I know you hate it - They hate us too

[wagtunes]

Also, what if I create a new prompt, say "Disco drum beat, 4 on the floor kick"? Does it create a new sample or just use what's already on the disk? If a new sample, where does it store it?

Haha for the manual I know will have to work on that one day instead of adding features and features, as I think you know (if you don't that's... Well... Weird) I don't like such corporate things that making documentation But apparently I have to grow up a bit, 40 is a good age for that they say.

So, for you issues.
I you create a new prompt it simply create a new prompt. When you create it, when you save it, it select on the left panel. Then you drag and drop on the target track you want the sound to be generated, and then you click on the generate button.
All samples are in C:\Program Files\OBSIDIAN-Neural\AudioCache and an other folder, I let you check that in your computer.

Okay, where is the generate button? I've never had to clock on ot to get the samples to load and play. I just select the box and drag the prompt into it.

Now, does my new prompt create a new sample when I click generate or just use something that's already on the disk?

[Innermost]

The generate button is the button at the right of each track, with a lightning icon and GEN words under.
Ok, social pressure won, tomorrow I make a tutorial video. You're far from the lone who want to understand how all that works

[el-bo (formerly ebow)]

I don't even know where the scat button is

If you do end up finding it, be very careful

Thanks for your support

You’re most welcome

[BlitBit]

[...]
All samples are in C:\Program Files\OBSIDIAN-Neural\AudioCache and an other folder, I let you check that in your computer.

If I understand correctly, this plugin is vibe-coded and it might show here. It is not a good idea to store user data under "C:\Program Files". Instead it should be stored beneath one of the user folders like %APPDATA% or %APPDATALOCAL%.

While this thread is a completely train wreck it at least made me aware of the "Stable Audio 3" models which are also used by the rather low level sa3.cpp project. So I am thankful for that.

How do you deal with some shortcomings of the model?

In some first tests it showed that model seems to be unable to generate percussions without a kick. It's a bit unfortunate because this would be one use case for me. Do the main beat elements (kick, claps, snare) myself and let it generate some filler background percussions.

Furthermore the model also does not seem to have a concept of beats because when I told it to generate two beats at a certain number of beats per minute it generated more than that.

Last but not least, when instructed to generate dry percussions it included delay effects.

[Innermost]

Hey!
Good catch with the path, have to check that, thanks.
What do you ear by "Vibe Coded" ? Where does vibe start for you?
Coz I don't use any agent to build this. Web browser with Claude yes, not for everything though. But when you're working on a project that you have to present to engeneers (I presented this VST twice in front of the Audio Engeenering Society - https://en.wikipedia.org/wiki/Audio_Engineering_Society), it's better to understand what you are doing, at least the maximum.
And about the model, to be honest I let you hack it by yourself and give your feedbacks here. Try its limits. I use this model coz' it's the best open weights one. But I don't know everything of its limits. That's why you are here, to traumatize it as you would traumatize an old school analog synthesizer. I am not inviting you to be nice guys with AI, just to be creative in order to dominate it.
WE are the human in the equation.

[BlitBit]

[...]
Good catch with the path, have to check that, thanks.
What do you ear by "Vibe Coded" ? Where does vibe start for you?
Coz I don't use any agent to build this. Web browser with Claude yes, not for everything though.
[...]

To me vibe coding is one extreme side in the spectrum of agentic or AI-assisted coding. Vibe coding means getting code from the AI and putting it into the code base without any understanding or chance to dissect and to critically challenge the code. The opposite side would be to use agents and AI coding as another tool in the tool belt of an experienced engineer. The tool is simply used to speed up development and the developer/engineer is still in the driver's seat.

So instead of "vibe-coded" I should have written "coded with an AI" because as you have said, you do not use AI in the extreme vibe coding way. Sorry about that.

