HANSY SYNTH OPLA ArpDemo

video upload by gilleslacaud

"HANSY SYNTH OPLA ARPEGIATOR DEMO"

Acids Neurorack - The First Deep AI-based Eurorack Synthesizer

video upload by Acids Team - Ircam

Note Artisan Electronics has a Neurorack module system (4:52 here), however it does not appear to be AI based. There is also this user labeled Eurorack system with "brainwaves/EEG signals as source of modulation (the Neuro portion of it)", but again no AI (there is also soundmachines' BI1brainterface (no AI). (Update: there was also the Hartmann Neuron and Jomox Neuronium, both based on neuronal networks.) As for AI applied to synthesis in general, you can find posts mentioning artificial intelligence here. I believe the earliest reference would be John Chowning in 1964: "Following military service in a Navy band and university studies at Wittenberg University, Chowning, aided by Max Mathews of Bell Telephone Laboratories and David Poole of Stanford, set up a computer music program using the computer system of Stanford University's Artificial Intelligence Laboratory in 1964."

Description for the above video:
"The Neurorack is the first ever AI-based real-time synthesizer, which comes in many formats and more specifically in the Eurorack format. The current prototype relies on the Jetson Nano. The goal of this project is to design the next generation of music instrument, providing a new tool for musician while enhancing the musician's creativity. It proposes a novel approach to think and compose music. We deeply think that AI can be used to achieve this quest. The Eurorack hardware and software have been developed by our team, with equal contributions from Ninon Devis, Philippe Esling and Martin Vert."

https://github.com/ninon-io/Impact-Synth-Hardware/
http://acids.ircam.fr/neurorack/

More information

Motivations
Deep learning models have provided extremely successful methods in most application fields, by enabling unprecedented accuracy in various tasks, including audio generation. However, the consistently overlooked downside of deep models is their massive complexity and tremendous computation cost. In the context of music creation and composition, model reduction becomes eminently important to provide these systems to users in real-time settings and on dedicated lightweight embedded hardware, which are particularly pervasive in the audio generation domain. Hence, in order to design a stand alone and real time instrument, we first need to craft an extremely lightweight model in terms of computation and memory footprint. To make this task even more easier, we relied on the Nvidia Jetson Nano which is a nanocomputer containing 128-core GPUs (graphical unit processors) and 4 CPUs. The compression problem is the core of the PhD topic of Ninon Devis and a full description can be found here.

Targets of our instrument
We designed our instrument so that it follows several aspects that we found crucial:

Musical: the generative model we choose is particularly interesting as it produces sounds that are impossible to synthesize without using samples.

Controllable: the interface was relevantly chosen, being handy and easy to manipulate.

Real-time: the hardware behaves as traditional instrument and is as reactive.

Stand alone: it is playable without any computer.

Model Description
We set our sights on the generation of impacts as they are very complex sounds to reproduce and almost impossible to tweak. Our model allows to generate a large variety of impacts, and enables the possibility to play, craft and merge them. The sound is generated from the distribution of 7 descriptors that can be adjusted (Loudness - Percussivity - Noisiness - Tone-like - Richness - Brightness - Pitch).

Interface
One of the biggest advantage of our module is that it can interact with other synthesizer. Following the classical conventions of modular synthesizers, our instrument can be controlled using CVs (control voltages) or gates. The main gate triggers the generation of the chosen impact. Then it is possible to modify the amount of Richness and Noisiness with two of the CVs. A second impact can be chosen to be "merge" with the main impact: we will call this operation the interpolation between two impacts. Their amounts of descriptors are melt to give an hybrid impact. The "degree of merging" is controlled by the third CV, whereas the second gate triggers the interpolation.

DX5 Playing Alphaville "Forever Young" (improved take)

video upload by DX5

Previous version posted here.

"*** I don't use to upload the same cover within 24 hours but I was not too happy with the "Vocoder-ish" intro I did for the previous video. Never too late to improve. ***
"Forever Young" Instrumental cover. I tweaked the JX-8P filter live for the song intro which sounded quite accurate (I guess it was originally done on a Jupiter 8 and the JX-8P did the job well).
The vocoder style effect in the intro was finally made with the Access Virus TI Snow, sampled into the Emax (they might have used the PPG Wave for it on the original recording).
Gear used (L to R):
Roland JP8000,
Roland JX-8P,
Emu Emax.
Backtrack recorded on its entirely, track by track, by me using Pro Tools. No original audio was involved. Also used:
Access Virus TI Snow
Simmons SDS 8 for a couple of effects/drums.
Original song composed by Marian Gold, Bernard Lloyd, Frank Mertens.
Performed here by DX5 Jose Maria Bara."

V.A.I. 58 - Welson Syntex / CRB 709 / Böhm Solist 78 / Emthree PFV3

video upload by Vintage Audio Institute Italia

This appears to be the first post to feature the CRB 709. You can search for gear via the search box on the top right of the site.

"All great instruments that have been featured before, the Böhm Solist 78 is such a great arrangement / songwriting tool, a auto accompaniment machine with a very distinct thin sound form the early 70s, built in Germany.
The rest of the gear is Italian, the Welson Syntex is a hidden gem of Italian synths, the ultra rare CRB 709 String machine is quite like the Elka Rhapsody 49 in timbre but still a bit different, it came equipped with a 5 inch power cable - thanks for that mod, previous owner. This song will be released later this spring, so all rights are reserved."

Signal Sounds Jamuary #1

video upload by Signal Sounds

https://www.signalsounds.com/

Chill

video upload by Todd Barton

"a little chill exploration . . ."

https://www.patreon.com/synthtodd

Compact techno setup with Novation Circuit Tracks, MAM MB33 and Korg Volca Kick

video upload by motobor

"First video for 2022. Took some time off with the videos around the christmas and now getting back on the track."

Novation MINI NOVA Demo & Review

video upload by musictrackjp

DEMO by Katsunori UJIIE.

Quick Tips : Fun Filter Sweeps for Synthesizers !

video upload by Perfect Circuit

"Read our in-depth Signal article here : https://bit.ly/3EZFI1e

Join our pal Wes for a tubular time with some of his favorite filter sweeps!

Filter sweeps are an iconic sound in electronic music, and they come in tons of variations and different styles, Check out Signal for the full article with all the hot details!"

Tropical Additive Synthesis Introduction and tutorial on MaxMSP

video upload by Giorgio Sancristoforo

"In this video I present the Tropical Additive Synthesis that I and Dr. Cristiano Bocci have developed in 2018 as a new form of sound synthesis that uses Tropical Algebra.

We hope that developers and builders will implement tropical additive synthesis both in software and hardware for the future generations.
We don't ask anything but a credit as creators of the synthesis algorithm which we call Trop(x[n])."