TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Suno v4.5

390 pointsby platers19 days ago

51 comments

kelseyfrog18 days ago
The real potential of tools like Suno isn’t in cranking out radio-ready hits. It’s in creating music that <i>doesn&#x27;t</i> have commercial incentives to exist. Case in point: Functional Music.<p>I started using it to generate songs that reinforce emotional regulation strategies -things like grounding, breathwork, staying present. Not instructional tracks, which would be unbearable, but actual songs with lyrics that reflect actual practice and skills.<p>It started as a way to help me decompress after therapy. I&#x27;d listen to a mini-album I made during the drive home. Eventually, I’d catch myself recalling a lyric in stressful moments elsewhere. That was the moment things clicked. The songs weren’t just a way for me to calm down on the way home, they were teaching me real emotional skills I could use in all parts of my life. I wasn’t consciously practicing mindfulness anymore; it was showing up on its own. Since then I’ve been iterating, writing lyrics that reflect emotional-cognitive skills, generating songs with them, and listening while I&#x27;m in the car. It&#x27;s honestly changed my life in a subtle but deep way.<p>We already have work songs, lullabies, marching music, and religious chants - all music that serves a purpose besides existing to be listened to. Music that exists to teach us ways of interacting is a largely untapped idea.<p>This is the kind of functional application is what generative music is perfect for. Song can be so much more than listening to terminally romantic lyricists trying to speak to the lowest common denominator. They can teach us to be better versions of ourselves.
评论 #43874568 未加载
评论 #43876169 未加载
评论 #43874696 未加载
评论 #43875708 未加载
评论 #43877974 未加载
评论 #43879376 未加载
评论 #43886027 未加载
评论 #43874684 未加载
评论 #43876881 未加载
评论 #43879245 未加载
评论 #43877415 未加载
评论 #43878897 未加载
评论 #43884457 未加载
arnaudsm18 days ago
The biggest impact Generative Music had on my life was for wedding skits. Families that wanted a funny song about the bride filled with anecdotes didn&#x27;t need talent anymore.<p>The first time I heard it, it was incredible. The 2nd wedding that did it, it started to feel boring. The 3rd time, everyone hated it.<p>Similar to image-generation, we&#x27;re getting tired really fast of cookie-cutter art. I don&#x27;t know how to feel about it.
评论 #43873880 未加载
评论 #43871330 未加载
评论 #43876840 未加载
评论 #43879520 未加载
评论 #43871110 未加载
评论 #43874064 未加载
评论 #43873670 未加载
评论 #43872619 未加载
评论 #43871903 未加载
评论 #43871395 未加载
bobajeff18 days ago
I had not known that this was AI until reading the comments here. I was really enjoying the &#x27;anti-folk big band&#x27; station. Now I&#x27;m sure that&#x27;s just a nonsense genre but that nonsense was more enjoyable than the stuff I&#x27;ve found on Spotify. I&#x27;m not sure what that says about me or the state of music but I did not expect it to be this capable yet.
评论 #43874083 未加载
评论 #43872016 未加载
nikkwong18 days ago
The mood here is as notoriously cynical as I would expect from HN. Yeah, let&#x27;s all brush this tech off as unoriginal, uninspiring and bland. Let&#x27;s all tell ourselves that music requires that &#x27;special human touch&#x27; or audiences will become bored, unimpressed and uninterested.<p>But I&#x27;ll bet you anything, the average ear won&#x27;t care. This music is already as good as what&#x27;s produceable by humans, and will be available for a fraction of the cost without the licensing fees. Be ready to see it popping up everywhere—in cafes, restaurants, on TV ads, on your next spotify playlist. These soundtracks will become ubiquitous, and these far cries in communities like these will become a marginalized minority just like any technology that&#x27;s been superseded.<p>Human generated music will still exist, of course, as the deep emotional ties that humans feel towards others (artists) cannot be replaced by this technology. But, there are massive use cases where that type emotional connection is not necessary (everything i noted prior, but also game &amp; movie soundtracks, in waiting areas, tv shows, etc), where I would place a strong bet that this will eventually become even more commonplace than human generated music.
