Live data from Hacker News

Show HN: Sonauto API – Generative music for developers

sonauto.ai

131–140 of 165 posts

Re: Show HN: Sonauto API – Generative music for developers

#131
The movie Electric Dreams is now the most prescient '80s movie about gen AI so far; An architect builds an approximation engine on his home PC which then ingests the whole internet/TV and learns to compose music for the cute girl next door who plays the cello. Song mis-attribution is the central theme. The hit song from the movie Together In Electric Dreams is actually from the perspective of the gen AI choosing to self-destruct as a final show of his love. https://www.youtube.com/watch?v=kDV-_q-iaK8

I bring it up only to provide a bit of balance to the soulless slop debate, proving creators can have diverging opinions on what is good in music creation and life—they don't all feel threatened by poor substitutes no one can possibly enjoy.

Re: Show HN: Sonauto API – Generative music for developers

#132

Earlier quoted context omitted.

Well, I create and know a fair bit about the history of music technology. Self playing pianos, for instance, allowed composers to write pieces with new complexities that would be physically impossible to play. Drum machines opened up for new types of music in the 1980s that would have been very unnatural for a physical drummer. In general, innovations in music come as consequences of technological advances and you ca…

I think many folks making the "music technology" argument tend to blur things so that human composition is reduced to "just another dial, just another new tech aid for music", "get off my lawn" etc. But its interesting to note that generative AI is unique in that it needs massive amounts of music that has already been produced to train on. Its a very unique development with some interesting questions once you sharpen…

Let's not forget that extraordinary musical talent tends to be the result of MASSIVE exposure to music as a toddler. It isn't entirely a question of DNA or effort. They start by emulating what they hear, over time they might evolve their own style, or they may not. In other words, you are less likely to become an extraordinary musical talent if you weren't saturated with music before you started going to school. Nobody finds it problematic when a musical star is performing way beyond their age, even though he/she essentially is engaging in deliberate mimicry to a much larger extent than an AI usually would be.

Are you saying that it is wrong for a machine to learn? Even if it was, it is the massive amount it is based on that makes it less problematic, as that makes room for building abstracted knowledge.

Re: Show HN: Sonauto API – Generative music for developers

#133

Earlier quoted context omitted.

I think many folks making the "music technology" argument tend to blur things so that human composition is reduced to "just another dial, just another new tech aid for music", "get off my lawn" etc. But its interesting to note that generative AI is unique in that it needs massive amounts of music that has already been produced to train on. Its a very unique development with some interesting questions once you sharpen…

Let's not forget that extraordinary musical talent tends to be the result of MASSIVE exposure to music as a toddler. It isn't entirely a question of DNA or effort. They start by emulating what they hear, over time they might evolve their own style, or they may not. In other words, you are less likely to become an extraordinary musical talent if you weren't saturated with music before you started going to school. Nobo…

I like to think of mozart and the amount of music he listened to and was influenced by and compare it to what (I imagine) is used by these machines. Heck, you don't even instruct the machines on scales, rhythms or other sorts of fundamental musical aspects, you just tell the machines to make noise that sounds like what they've hoovered up. I'm still convinced that AI music proponents want to blur and obscure the differences between human composers and machine "composers" but I personally think the differences are pretty interesting and worthy of consideration.

Re: Show HN: Sonauto API – Generative music for developers

#134

Earlier quoted context omitted.

Let's not forget that extraordinary musical talent tends to be the result of MASSIVE exposure to music as a toddler. It isn't entirely a question of DNA or effort. They start by emulating what they hear, over time they might evolve their own style, or they may not. In other words, you are less likely to become an extraordinary musical talent if you weren't saturated with music before you started going to school. Nobo…

I like to think of mozart and the amount of music he listened to and was influenced by and compare it to what (I imagine) is used by these machines. Heck, you don't even instruct the machines on scales, rhythms or other sorts of fundamental musical aspects, you just tell the machines to make noise that sounds like what they've hoovered up. I'm still convinced that AI music proponents want to blur and obscure the diff…

My best tracks are extended in 10-20 second sections. And I carefully choose the prompt and what to keep and where to continue (crop), sometimes just a few seconds. So you can compose with these models, basically, you have to if you want to get something that isn't bland.

