Thank you so much for the response!

So here's the situation....

I think I'm a pretty damn good programmer, but I'm not really a DSP guy (I know enough to get by). I spent 4 years at my last job working with Will Pirkle, so we pretty much had the DSP covered...LOL. Now, I'm trying to do as much as I can on my own without bothering too many people . I figured that maybe the solution would be to leverage AI to fill in the holes in my tool kit. I've tried SOOOO many AI plugin development platforms (Amorph, APC, Vybecoding VST, etc, etc, etc) and they all seem half baked. So, I'm back to HISE (which I love) but, to build some of the things I need to build, I feel like I'm going to need some custom scriptnodes. I probably just need to get in there and start the old tried and true way, but I was hoping I could save some time. I think what's been missing in my vide coding attempts has been that I need go to lower level in my prompts and specify actual DSP tasks that I'm trying to get solved.

I apologize if this has been discussed before....

Has anyone had any luck in vibe coding new nodes (SNEX or C++)? If so, could you share anything that might either talk me out of even trying or, better still, point me in the right direction?

Chances are I would mostly be porting existing code into custom scriptnodes. There might be cases where I try to vibe code something from scratch...

Any advise would be greatly appreciated.

Welcome.....very glad you are here!

Thank you so much for doing this. Truly great.

YES!!!
Thank you. I cannot wait.

Thanks for the help....I really appreciate it. I knew my code was a bit slapped together and this is a great improvement.

I finally heard back from the developer that created the IRs to begin with and it appears that their IRs are XOR obfuscated. That would have been good info to know ahead of time. Very frustrating.

I hope this makes sense...lol...

The snippet does 3 things:

[1] Dynamically builds a 3 tiered combobox menu by scanning a shared IR folder

[2] Load 2 default IRs when launched - NOTE - This is where the code that loads the suspect IRs is