评论 #43877265 未加载
评论 #43877539 未加载
评论 #43877606 未加载
评论 #43879354 未加载
评论 #43877579 未加载
评论 #43877295 未加载
评论 #43877696 未加载
评论 #43877203 未加载
TheAceOfHearts18 days ago
One of Suno&#x27;s biggest weakness is their lyrics generation, and that you can&#x27;t generate lyrics without also generating a song. I think it&#x27;s better to use a different LLM to generate and iterate on lyrics, which you can then pass to Suno in order to generate a final song.<p>If anyone here has a subscription and they can spare the tokens, I think it would be fun if someone shared a song about Hacker News.<p>I&#x27;m hoping that in the future tools like Suno will allow you to produce &#x2F; generate songs as projects which you can tweak in greater detail; basically a way of making music by &quot;vibe coding&quot;. With 4.0 the annotation capabilities were still a bit limited, and the singer could end up mispronouncing things without any way to fix or specify the correct pronunciation. This blog post mentions that with 4.5 they enhanced prompt interpretations, but it doesn&#x27;t actually go into any technical details nor does it provide clear examples to get a real sense of the changes.
评论 #43875267 未加载
评论 #43874921 未加载
评论 #43871900 未加载
评论 #43874384 未加载
评论 #43871781 未加载
andrewclunn18 days ago
I&#x27;ve been doing music composition and songwriting as a hobby for a decade. 4.0 is where Suno added enough features where workshopping things conceptually there first made it worth it, even for someone who can and often will, break apart stems into composite instruments and then manually adjust as needed. People always worry about what this means at the low effort &quot;spray and pray&quot; approach to music, but ultimately, it also allows for faster and cheaper iteration and development for all involved. Is the finished product ultimately &quot;better&quot; though? You be the judge.<p>For comparison, here&#x27;s a song where I forced myself to do everything within Suno (took less than a week):<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=R6mJcXxoppc" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=R6mJcXxoppc</a><p>And here&#x27;s one where I did the manual composition, worked with session artists, and it took a couple months and cost me several hundred dollars:<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=I5JcEnU-x3s" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=I5JcEnU-x3s</a>
tern18 days ago
The fact that LLMs compute an average of human culture is more apparent in music AIs than any other medium. You cannot get these things to do anything original, same as with images, designs and creative writing—and it&#x27;s not an &quot;intelligence&quot; problem.<p>I&#x27;m not sure if this is solvable, but I think it should be a bigger research topic. If anyone knows of any papers on this, I haven&#x27;t found one yet (not sure what to search for).
评论 #43874527 未加载
评论 #43875356 未加载
评论 #43877688 未加载
评论 #43876211 未加载
评论 #43876113 未加载
cdrini18 days ago
That is a very cool UI; super fun to just hit random and find new niche genres&#x2F;styles. I&#x27;d never heard of klezmer, for example, but such a nice style! I don&#x27;t know if it&#x27;s the music, but it&#x27;s been a while since a website has put this big a grin on my face!<p>I keep wanting to save some of the songs I hear. Damn, I don&#x27;t think I would really be able to tell in a blind test that these were AI.
评论 #43870395 未加载
评论 #43873958 未加载
评论 #43875121 未加载
progbits18 days ago
Aren&#x27;t they still in active lawsuit with Sony etc about training on music without license? Yet still releasing new products?<p>I guess they are hoping for the Uber outcome where they earn enough money during the illegal phase so they can pay some tiny fine and keep going.
评论 #43870978 未加载
评论 #43874741 未加载
评论 #43874316 未加载
评论 #43871225 未加载
评论 #43879248 未加载
whywhywhywhy18 days ago
Feel they didn&#x27;t really test these genres<p>&quot;Cajun synthpop chant&quot; has no chanting or synths, it sounds more like country music with french woman vocals
评论 #43870566 未加载
评论 #43870437 未加载
评论 #43870194 未加载
评论 #43873571 未加载
评论 #43870103 未加载
srrdev17 days ago
Excited to see Suno&#x27;s model advance. We use it for rock vocals (<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;shorts&#x2F;Zi0KXpSuQeQ" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;shorts&#x2F;Zi0KXpSuQeQ</a>) because nobody in my band can sing. We do all the music and layer the vocals on top from the Suno-generated stems. All things considered, it&#x27;s been great. We have, however, run through the &quot;range&quot; of rock vocalists. Suno must be under a bit of pressure to generate vocals that don&#x27;t sound <i>too much</i> like any real singers that themselves are not derivative.
