121–130 of 291 posts
Aren't they still in active lawsuit with Sony etc about training on music without license? Yet still releasing new products? 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.
Do most companies just stop releasing product while in legal disputes? I don’t think I’ve ever heard of that.
Feel they didn't really test these genres "Cajun synthpop chant" has no chanting or synths, it sounds more like country music with french woman vocals
None of the Acid House samples have anything to do with Acid House either. The Jungle samples sound more like Liquid Drum & Bass.
So another slop?
Its great, however it sucked in other languages, sounding like a foreigner trying to speak like a local.
Earlier quoted context omitted.
But what's the point of spending time and thought for music prompted by others? What I can generate sounds exactly as good and has the exact same value...
Can’t you say the same thing about why listen to human jazz musicians?
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's not an "intelligence" problem. I'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't found one yet (not sure what to sear…
Any musician will tell you most music isn't original. You just don't have the ear for it. You telling me Green Day's songs are all unique and original? Even jazz uses 6-2-5-1's over and over. Unless you only listen to avante garde prog rock or something, all of music is derivative. And that's ok. Every song being a unique snowflake isn't important. If you like it or it makes you feel something, that's all that matter…
Honestly it baffles me at this point that Suno keeps trying to generate lyrics when everything else it generates sounds so good. All of these example get ruined by the most simple and boring lyrics imaginable. Poetry is an art and clearly the model doesn't yet grasp all of its nuances like it does for the rest of the "composition". At this point the only thing that gives this away as AI generated are the vocals.
Yeah, I find it funny that they have this super strong music generation model, but then they use what could only be GPT 3.5 for lyrics.
One of Suno's biggest weakness is their lyrics generation, and that you can't generate lyrics without also generating a song. I think it'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. 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. I'm hoping that…
Your comment inspired me to upgrade it to 4.5 because it did have that AI tinny quality. https://suno.com/s/tbZlkBL7XeLVuuN0
It sounds better but has lost some magic.
Here is the original comment - https://news.ycombinator.com/item?id=39997706
In that spirit, from the same “artist” here is your comment - https://suno.com/s/AumsIqrIovVhT0c9
And
https://suno.com/s/YGlpHptX6yXJVpHq
Not sure which I like more.
Immediately got a banger: "Dimensions of being" https://suno.com/song/dd3dbde0-4df6-4aec-a9be-bd2f64c281c8
Someday, I’m sure, Suno will find a way to fix this issue. But today isn’t that day.
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. Allow users to creatively engage by providing suggested starting places in the…
Try aiva.ai
Honestly it baffles me at this point that Suno keeps trying to generate lyrics when everything else it generates sounds so good. All of these example get ruined by the most simple and boring lyrics imaginable. Poetry is an art and clearly the model doesn't yet grasp all of its nuances like it does for the rest of the "composition". At this point the only thing that gives this away as AI generated are the vocals.