[3] Allows the user to load their own IRs

HiseSnippet 5083.3oc6cs0aiijclxtoaa0SOWxN6lj2HTR.r231iHssrrGjc78dbFq1FRd3r.wKZPQUxhaSQpPRYasaZr8i4w8k.jGyKA4uQdJOm+AY+IL+.Bvrmp3spHqhVRc6dbOPZvzvrN04RcpyWwCqhUwy8bMQ99tdRkJewnAHoRejbqQNA8NnmgkizIGJU5SjewdMTt.4GnTccsZR6OZfguOpiToRy+bbkJszijH+99uZeCaCGSTZQRR5tVlnSs5aEjV5469MV11GazAcgUepZuwtmX55bfqs6PvflWtpz.CyWYbE5EF3pMmrzWa32SpzuT1ryFlaXVq8FpFFc2RscMT65paohpatYmsMMML2rso55qaHUZgi5XE350JvH.4KU5Q661YTqdt23Dp.cKeq11H7EpRs.MGV7wt1cvMQboRGzyxty4wdJeIoRxmm52lOzu84xMr5XkTdp+6SIDTR4f1AVZNVyadFySk17pRYdbLoRTljbnI8YxsL8rFDjRAaOOQ9Dm.jWWCneh1Tdwv96Mrik6wV1XKQtz7PORn.jlq8mIefKvlSvZ8MdE5XO3hDwrbspUWUA9mU9xxk+hu34n.ECrjT5BhRYfqqcYna0OpTh7U9GTNx4JKGzZ1tFcR0KHS2yAFVFKJPVmaDzSIvUYf8Pn1J98L7PcT7P9PDhIRoKtaxKR5Vd3Z+7CAYW4fct7RnYekmQ+CMBLt7xm2yEpxgVWCNTWmJeIkriD5IMiDmeF4c7Pa6wPlWdooa+9tNuzxyuBwQzZ.xzpqkIVzC.QEI2fdnSZRT9jIzKu76Z8bE8KVu5kWtQ8zqTdlx2VeK3egdHzKOpyUn0tBKjJDO38zuDIevd6yq3245Cj7oPnB16ozA00XncfhoQ6x33mCLZqFGwP+iv.IL0wvlzASh8rffLk9tcFBWvpDKGaHlTo6PGy.v6qjJ7ee4kJuzW7EldH.np3192BAgcQdHXzNbLDXIJpJP+60t1CIrFI+xKY6ZBJG3.KHnKmL75ZWgBHQ8sL5OvFkfPWtBTqJPSgnMLRB2d0TP2F0Hn.V91tAIxuKDfD.ROROIxGipVFCLipmOBLxNhpnJ1IRTc6gv.LDkG41TbfwfSTGv5IMUe4MFWiChwQhMCiD2jDHhv970.pUhZI1wccbZHQcHDmWpaizfHiNPrrJ+9yad1+3QGbwKO9rSO7nluthxeOkUfafgMsTVv+SqQ9An9q00ys+ds8w8MHLxa4DL3JqE31Jvyx4JvKga8ulNH5naSicvxE4IHzjsppgkGB2u1vSocfyIMOkH.bHP7Pofu+.29C.XqSvxUnqTERzb1vQWG55fkhGLToYrHVEzk8PzJkiBV+tdHGVmNXasGFD.hxxWY.LLJL1+pJ1FfB5oXD1O21y8FejGzMFAy.eCNDGKHeh6ToxgtlC6CZzuR7PvzpaHlcejMxLvWwvAz5pDumhU.UWcDNwwsCRQs7RT8VgV.c+Wh9VUoqgsOZUkJ+xnA4VMw8rLzd.yckxKAs+oCqtzR3dqIFqtDlS7+m.YEgWiUAI5F5MJBvlQjP6z1N9VIJ3HZRogM5X4lDWis9PRzA3eYnDgHG.KfVa.TbPJVPkVqSNhcokhZUoPPVQ+Z3edMDWONg+q4iIRBvOvv1tMjG3xbC+SG1mFApEiM4hA0FGLn1XfA0JDC99FB91gA0.AL4fP7X7OHffSF9qE4dEhAfpu0.PMw.voGfEa1bPXZSDBSaLPXZ4PXSVlgvu8+1SN8PrK6fyZr+Y6e1uNWUObDjWgEjRg8HElbN.DUaWk1t2pz1.fHJtc6B+eDUr+IDMjj6dGKOHV20aTnsx6tvGfE49t2J9VvI0PD1OoBEA7KuD6.rILg01I.T5BnKe4UJruhxR32Qk0Rh5kNvFEFER4.IFle4Ty.D3xUr.CwuxpUpD9TaMQP3HH9vHcRLXRHN3LMhxdh9AYr7HOyF4ItnS1xxgDa5WXFXzOc0JL2OOvCbiDa5b2ACswCfPGSfaQ2XgezsdQIkFGWPiedlhOf4FnXbiwnvlDYPRpggLb5jzVIXPGber+Rk655or7s3HrjFHY3bv4FNbVznZINYrE4OrsIT3UtdVf1iBYcxm.sxyfevCFBODs2upgkI9+O202BqarJ7PCrMLCEdEnUTAFDefgmADYmDzmHsP+Pkc1oBNjKt20nSGbP1xKea5HOpqrxZQhdYhXWkvFDCpDlqH4gbw8HYCduMSBx35lneWG.1triK1+sRAbpliSnev0quQP.3mvN7DGIbGlgYkz30RvirhATjeJT+JS+iBL+B2.zYNKGlu7qKqjkT2tboEA3rQdbIimRKuhXbYmg8ai7XxVGpnTIY14BRV7bAQOUUlgiePUQWmSbrBNa.xQzDXIEMnijToEirJnpAjYM5iil0nV1V.fQxpiToGK+MNtsUkHFb7z0sxk+eekjHl2mjhCg4mHC2S47d.hPiU.jeig.9Dr.faQGNYUpYEx2+UStPzlNg7wQBgzZTmtVCQFIIw9NPFiiW8SijQ7fDQcLIiYvwc7BTvMtduBO0hyE82PvBdBDWTFFDZu9CjzQd34nBGeTcM3+j1y118F7MwrfQsITJMOorycsGMnmqikItnvZfNnmgiCxdu9tCgHwRxklCzbCbxNDl22107Usr9cHLIrQ80F9WXXAMpRy0ZnODc24LmVfbHS3LdpTeAjFqToEN1fjG.dvL7bfhwGFvsw8VyLYNYSZBoS.JFJENMyIDwxKdxnCMAvxwY.SlJ5RyioiASmCiO2GAIwQtvyc.xKvBEOor3qFAbf06GIehuNlJjvijdnOGZ16659p9FDmsDquVVFB2dn4nKE5ne7X3nCsedd4mJCOD.T6.hvvidQ4FICaMlt+XyYAr9drbntuCSimAEy53p14nT6hx21EiEY06mRzKfCWKhJ+nsHh2kdYBrlKSf0mH+hg8obfQwVyKqkDQFW0EjafM7nZHK2rQKIoVPlDl8tvvCxBkHe5Bv9XXDEGD4FY9rWF4HNoCVxWgcfIlQXYj0HRZZj2iIxSku.oAc.NK9JnE0vxIowgAKMLtM4ZU35v3jvhNL74qop+lR6MLvExLIY4eXBu7GXaEHN7JjL+vqPZSS30Sk8c6F7x1Dwxp7+RZkSUI9PN5Z7VFu0puqaPOHiLxR3E4.ejrV0bAbBFzKC78wg3HBFTcZvuI7lerjpisWedJudT3Lio7DvT7PqckHiHhm6PcywD7NOUv6iSCdWT9YpUyF+hutU.ZP3v0eNbMTGxO0M1tppZMn4+JzMg1rToel7lqsgll1VU2ZqMpug55U2VJroQ.Q3mC8BWhvA.30PeD1FVR9PjoUajMMR.5v3alYwXKJisnIyLwUX8ppUWGpv1aWeis2ppZzZUlDlIvXWPlN9aAH9aspRRu+8nejbSD7X0gh8t7qLJmIiAIFTO0DjwFF9ykgmADG9rFcU3EPJKeRy69Vo3DErQ2hWARLhjZcfouBp3INcP2FJ+T+J4pDWJY8oYBvkmjQmS6KRGsFGtFPcKK0L8wKLQgioxsr74dnNHaiQiUzUb+068fKHxw.xjSHHPXjEWKMBjjZmKAEv2IkEjpos81U2XyZZZquQ8spuYz8R+ZqCFFHv1dh7wdn+4gPxiijxoOo21HimJ2.O83A87PFcFSb0GSeaPso+1oYjyCr6mFcKLKmqyzDKKCCo2aMfff6fQXYhtCVowCKlsaDqT5jwXXqP.IaeK6ye819vXLBPTXi56nvF0GjgMQoRo8VjFl1TkxUbF+STNWwLMKoqYIc8Vmz0GSmzk1zl00BPVWuT6dHsK0YocMKsqeBj105uit+45OHu+oLNGpIJqqPNl5jtdzjLmWEzccOlIkPo8tUOLi5EOmRFsaXcqzc4iZ31g9UOO90IJchxw8hGZ4az1FkDzigmvXJjeau4501Zi003Nqhi2TdlLavLy4YbOGMtcwvaUCsMUxxQIMI4cqNgMV1FDDKxnowqok4wkXZfkkS.E7aiZe.1FWerZiONLvF2OFR+dsQxHnwqMwNqwSVSR6gYSJyifItMMECF8smDmNWzZrSIjRkNDcskIJb6YfSev+UAtCfX7j27GHn+NWF9aSVn1cc2cTxE+w2ra.jK.1UfGtaP758iaUgqC2.5FZx3hcXB7iWB3+DdEwEYTBVd+TC6+XDkg8m9CQF1SwVghlRHXlud+9u5tLb5ADFOaL6aPPpcJcAsc9FF6TU4b2a.W+cYOLfWQMpowPE6PeSVG53anZSfg93w8MgPjC8Oj0gR5zFqNX07cvKLtuTEBLm+6+kHy4Ixg6LjlJpRV9MbwoXY3MJ9skYh0HcG0ebTwZTqXM9jw7E1HUguoKkBey06NzGcvP+.2932dtAgZH1HNHbI2gl8.Lw8rstxIL+RYY7.Q2X0AmrZ7nKC1sGx5pdT6bue0tjWaPo4929qkKeTeKGkCz2Zyc1Yys1Ymvc8A+RIaKobjf1LuxxU4C1PcCdxmtbQLkQGokRX3kpEQTil