhic wrote:
       | What is the current SOTA for open source or open weights music
       | generation model?
        
       | jononor wrote:
       | How is the stem support these days? In particular I would like to
       | create some songs with vocals (my lyrics), then be able to remove
       | the vocal track and replace it with my own.
        
         | lomase wrote:
         | I don't know if Suno does it, but it should be doable.
         | 
         | For voice removal I use Ultimate Vocal Track Remover, is on
         | Github.
        
       | jasongrishkoff wrote:
       | I've been working on an AI detector for the last few months.
       | Updated it to handle Suno V5 on Wednesday - looks like it's very
       | similar to V4.5. Am curious to see how this Studio version
       | impacts the model I've trained.
       | 
       | If you want to test it, here's the link:
       | https://www.submithub.com/ai-song-checker
        
         | BrokenCogs wrote:
         | If only I could use it before logging in.
        
           | jasongrishkoff wrote:
           | After login it's free. But my site has been targeted by a lot
           | of spam/abuse over the last decade, and login is something
           | I've needed to set up to avoid that :(
        
             | lomase wrote:
             | We just can't have nice things anymore.
        
       | mrandish wrote:
       | This is an excellent example of where AI-assisted pro music
       | production needs to go. Five months ago there was an HN post on
       | Suno's prompt-based music authoring and I asked for exactly this.
       | 
       | > "I have little interest in typing a text prompt and getting a
       | complete song as an output. However, I will gladly pay serious
       | money for a tool that interactively collaborates with me in a
       | granular, iterative process of generating, adjusting and mixing
       | individual instruments and sections toward a finished multi-track
       | song project." https://news.ycombinator.com/item?id=43873781
       | 
       | It's clearly early beta and some key elements still aren't there
       | - like optionally getting dry tracks (no effects) and MIDI output
       | for generated solo instrument tracks - but Suno is absolutely
       | headed in the right direction. So... congrats to the team. I'm
       | excited! Although I recently retired and no longer have a studio,
       | big budget or session players - I also no longer have the client,
       | the client's "wife with _great_ ideas " and a hard deadline. But
       | I've still got passion, experience and a good ear along with more
       | time to explore creatively interesting directions. Vibe coding is
       | fun but extrapolating forward from the Suno Studio demo video,
       | it's clear Vibe Producing has the potential to be _amazing_.
       | 
       | ASKS: I'd also love to see the ability to collaboratively evolve
       | one aspect of a generated instrument track while holding most
       | other aspects constant. This is how we'd work in the studio with
       | session players. Stuff like "That's almost it... but give me a
       | few variations with a trill at the end like _this clip_ but
       | played with the sultry sound of the trumpet in _this clip_. "
       | 
       | CONCERNS: My concerns are similar to the gaps experienced devs
       | report with coding AIs being like "a junior developer with a bad
       | memory and a parakeet's focus." If Suno Studio's AI is granular
       | enough to collaboratively evolve its generated tracks over
       | several iterations without losing sight of what's good about
       | them, then it'll be productively useful. The only other
       | significant concern is Suno Studio being it's own web-based DAW.
       | A real DAW like Cubase or Bitwig is Hard. A browser-based tool is
       | going to quickly run into thorny challenges around sample-
       | accurate, jitter-free audio I/O, multi-track disk buffering,
       | real-time effects, sub-mixes, ASIO plugins, etc. And none of that
       | intractable mess of heavy-lifting is required for Suno to deliver
       | their core value prop.
       | 
       | STRATEGY: If I was having a beer with Suno Studio's PM Henry
       | Phipps, I'd be encouraging him to either partner with or buy a
       | mature, cross-platform DAW that's already solved those problems.
       | The "buy" strategy has obvious benefits in quickly side stepping
       | all the challenges of browser-based pro audio tools as well as
       | securing an installed base of experienced producers used to
       | paying real money for real tools. The partnering strategy seems
       | cheaper and easier but, in my experience, doing it well is
       | harder. I'd suggest working with one leading DAW but developing
       | an open API to enable seamless workflows between traditional DAWs
       | and AI services. Such an API would let Suno focus on what Suno
       | does best while letting DAW makers avoid having to become
       | competitively competent in neural nets, licensing tagged training
       | data and running cloud GPU services profitably. No DAW developer
       | has the capital (or access to capital) to seriously compete in
       | those domains. Whether through acquisition or partnership, the
       | long-term silver-lining for Suno may be gaining deep experience
       | in digital media production tooling, workflows and customer
       | mindsets.
        
       | samfriedman wrote:
       | Nice, I commented looking for this last year:
       | https://news.ycombinator.com/item?id=40588038
       | 
       | Looks like the "covers" need some better instrument isolation,
       | but this is really huge for the music industry.
        
       | fortranfiend wrote:
       | Well there's now a polka about diarrhea after eating spicy food.
       | And a rock ballad duet about macaroni and cheese with a female
       | singer and a screamo male part.
       | 
       | Yup totally won't mess with their algorithms.
        
       ___________________________________________________________________
       (page generated 2025-09-26 23:00 UTC)