[Innermost]

No problem.
Thanks for your clarification message.
I spent a lot of time these last days criticizing posts about AI agents on LinkedIn (what explains why I didn't care behing rude here. When you've been rude on LinkedIn, you've no future anymore, then you're free to say what you want ) so yeah, I have my opinion on all of that
Last week I saw a video on youtube where a guy was showing how he vibe code a GTA like game with Fable 5. And so many people where extatic in the comments. I was chocked. If any video game studio would have coded such a "game", everyone would have gone to the studio to burn their offices, but there, coz that's a LLM who's coding, everyone's losing his brain. Strange world...

[Innermost]

@wagtunes
@BlitBit

Sorry for my error, files are well saved here:
C:\Users\[username]\AppData\Roaming\OBSIDIAN-Neural\SampleBank

In
C:\Program Files\OBSIDIAN-Neural
are the binaries and the uninstall file

[VOODOO U]

When I press the play button on the VST itself, it plays all the way through the sample. But when I hit the Cubase transport, it starts to play, gets through 1 bar and then goes back to the beginning of the sample. Very strange.

It could be you have the Cubase arrangement set to loop 1 bar (loop point brackets?) and the plugin is following that.

[zerocrossing]

In my view, AI is simply a new, powerful tool that will continue to improve. Like any tool, it can be used for bad or for good. The potential for bad is as strong as the potential for good, and like any new powerful tool, it can have a great deal of effect on whatever it is being used for. The point is, that useful tools don’t go away. They get used, as long as they are useful, or until something better replaces them.

So, assuming AI isn’t going to go away (which I believe will be the case), what can be done to mitigate the problems that people see with the technology? I would argue that this question is already being worked on.

They say necessity is the mother of invention. Already, science is working on ways to make data centers have less impact on the environment. It is very possible that innovations in environmentalism can come about because of these existing data centers. It is very possible that new conservation technologies can be developed from this. In fact, I would argue that in 10 years, there will be a whole new way that data centers run compared to how they run now and I bet they will be more convenient and more ecological and more environmentally friendly. I would also argue that they will also run much more efficiently than data centers of today and all of this will come about because of the concerns and complaints of the people about data centers. I work IT. Data centers have existed for decades and decades, and they don’t run very efficiently. However, attention is now on that very problem and there are new technologies and new ways of doing things that are being introduced. Even these days in the end, it is very possible that things could end up better than they were before because of the concerns people have with these data centers. Sure, AI data centers are huge, but don’t be naïve, data centers exist everywhere. In every hospital and every large business that I know of there is a data center running every place. An industry has a large set of computers being used, there is a data center. there are hundreds of thousands of data centers in the world that have absolutely nothing to do with AI. However, all of these data centers are going to benefit from the attention, AI data centers are putting eye on an issue that affects all data centers. After this, even the ones that aren’t for AI, will benefit.

Well again, the term “AI” gets bandied about a lot to describe a lot of different applications of what’s what we used to call “machine learning.” What we need to think about is cost vs. value. A Gemini search costs like 10x that of a regular Google search. Are you getting value from it? I find it often gives me incorrect information, so after I look at it, I’m back looking at the regular results, so that extra money was spent for nothing. The resources used, wasted. The Gemini response, has no value over the traditional search results.

The same holds true for generative AI music. If I’m going to use a prompt to create a song that I didn’t really write or produce, why no just listen to a song that’s already out there, ready to be streamed, or maybe even in my physical media library? (I’m old!) It’s probably a better song, and uses a lot less resources. I’ve already heard first person accounts of companies that tried to use agentic AI to replace employees having problems as prices increased and hallucinations and odd behavior created as much work as they replaced, so now they were paying for the agent and the person minding the agent, effectively increasing their costs. Meanwhile that data center that’s running those agents is increasing the costs of power for the community it’s near. I just don’t see how that’s sustainable, and a lot of it is betting on “General AI,” which I think is either a red herring to drive their stock prices up, or a complete misunderstanding of what actual intelligence is doing.

[Innermost]

@zerocrossing
I agree, especially with the full song generated. I think these kind of AI usage are futiles. Because music is not only data, music is souvenirs, culture, emotions shared with others, etc. Yes, you can generate a song with Suno, but you will generate everything exist around that song, all the concrete and imaginary things which participate to create a relationship with the listeners.
Music is a lot more than structured data.