3Q0ptMOift7bFQDwLFQZo4XnwganoxSMLDDxVFE0TkuvnKOmrhHxWT7r4VM1ZedZgtbQLkQKokligucCtwXTEKfkLpHov7UuFeMTimTpITJ04Kk5r1IajWNpZ4ol0Bpm2BNTeqsxCFyVJeFRDOaY4pbdvX9xEwTFcjAuQSJOZKe4hXJiV3h1BIwAswgfP1xnHphywRdjX9xEwTF0vEIFRJORLe4hXJiV3hDCIkCIlqXArjQE7PhQTpwWC0JPC0DJr57EV8BDVB1RkewZ7KNTNMT9FCOGqqc8PrfQADDxFwewsXdrvBLERp.VyqubHTFprfTgjJf07ZLGZkgZF.qXZEwbdklG4xPlE7JjTArlWk4PwLTYAxBIU.q40XNDMCUFPsHJhYLu5xhtYIVSn1pUr1pIPa0JRa0Eps5Eqs5BzFKh+qOpkxgn9tNLvctkxmArF3TVtJy.wETtHlxnirHaJRLvZAkKhIPd6rCdG+vmVN1XAzhHHjsLMpb3XJZLfXAkKhoLpIK1khDCvUP4hXJiVxhWoHQCV4Wr.VxnhLXTZJ03qgZEngZ7zPMgZnNeMTu.MTmmFXwhmZY1KP4zCNFd39Mqx.HESp.VwZSDA9rw.RKhXgrySuYwrYoy.bKhXgrySyYQvYoyBiKjZwBfmxygpyVAFncQDKjcdpNKROKcF3dQDKjcdZNK5OKc5g.JfVQLySsYFQHG4ZEn0Z2kVqITq0JVq0KPq0uKsVWnVYG4H9TLgYLCdExs5XEjunrUkYrA9EKfEV4mcjfTJLiAvuXArvpgrH9TJrXcAkKhIVkjCYmRhASyuXArvphrH3TJLXW9EKfEVMjEolRgFixsT9LvJ9LHRJB03J8ZhkdMNRulHoWmqzqKV504H87HLcdHLcgHL87HLcAHLc9HL8BPX57PX5BQX57QX5Efvz4gvzEhvzEfvzKBgoyEgoKFgoyGgoW.BSmGBSWHBSmOBSu.DlNODltPDlNWDltXDlNGDltHDlNWDltXDlNGDltHDlNWDltXDlNGDlNGDlTeiawu5P++Qu6PYVGqmFspRmZfeo0rHKBL4uEtjY696hV.qedxBXoaYnre3ATCYckhWp9kVPR5G9AoITyjkNStz+dIIoQ3+3+B9i6WMtNca0gpsJED0VqH2.4LTYexwQxw3CAiVIGyHjCFRglA0Yv3itHZg7hdsEXORHwuIvTuOCzmCi3yqNGeqfQzqJ66ryIxw0D+L4ywaXS913bbrQ7aW28fMFc5Z9T4i51EYFjZfOR93e86uiRyxQQSfN4ssl4b5Y9nzSOyR+qxoGCDC7vmmGnKbO21Xzx9jyynlfEupR638gc9yNhnULmrSsW1Lb6b6OMGwDKL19H0h6hZ5NDepT0vHvyBifg1eKxYxYzlM2OdelGcc032nwVHmNjK9A3WDQU70khHpFSL8Ppf9vHnzG.aP94lsA4msA4msA4msA4msA4eWuA4W7g6d0hApv9dL+vdmawhw4rctV7g914J+nT+zae0KWZ4+FoB1hWK7tZKdk0YpJdOMc+usu32y9dOzbJ2JXSf0+.Z6gwZ0721XK7NdaiMQH3Y6f+6ycv+ieerC9u696Y6p+Y6p+2lc0+rLEmko3aYlhevdX.DJ+Y4JNKWwY4JN6XG3d6XGPdpO1A9QM8uYGEAyNJBlcTDHnM9iyQQ.u7HtuNdBV7GuimfouYdedjEPe7iOMGeAzqW+OKd85IYrdpKlYxsA97vRTvEofW6a7F0V72Rz+2w8aI5fw9aIZqQNljU1i58pf7RNbgmg4qv4qQoJrYdjSXWHU8aB21F+sgf9aYZ32jnVAFdAf3oERSDjCkOhoLbR7g27su7y24xFiTNzy5ZD9i.4uE+wZ5xlH3Ai6.lykPZjVHGEspZZJOS4ep4Q6c9QM+MWdH9K0xYcU9NK7KIzksvaH6KacwQMZob7YMUZr2EW97KZBbb3Ij+PE+QZRpO16JW5+r7bwujP+O+h+NIanYRr7XZ1j1cmX5klunOeppS4mO0G8f6ym5G.u4NLuVJKEaisrvAeGAIqaCPMhM9WHGMLSbor3rFtNtwuADzgpAdVWcE44SRrctMn8BB.3RZIe9tMQ1H7sDSJ5uc2SgbpM7xh1l.eg536KJp+5uRNzbUvCNn7g6ab07+j9Mt58xaSz6Ccz2vzy8kQuTK33zEIk.saGxP9KI2.esBmu6K8gQ4dooIqnxwn1zx35SKiaLsLt4zxXsokwslVFqe2LhuITzb3hglRRMN+HRlRkJkjlPo4k9y+o55AC