nusaru18 days ago
Immediately got a banger: &quot;Dimensions of being&quot; <a href="https:&#x2F;&#x2F;suno.com&#x2F;song&#x2F;dd3dbde0-4df6-4aec-a9be-bd2f64c281c8" rel="nofollow">https:&#x2F;&#x2F;suno.com&#x2F;song&#x2F;dd3dbde0-4df6-4aec-a9be-bd2f64c281c8</a>
评论 #43874944 未加载
评论 #43873773 未加载
评论 #43876985 未加载
spaceman_202018 days ago
AI has killed my desire to write and make music. It all feels so pointless<p>I increasingly feel like withdrawing from the internet as well. Half of the users are bots anyway
评论 #43877232 未加载
评论 #43877117 未加载
评论 #43879250 未加载
cryptonector18 days ago
I put in &quot;milonga&quot; and it didn&#x27;t know what to do with it. I put in &quot;tango&quot; and it gave me a bandoneon solo that meandered jazz-like -- it wasn&#x27;t bad, but it wasn&#x27;t tango either. For &quot;vals&quot; it gave me more of what it gave me for &quot;tango&quot;. For &quot;candombé&quot; it gave me nonsense. But all the pre-canned stuff sounded pretty good to me. I guess if I was familiar with &quot;Russian techno&quot; I might find what Suno generates for that to be garbage.
jppope18 days ago
Love the site, and impressed by what they generated there. With that said... I&#x27;m starting to feel like music might be the last thing to be affected by Generative AI.<p>I IV V with different accents over the music and different drum sounds is fine, but thats not really music. It&#x27;s pretty bad when you can pick out the chords progression in 5 sec. Cue the infamous 4-chord song skit by Axis of Awesome.
评论 #43872024 未加载
评论 #43871573 未加载
评论 #43872518 未加载
评论 #43876772 未加载
smusamashah18 days ago
I tried Urdu. The music quality seems good but the pronunciation is wrong (e.g. slight aa sound instead of ee sound) for many simple common words and helper words.<p>But I don&#x27;t understand why its wrong. If its trained on lots of Urdu&#x2F;Hindi music, no one pronounces those words like that. How does it get the a&#x2F;e wrong while still singing almost correctly? It&#x27;s weird.
评论 #43873569 未加载
BeFlatXIII18 days ago
What I&#x27;d love more than generated audio files are if music AIs output sheet music or a Garage Band project file containing the same song. Much more useful to use as a musical base that way.
cynicalpeace18 days ago
I have a hypothesis that AI music and other arts will not take off.<p>My reasoning is that the fact that it was made by another human is <i>really</i> important.<p>Not only because you might think a piece of music is lame because it was made by AI vs a human.<p>But also because all the things that bring you back to a piece of art is wrapped up in the person that made it.<p>People who are immense fans of the Beatles, Taylor Swift or Kanye West illustrate this point.<p>You keep coming back because you liked this person&#x27;s music before, and so you can&#x27;t wait to preorder their music in the future.<p>Same goes for books, paintings and really all other art I can think of.<p>An artist develops a following that snowballs into their music being broadly consumed.<p>There are &quot;AI music artists&quot; that have been around for a decade. Miquela is the one I know about. But in that timespan, hundreds of human artists have developed followings and cultural sway that far outweigh what Miquela has done.<p>It seems more and more that AI is simply another tool for humans to use. Rather than a replacement altogether of humans.
评论 #43877928 未加载
评论 #43874276 未加载
codergautam18 days ago
Blog post <a href="https:&#x2F;&#x2F;suno.com&#x2F;blog&#x2F;introducing-v4-5" rel="nofollow">https:&#x2F;&#x2F;suno.com&#x2F;blog&#x2F;introducing-v4-5</a>
albert_e17 days ago
A more simpler realization after playing around with the music player on the home page -- being able to skip tracks and sample a large variety of music tracks without any ads in between -- was pleasantly surprising!<p>Everytime I clicked next I was subsconsciously cringing and expecting an unwelcome and jarring ad to blast through my speakers - and each time releived to actually be greeted by the next music track.<p>What have we done to ourselves.<p>It only feels like yesterday that the default was hoarding all your favourite tracks and playing them at will through winamp.
