More audio-tools for you!
Hey all!
I'll be doing a livestream later today to show and explain all these and the ones from the previous post but for now I just want you all to have them and play around with them :)
You just run them in your browser, all of these need you to import a sample by the way!
Maybe some of these are going to turn into actual plugins with the help of some real coders and graphic designers! \^-^/
Love you all!
Val
Comments (24)
Variant looks fucking killer, reminds me of a beefed up super slicer, awesome work man gone try them out now
I'd prefer you didn't use GEN AI or AI at all
<3
THANK YOU <3
LOVE YOU M8
Brother, I would love to help develop your plugins. I'm a software developer
Variant is awesome. thank so much val, I learned a lot from you since 2014.
So sick! I’ve developed some plugins in the video space. Could definitely transition to building VST’s if you ever wanted to develop these fully!
Loving Variant so far. Thank you for everything always Val!
Scrambler - also awesome 👍
Variant is awesome 👍
Can we get the combfield too?
and can you make it as an fx unit too thank you
Dude you are a godsend.
I'm glad these tools enable you to make interesting prototypes, but if you're still open for feedback from the community, there's a lot of nuance and hidden cost to AI usage I'd like to explore. That being said, I'm going to repost my comment from your last tools post because I think I made it too late to be seen: TLDR: A lot of us have a clear line in the sand in using AI to generate music or visual art. Why don’t we have the same for other AI use? A lot of the same qualms folks have with AIs like Suno apply to all other AIs. I challenge everyone to find that line in the sand for themselves when it comes to AI coding. I know there’s been a variety of opinions expressed here. I’ll speak to my experience as an audio dev. Yes, I understand the accessibility, convenience, possibilities vibe coding provides, but I want to provide pushback on the cost. I see a lot of people assuming the ends justify the means, but never really investigate for themselves where the line in the sand is with their personal use. There’s the obvious - the environmental cost and justification for building data centers. There’s others - this tooling is only able to work because it was trained in the work of countless developers’ code without their consent, credit, or compensation. There’s also the potential threat of replacement of human career paths. Rampant usage of AI contributes to the overwhelming manufactured consent to these AI companies to continue their practices unchallenged - building data centers, scraping the internet, etc. I’m not trying to assign blame or shame, but want to make these tradeoffs clear. Yes, AI has been integrated into a lot of dev’s workflows. Yes, it’s a service that can be used to increase productivity. However, it’s used in varying degrees - there’s a difference between vibe coding and more intentional use that most devs use. Vibe coding leads to inefficiencies, bad architecture, and spaghetti code which is not maintainable. In my experience, AI is helpful with documentation, writing tests, and changes small in scope. Heavy reliance on it results in the issues I outlined above as well as deskilling. For that reason, if you had provided me the source code for these prototypes to port into JUCE or whatever, I don’t know how much I’d actually read and reuse. All that being said, me, I’d much prefer something built in Max/plugdata/phaseplant/bitwig/ableton racks/etc. however, that’s just me. All in all, I just challenge everyone to approach AI usage with the costs in mind and determine what level and type of usage is acceptable given these costs.
My opinion: I’m not cool with your usage of AI here. I get the function it provides, but there are alternatives that don’t have the same baggage.
These are awesome, as it happens I've just finished the MVP of my full Mixing and Mastering suite using Spec-Driven Development in Claude Code (Think along the lines of Neutron and Ozone). I also created a standalone sample/plugin/user library manager with click-and-drag to and from Live plus a load of other bells and whistles like text-to-speech synthesis, BPM and key matching of samples so they can be previewed exactly as they'd sound in your currently open Live set, built-in browser tabs for Splice, Loopcloud, sample focus and an editor so you can add your own, video wallpaper, plugin pictures in the list so it isn't just text. I'll be putting them on GitHub for free when I'm happy with them if anyone's interested.
VR you gotta start making some IDM breakcore stuff with all this experimental stuff you’re doin
sick! do you most drive with sonnet or opus? any skills/mcp/cli's that were helpful in the design process?
opus 4.6 is fairly impressive for DSP work, helps if you save the notes per build to create dataset for agent to refernce to familiarize claude with DSP work and it does a fairly solid job.
You can build it into VST3 using claude (Free version works) by using JUCE and XCODE to build the plugin, then you can post the build on github (private or public) and github will compile and create the vst so you can share and such
What about the whole authentication thingy on Mac OS where you have to manually “validate” the file so your Mac doesn’t think it’s a virus?
Can make em into vst's using JUCE < ?
Maybe in the future! A lot of these aren’t really “playable” and more like sample/loop generators but if any become full plugins I’d get some real people involved since these are just vibe-coded prototypes :)