InnerMost47 shared this video demo of Obsidian Neural, a plugin that brings AI-generated samples to your DAW.
All drum loops, basslines, and atmospheric elements were generated using AI text-to-audio prompts, then arranged and performed live. No pre-recorded traditional samples used.
Technical Details:
- OBSIDIAN Neural VST3 plugin in Bitwig Studio
- AI-generated samples (drums, bass, pads, FX)
- MIDI controller for live triggering
- Real-time mixing and effects processing
Features showcased:
- 8-track sampler with MIDI triggering (C3-B3)
- Quantized launch system (beat-synced triggering)
- Automatic BPM synchronization with DAW
- Live sample switching between 4 pages (A/B/C/D) per track
- Multi-output routing for individual track effects
You can find out more at the Obsidian Neural site.
I’m enjoying making all those beats, melodies and atmospheric elements by myself…what is the point in this AI tool?
AI samples are legally not allowed to be copyrighted so a plugin that can generate AI samples can make sounds on the fly without worries about legal action
“ OBSIDIAN Neural VST3 plugin in Bitwig Studio” what kind of technical detail is this?
The infection continues.
Is there a DIAF emoji?
This actually looks pretty useful for producers, vs the tools that generate entire tracks of garbage.
you’re using the term ‘producers’ pretty similarly to what i experiance after morning coffee
Hard to say what is more disgusting, the AI generated samples, or the monthly subscription model.
At this point… its all disgusting…. Im all out tears though… Image generation, video generation… AI Slop.
Enshitification is the new standard. Even how some people speak/post using AI.
Here is one of the best quotes Ive read which sums our reality up. It was written in 1926.
“The most merciful thing in the world, I think, is the inability of the human mind to correlate all its contents. We live on a placid island of ignorance in the midst of black seas of infinity, and it was not meant that we should voyage far. The sciences, each straining in its own direction, have hitherto harmed us little; but some day the piecing together of dissociated knowledge will open up such terrifying vistas of reality, and of our frightful position therein, that we shall either go mad from the revelation or flee from the light into the peace and safety of a new dark age.”
? H.P. Lovecraft
With the endless and high speed parade of life and freedom ruining technological advancements, I would have quoted some ever relevant Unabomber statements. But this being such a public space, yeah… Lets not. 🙂
The synthesizer revolution and its consequences have been a disaster for the human race. ?
“AI”
this one is just a sad little footnote
to me it’s worse than a monthly subscription; it’s token-based.
Synthtopia, why are you promoting this kind of thing? There are literally yottabytes of FREE samples out there from genuine artists and real sources and you’re highlighting this when there is a growing anxiety and resentment about the devaluation of human creativity through the reckless exuberance of diving into generative AI? If you want this to be a place where artists can feel respected and supported please be bold enough to take a pass on generative AI models for music and visual arts.
This plugin is worthless.
“This plugin is worthless.”
Have you tried it?
What about the other stuff he said?
They’ve locked us Logic users out.
What kind of logic is that! lol
Hi Jeffrey!
What do you mean by “locked us Logic users out”?
I am the developer of Obsidian Neural and if there are any bugs with Logic I would be glad to understand why.
congratulations on foisting yet another faeces picasso upon the arts
Deaf to what samples and sampling are, and it shows.
è fatta per i very normal people, che non sono musicisti, scrittori, creatori figurativi… ma desiderano esserlo. Però attenzione a non essere superficiali, l’A.I. è anche uno svelamento ontologico : il soggetto parla e l’evento av-viene, l’oggetto risponde alla chiamata del soggetto creatore…la parola crea in questo senso virtuale-tecnologico, abracadabra…
Quick update: Audio Units (AU) version is now available for Logic Pro users!
Download the AU build from the latest release:
https://github.com/innermost47/ai-dj/releases/tag/v216
Install OBSIDIAN-Neural.component to ~/Library/Audio/Plug-Ins/Components/ and rescan in Logic.
Thanks for the feedback!
For people who don’t want to pay any subscription, everything is open sourced and FREE if you want to build your own server. You just have to install python 3.10, having a NVIDIA Gpu on your computer and everything is there.
https://github.com/innermost47/ai-dj
So uhh, these samples are royalty free but also cannot be useful for making bucks, right?
Amazing but it’s kinda just a toy
The samples YOU generate are 100% yours to use commercially.
The AGPL license only applies to the plugin code itself, not your audio output.
AI generated sounds cannot be copywritten but music made with it can. it means that you can use the samples without fear of legal action but the music made is human construction and can be copywritten
I am the developer of this plugin. Generated samples are usable commercially under the Stable Audio license, provided your annual revenue does not exceed $1 million USD.
https://huggingface.co/stabilityai/stable-audio-open-1.0/blob/main/LICENSE.md
I have my own home-made biological neural network for creating samples, thanks. Some things shouldn’t be too easy.
Garbage generator.
that was my first thought also.
Thanks for covering this!
Another piece of AI garbage nobody asked for and that they’re trying to shove down our throats.
I see a lot of criticism here about AI—disgust, concerns about devaluation of creativity.
Honestly, I get it. Even as the developer of OBSIDIAN Neural, I have conflicting feelings too.
When I see tools like Suno or Udio generating entire tracks from A to Z, yeah—I worry. Because the fun IS in creating music, working through ideas, composing. I’ve been making music for 23 years. I understand that joy deeply.
What I tried to do with OBSIDIAN is different: it’s a plugin that lets me perform live, mixing AI-generated elements with my hardware synths. I trigger drum loops, bass, pads, and ambient sounds via MIDI while I improvise on my gear. It’s just another “instrument” in my setup—not a replacement for composition.
Generative AI is here. Rather than reject it entirely, I asked myself: How can I use it creatively and non-destructively? How can I integrate it with existing tools without replacing them?
That’s my philosophy. If some people disagree, that’s fine—they can follow their own path. I won’t be offended if, as a guitarist, someone doesn’t want to hear about guitars. Everyone has their thing.
I also like the unpredictability—asking the AI for a sample and getting something slightly different than I imagined. That adds an element of surprise I find creatively interesting.
Yes, there’s a SaaS with a subscription. But the entire codebase—VST and inference server—is open source and free: https://github.com/innermost47/ai-dj
Anyone can download it, self-host, and have total control over the infrastructure. It’s completely free that way. You just need a decent GPU (my RTX 3070 generates samples in ~30 seconds).
I built the SaaS for users without GPUs. And yes, this project takes significant time—as a developer who wants to work on it full-time, I charge a subscription to pay myself and cover third-party services (I use fal.ai for inference models on the SaaS).
That’s the full picture. Use it, don’t use it—either way, I respect your choice.
Quick update: v231 now live with full stereo support!
– All 8 tracks now output in stereo
– Stereo waveform display
– Stereo VU meters
– Complete stereo pipeline
Download: https://github.com/innermost47/ai-dj/releases/tag/v231
I really like the developer’s response, the fact that the entire code-base is freely available is amazing. GPUs are expensive, writing complex plug-ins is too, not to mention maintenance. The ability to generate new sounds on the fly is interesting, it’s a new form of synthesis, and is not taking anything away from your ability to compose and orchestrate. Kudos.
Thanks Richard!
“New form of synthesis” is exactly how I see it too.
Just like FM brought new timbres in the 80s, or granular
opened new textures in the 2000s, AI-driven sample
generation is another tool in the creative palette.
Not a replacement, an addition.
Appreciate you getting the vision.