IAmGraydon18 days ago
I&#x27;m a musician and I&#x27;ve been pretty excited about AI music generation, which seems to stand in contrast to most musicians. So far though, the available AI music gens are just plain terrible, including Suno 4.5. Everything sounds exactly like what you would get if you bought a library of really bad loops and just layered some together. Boring rhythms. Boring harmonic progressions. Boring melody. Boring lyrics. It&#x27;s just terrible. I just listened to around 100 song on Suno and I didn&#x27;t find one that was even remotely interesting or even just fun to listen to. I&#x27;m not a music snob - I&#x27;ll listen to everything from Sigur Ros to At the Drive-In to Insomnium to Ella Fitzgerald to Taylor Swift to Dua Lipa. I just want something that can grab my attention, show me something interesting, and generate a feeling.<p>Here&#x27;s the thing about music - what makes a good song is a sense of unexpected familiarity. In other words, it&#x27;s based on a set of broad, familiar rules (music theory), but surprises you by implementing those rules in a way that&#x27;s extremely unique and novel. Because generative AI is kind of like an averaging machine, rounding off the outliers, what you get is an example of the rules in the most boring, typical way possible. It completely lacks the element of surprise, and I&#x27;m not sure it will ever be capable of that essential element of surprise because of how it fundamentally works. If you want to generate a bunch of background elevator music, however, this seems to be extremely useful for that.
joshu18 days ago
i want the reverse. i give it a song and it tells me what the description is, and then let me search other existing songs. i have a bunch of weird music that i like and not even their creator&#x27;s other songs sound much like the one song that i like...
评论 #43877306 未加载
userbinator18 days ago
I stumbled into the rabbithole of AI-generated music on Youtube several months ago, without realising it was AI, and I don&#x27;t know if they&#x27;re using Suno or some other generator, but I was impressed and entertained. I doubt it will replace real concerts but for background music and the like, it definitely does its job.
hombre_fatal18 days ago
That&#x27;s a sick UI gimmick.<p>And it&#x27;s even cleverly mobile friendly.
hargup18 days ago
There are some really fun songs in the &quot;Search&quot; section after you login. Example <a href="https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;xI4rAExMFVsEf1ZD" rel="nofollow">https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;xI4rAExMFVsEf1ZD</a>
mrandish18 days ago
Personally, 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.<p>Allow users to creatively engage by providing suggested starting places in the form of BPM, key and chord progressions or as brief audio and&#x2F;or MIDI sketches. For example, let me give the AI a simple sketch of a couple bars of melody as MIDI notes, then have it give me back several variations of matching rhythm section and harmonies. Then take my textual feedback on adjustments I&#x27;d like but let me be specific when necessary, down to per-section or individual instrument. Ideally, the interface should look like a simplified multi-track DAW, making it easy for users to lock or unlock individual tracks so the AI knows what to keep and what to change as we creatively iterate. Once finished, provide output as both full mix and separate audio stems with optional MIDI for tracks with traditional instruments.<p>Targeting this use case accomplishes two crucial things. First, it lowers the bar of quality the AI has to match to be useful and compelling. Let&#x27;s face it, generating lyrics, melodies, instrumental performances and production techniques more compelling than a top notch team of humans is <i>hard</i> for an AI. Doing it every time and only in the form of a complete, fully produced song is currently nearly impossible. The second thing it does is increase the tangible value the AI can contribute right now. Today it can be the rhythm section I lack, tomorrow it can fill in for the session guitarist I need, next week it can help me come up with new chord progression ideas. It would be useful every time I want to create music, whether I need backing vocals, a tight bass riff, scary viola tremelos or just some musical inspiration. And nothing it did would have to be <i>perfect</i> to be insanely useful - because I can tweak individual audio stems and MIDI tracks <i>far</i> faster than trying to explain a certain swing shuffle feel in text prompts.<p>Seriously, for a tool anything like what I&#x27;ve described, I&#x27;d be all-in for <i>at least</i> $30&#x2F;mo if it&#x27;s only half-assed. Once it&#x27;s 3&#x2F;4-assed put me down for $50&#x2F;mo - and I&#x27;m not even a pro or semi-pro musician or producer, just a musical hobbyist who screws around making stuff no one else ever hears. Sure, actual music creators are a smaller market than music listeners but we&#x27;re loyal, not as price sensitive and our needs for perfection in collaborators are far lower too. Plus, all those granular interactions as we iterate with your AI step-by-step towards &quot;great&quot;, becomes invaluable training data - yet doesn&#x27;t require us creators to surrender rights to our final output. For training data, the journey is (literally) the reward.
评论 #43874013 未加载
评论 #43874182 未加载
评论 #43874799 未加载
评论 #43879215 未加载
评论 #43874763 未加载
sgt18 days ago
If you actually know some of the languages and you realize they are just singing jibberish (much worse than actual real songs), it&#x27;s impossible to listen to. The instrumental ones can be great.