So overall, yes, anyone can, with some luck create a "radio friendly" track with music AI, but not everyone can create good art with it. You still need to understand music, and the more you know about genres and composers and how they fit together the more power you have to create musically interesting patterns.

Keep in mind that Sunauto has 3400 generic tags + an undisclosed amount of artist names. You need to understand what makes it possible to combine different Artists/Musicians and what could lead to something interesting.

So musical knowledge is still needed.

Re: Show HN: Sonauto API – Generative music for developers

#135

Earlier quoted context omitted.

I like to think of mozart and the amount of music he listened to and was influenced by and compare it to what (I imagine) is used by these machines. Heck, you don't even instruct the machines on scales, rhythms or other sorts of fundamental musical aspects, you just tell the machines to make noise that sounds like what they've hoovered up. I'm still convinced that AI music proponents want to blur and obscure the diff…

My best tracks are extended in 10-20 second sections. And I carefully choose the prompt and what to keep and where to continue (crop), sometimes just a few seconds. So you can compose with these models, basically, you have to if you want to get something that isn't bland. So overall, yes, anyone can, with some luck create a "radio friendly" track with music AI, but not everyone can create good art with it. You still…

I am certain that AI music can produce something, but that training data needs to be figured out.

Re: Show HN: Sonauto API – Generative music for developers

#136
post #92
post #61

On one hand this is impressive, and I've been wondering when something like this would appear. On the other hand, I am -- like others here have expressed -- saddened by the impact this has on real musicians. Music is human, music theory is deeply mathematical and fascinating -- "solving" it with a big hammer like generative AI is rather unsatisfying. The other very real aspect here is "training data" has to come from…

> "solving" it with a big hammer like generative AI is rather unsatisfying. The reason is greed. They jump on the bandwagon to get rich, not to bring art. They don't care about long term effects on creativity. If it means that it kills motivation to create new music, or even learn how to play an instrument, that's fine by these people. As long as they get their money.

If our sole goal was to get rich we would have pivoted to some b2bsaas thing as many suggested to us. What we’ve actually seen is so much new creativity from people who otherwise would never have made music.

Re: Show HN: Sonauto API – Generative music for developers

#137
post #117

I would encourage everyone who thinks "I want to apply AI to music" to look at the existing problems that creators have, talk to them, and work to bring new products to market instead of things that devalue their work. "Generate a rock song" is not a problem that working musicians have. "Take this riff I recorded with whatever guitar I have in the studio and show me what it sounds like as a Les Paul through a 5150 or…

Cointerintuitively we need to build the base model before we can do the advanced production stuff that’s most useful to existing pro musicians.

Re: Show HN: Sonauto API – Generative music for developers

#138
post #117

I would encourage everyone who thinks "I want to apply AI to music" to look at the existing problems that creators have, talk to them, and work to bring new products to market instead of things that devalue their work. "Generate a rock song" is not a problem that working musicians have. "Take this riff I recorded with whatever guitar I have in the studio and show me what it sounds like as a Les Paul through a 5150 or…

Cointerintuitively we need to build the base model before we can do the advanced production stuff that’s most useful to existing pro musicians.

[flagged]

Re: Show HN: Sonauto API – Generative music for developers

#139
post #138

Earlier quoted context omitted.

Cointerintuitively we need to build the base model before we can do the advanced production stuff that’s most useful to existing pro musicians.

[flagged]

I feel like I've proven I know what I'm talking about at least from an ML perspective given we trained the model on the website. It's not strictly required, but I know you'll get much higher quality more powerful tools much more easily by building on top of a solid music foundation model than training a bunch of one-off specialized tools.

Re: Show HN: Sonauto API – Generative music for developers

#140

I really wish this trend of prompting gen AI models with text would stop. It's really meaningless. Musicians need gen AI they can prompt with a melody on their keyboard. Or a bit of whistling into the microphone. Or a beat they can tap on the table. That is what allows humans to unleash their creativity. Not AI generating random bits that fit a distribution of training data. English language is not the right input fo…

Agreed! Those will be much more fun and we plan to support that. However, right now we're focused on making the base model slightly better, then we can easily add all of those controls (a-la ControlNets with Stable Diffusion).
Post reply on HN