[wagtunes]

When I press the play button on the VST itself, it plays all the way through the sample. But when I hit the Cubase transport, it starts to play, gets through 1 bar and then goes back to the beginning of the sample. Very strange.

It could be you have the Cubase arrangement set to loop 1 bar (loop point brackets?) and the plugin is following that.

Well, if I do, I never set it and I have no idea how to change it.

[VOODOO U]

Well, if I do, I never set it and I have no idea how to change it.

This is really basic stuff man. Just make sure that the loop/cycle button on the transport is off. If it's on the playback on the main arrangement follows the left/right locator markers. So if the markers cover a bar, then only one bar will loop and the plugin will follow that playback (if that's how the plugin was designed).

[Innermost]

I am very happy to see you cooperating together via your messages to find solutions.
As I don't have Cubase installed on my computer, tank you @VOODOO U for helping @wagtunes on his issue

[audiojunkie]

In my view, AI is simply a new, powerful tool that will continue to improve. Like any tool, it can be used for bad or for good. The potential for bad is as strong as the potential for good, and like any new powerful tool, it can have a great deal of effect on whatever it is being used for. The point is, that useful tools don’t go away. They get used, as long as they are useful, or until something better replaces them.

So, assuming AI isn’t going to go away (which I believe will be the case), what can be done to mitigate the problems that people see with the technology? I would argue that this question is already being worked on.

They say necessity is the mother of invention. Already, science is working on ways to make data centers have less impact on the environment. It is very possible that innovations in environmentalism can come about because of these existing data centers. It is very possible that new conservation technologies can be developed from this. In fact, I would argue that in 10 years, there will be a whole new way that data centers run compared to how they run now and I bet they will be more convenient and more ecological and more environmentally friendly. I would also argue that they will also run much more efficiently than data centers of today and all of this will come about because of the concerns and complaints of the people about data centers. I work IT. Data centers have existed for decades and decades, and they don’t run very efficiently. However, attention is now on that very problem and there are new technologies and new ways of doing things that are being introduced. Even these days in the end, it is very possible that things could end up better than they were before because of the concerns people have with these data centers. Sure, AI data centers are huge, but don’t be naïve, data centers exist everywhere. In every hospital and every large business that I know of there is a data center running every place. An industry has a large set of computers being used, there is a data center. there are hundreds of thousands of data centers in the world that have absolutely nothing to do with AI. However, all of these data centers are going to benefit from the attention, AI data centers are putting eye on an issue that affects all data centers. After this, even the ones that aren’t for AI, will benefit.

Well again, the term “AI” gets bandied about a lot to describe a lot of different applications of what’s what we used to call “machine learning.” What we need to think about is cost vs. value. A Gemini search costs like 10x that of a regular Google search. Are you getting value from it? I find it often gives me incorrect information, so after I look at it, I’m back looking at the regular results, so that extra money was spent for nothing. The resources used, wasted. The Gemini response, has no value over the traditional search results.

The same holds true for generative AI music. If I’m going to use a prompt to create a song that I didn’t really write or produce, why no just listen to a song that’s already out there, ready to be streamed, or maybe even in my physical media library? (I’m old!) It’s probably a better song, and uses a lot less resources. I’ve already heard first person accounts of companies that tried to use agentic AI to replace employees having problems as prices increased and hallucinations and odd behavior created as much work as they replaced, so now they were paying for the agent and the person minding the agent, effectively increasing their costs. Meanwhile that data center that’s running those agents is increasing the costs of power for the community it’s near. I just don’t see how that’s sustainable, and a lot of it is betting on “General AI,” which I think is either a red herring to drive their stock prices up, or a complete misunderstanding of what actual intelligence is doing.

AI is the colloquial term the media and the masses use, but that wasn’t my point. My only point in this is that maybe some good might come from the complaints and concerns about the environment that people have with these data centers. Current data centers are inefficient—they will be improved, which will benefit all data centers, not just the ones being used for “AI”.


EDIT: Here’s just one of dozens of examples of the media calling it “AI”, which so much easier for me to hunt-and-peck type on my phone screen:

https://m.slashdot.org/story/456178