评论 #43874530 未加载
评论 #43871204 未加载
评论 #43872402 未加载
评论 #43871986 未加载
评论 #43873204 未加载
particle_theory18 days ago
I got suno to render a song that I used to sing to my daughter when she was a baby. After some amount of fiddling, it produced something quite nice and for this I am eternally grateful to AI.
visarga18 days ago
I can&#x27;t get Suno to obey the style tags, it&#x27;s as if they are not used at all in generating the output, or massively changed. Maybe they do the same trick Gemini used to generate the black queen of England. Or it&#x27;s a trick to waste our credits faster, the only way to get something decent is to spin the dice many times.
评论 #43870891 未加载
评论 #43870327 未加载
neom18 days ago
It&#x27;s gotten really good, I had it produce a track with double vocal harmonies as I instructed, it can also do echo and stuff now. I&#x27;m kinda annoyed that to try to remove the crispness they&#x27;ve just put dampening on it, it sounds... damp now... I&#x27;d take bright over damp.
lifeartreality16 days ago
I write music to create experiences, help me understand myself, much better, and even communicate in relationships. Suno has become a huge part of journaling in my process that really brings the journal to life!
jacooper18 days ago
This is going to be a life changer for youtubers and creatives who need background songs for their videos, you can now create tailored songs for whatever you need.<p>Its great, however it sucked in other languages, sounding like a foreigner trying to speak like a local.
killerstorm18 days ago
I&#x27;d be a lot more interested in AI which can take existing music as the base. I don&#x27;t want a new song, I want to hear music I love in a new way. Like img2img but track2track.
评论 #43875928 未加载
评论 #43875618 未加载
评论 #43880706 未加载
kkoncevicius18 days ago
16-bit blends (i.e. 16-bit Portuguese) do not feel like proper 16-bit sound.<p>Right now it probably blends the styles together, taking elements from both, but not following the required restrictions.
评论 #43881070 未加载
satisfice18 days ago
What is it? I hate products that are soooo coooooool that they don&#x27;t even bother to explain what they are.<p>Something about music? okay. What else? Is it all fake music or something?
Sammi16 days ago
Why can&#x27;t I log in using my own email?!<p>Why do I need a phone number or use a cloud provider? I don&#x27;t want to be associated with any of those.
S0y18 days ago
Honestly it baffles me at this point that Suno keeps trying to generate lyrics when everything else it generates sounds so good.<p>All of these example get ruined by the most simple and boring lyrics imaginable. Poetry is an art and clearly the model doesn&#x27;t yet grasp all of its nuances like it does for the rest of the &quot;composition&quot;.<p>At this point the only thing that gives this away as AI generated are the vocals.
评论 #43871213 未加载
评论 #43871818 未加载
评论 #43875066 未加载
评论 #43872529 未加载
评论 #43871197 未加载
tylershuster18 days ago
I&#x27;m conflicted about this. I want to dislike it, but frankly I don&#x27;t appreciate the actual musicianship in music the majority of the time. If I&#x27;m listening to something that has broad and long-lasting culture impact like Bach, or Britney Spears, it really matters more about how it&#x27;s been received than the actual quality of the music.<p>Or, if I&#x27;m listening to music just for the vibe, I really don&#x27;t care how it&#x27;s created, as long as it doesn&#x27;t offend me auditorially. I&#x27;m really not listening actively. So I suppose that&#x27;s a bit of an indictment of myself, but I don&#x27;t think it&#x27;s a serious character flaw in myself. I should probably just try to pay more attention to the people around me at all times.<p>I have a lot of fun putting my own poetry in here and mashing it up with the styles that I enjoy listening to, or that I think would work well with the poem. Again, I don&#x27;t want to like it, but I do.