Hmmm....that is not what I'm seeing.

The IR on the left is loaded from a custom location and has a custom ext and the IR on the right is from the HISE AudioFiles location.

I am working on a plugin that must share IR resources with a bunch of other plugins that were not built by me. My plugin must use these resources. The problem is that the company have given their IRs custom file extensions:

theirIRs.customExt

I'm guessing that I would need to modify the HISE source to allow this extension to load into the convolution node? If so, I honestly don't know where to start and any guidance would be appreciated.

On a side note, I imported the IRs into a DAW and they loaded right in as audio files. So, I'd assume it's just the extension that is the issue.

Are there any plans to add the ability to compile to LV2, and if so, would there possibly be support for headless builds?

@Oli-Ullmann
My understanding is that Claude (https://claude.ai/) is supposed to be much better than ChatGPT at writing usable code.

@Oli-Ullmann
That is amazing! If you don't mind me asking....could you share the prompt you used in ChatGPT?

Strange....
I'm getting a "function not found" error when calling loadNAMModel

@Dan-Korneff - If memory serves me, I tried this and it didn't work for me. I think it's not fully cooked. I have only been able to get the Tensorflow/AIDA-X stuff to work.

@HISEnberg Yes, that would be awesome.
BTW....thank you so much for the help. It's much appreciated.

@HISEnberg OHHHHH.....that might work! It ain't pretty.....but it might work...

@HISEnberg
So, I originally did that....each NN node had a different "model" loaded. But every time I switched between the nodes, there was an audible loud "click". You can also see from the first screenshot, I also used a Branch node....same problem. On the other hand, if I use just one NN node and switch the "model" in the dropdown parameter....no click. I just need to be able to control the value of the dropdown via script. The problem I'm having is that I can't figure out how to get a reference to the dropdown in the script.

I cleaned up the network a bit. If I can get script access to the MODEL dropdown, I wouldn't need 5 neural nodes anyway.

So, hopefully this makes it easier to see what I'm trying to do...

Again, any help would be greatly appreciated.

I am trying to change the "MODEL" dropdown value of a Neural node via script and I just can't seem to figure it out.

I had read that you reference the nodes by ID, but I don't see the IDs in the node properties.

If anyone could point me in the right direction, I would really appreciate it...

@Christoph-Hart
If I might throw my humble 2 cents in....and my 2 cents are change left over from a whole career of working in guitar amp modeling software, having spent almost 20 years with the ReValver amp modeling software and another 4 years with the HeadRush pedals and software. The software market segment of simulating hardware has completely turned from component level modeling to leveraging NN modeling. Neural Network modeling allows us to do in a matter off days what took months or years to accomplish, with better results (most of the time). Beyond guitar products, NN modeling lends itself to preamp, channel strip, etc modeling, which is why it's such an opportunity for @orange. This has really nothing to do with simply downloading models from tonehunt.org, this is about implementing something that will be "how it's done" from this moment on. Here's a real-world scenario: I am currently working for a guitar amplifier manufacturer that has a 60+ year history in guitar amps. They would like to release plugin versions of every flagship amp they have ever made AND ship a plugin version with every new amp that they design and release. This is my project, NN modeling is how to do it, and I have to find the solution that lets me get it done.
Having said that, I have really fallen in love with HISE in a short time, but it might not be a realistic solution (at this point) for my project. I would hate to see all this not properly implemented in HISE. It would be such a missed opportunity.

Having said all that.....we are about to enter the 2nd wave of NN modeling market disruption, which will truly change everything...again:

https://www.neuralampmodeler.com/post/the-first-publicly-available-parametric-neural-amp-model

Thanks for letting me get that out....