dumpsterdiver18 days ago
If anyone is interested in the difference between &quot;AI slop&quot; and something with a couple thousand credits into it, here&#x27;s my #soundseasons entry (I don&#x27;t expect to place; the end needs work I didn&#x27;t have the energy for (and I mean even if I did...)):<p># Original record scratch contest-style song <a href="https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;8MvZmfkDPIPmKLtm" rel="nofollow">https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;8MvZmfkDPIPmKLtm</a><p>And this is a good example how the &quot;magic&quot; is lost in a cover of that same contest entry with no attempt to curate:<p># v4.5 cover <a href="https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;KyCZZNn6PpL4JHbO" rel="nofollow">https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;KyCZZNn6PpL4JHbO</a><p>Here&#x27;s another one I put a bit of time into, but with a much simpler structure. What I appreciated about the original were the emotions it stirred up when the notes came together just-so:<p># Original ambient synth <a href="https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;JtmmbdA2VtgO4drK" rel="nofollow">https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;JtmmbdA2VtgO4drK</a><p>New cover, pretty decent but it lost what I liked the most (haven&#x27;t had great luck with v4.5 remasters yet, but I do a lot of weird things):<p># v4.5 cover <a href="https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;Gi8wy1QjUaHmYNKy" rel="nofollow">https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;Gi8wy1QjUaHmYNKy</a><p># Original piano piece <a href="https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;yj8rHRRgJEWD83GY" rel="nofollow">https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;yj8rHRRgJEWD83GY</a><p># v4.5 remaster <a href="https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;Xx5Y5SNl1MdDrLsO" rel="nofollow">https:&#x2F;&#x2F;suno.com&#x2F;s&#x2F;Xx5Y5SNl1MdDrLsO</a><p>When you ignore the stuff that humans shouldn&#x27;t get credit for - e.g. I didn&#x27;t &quot;make&quot; this song, or play any part in its &quot;production&quot;, but I did &quot;curate&quot; it - there&#x27;s still something left to give credit for, right? It&#x27;s basically like a DJ digging through a mysterious crate of records.
评论 #43893254 未加载
miffe18 days ago
Still not able to generate a &quot;Italo disco, sea shanty&quot;. Me and my friends have been trying since v3 somthing.
tsoa18 days ago
Where&#x27;s defiant jazz?
评论 #43876385 未加载
n8m818 days ago
I still hear hissing on many of the examples, has that improved?
Rochus18 days ago
Wow, this is just great. As a musician with computer science background (or vice versa) I&#x27;m just stunned. E.g. this track blew me away: <a href="https:&#x2F;&#x2F;suno.com&#x2F;song&#x2F;6478ac9a-00e9-4f7d-81bb-b0991001d236" rel="nofollow">https:&#x2F;&#x2F;suno.com&#x2F;song&#x2F;6478ac9a-00e9-4f7d-81bb-b0991001d236</a>. The drums and the sax solo are just great, sound like from the best musicians on the planet. It&#x27;s fasctinating what comes out of this grab bag with each click.<p>EDIT: don&#x27;t understand why this statement is downvoted; since when has HN been hostile to technology? Or if you think this is a paid bot comment, I&#x27;m real, here&#x27;s my website: <a href="http:&#x2F;&#x2F;rochus-keller.ch&#x2F;?cat=3" rel="nofollow">http:&#x2F;&#x2F;rochus-keller.ch&#x2F;?cat=3</a>
评论 #43878561 未加载
fuzzythinker18 days ago
Love the UI! Beautiful and great for exploration.
carefish18 days ago
Am I one of the few that strongly dislikes verbiage like &#x27;Commercial use rights for songs made while subscribed&#x27; on their billing page, it feels and smells an awful lot like &#x27;You&#x27;ll own nothing and you&#x27;ll be happy&#x27;. Also feels like another race to the bottom for yet another creative field. Not trying to dissuade usage of tools like this by others but it leaves a bad after taste.<p>Whilst it&#x27;s not clear where the training data is coming from, how can I be sure that I won&#x27;t accidentally trip up something like YouTube&#x27;s Content Match tool or other companies whom act on behalf of a copyright holder? Or did I miss something?
88stacks18 days ago
I want an api version of suno!
nilslindemann18 days ago
My Groove list is better :)
93po18 days ago
regular player on main site is entirely broken in firefox :(
iandanforth18 days ago
I recommend clicking around on genres for languages you don&#x27;t speak. The songs sound great as long as you don&#x27;t know what they are saying. Lyrics are still a very weak point for AI music, still, infinite enjoyment as long as you&#x27;re ignorant of the flaws!
tmaly18 days ago
I honestly would like to see an open source music model that can generate the stems
DataDaemon18 days ago
&quot;I want AI to do my laundry and dishes so that I can do art and writing, not for AI to do my art and writing so that I can do my laundry and dishes.&quot;
评论 #43874437 未加载
评论 #43877623 未加载
评论 #43870871 未加载