Dicy2 is both a package for Max and a plugin for Ableton Live implementing interactive agents using machine-learning to generate musical sequences that can be integrated into musical situations ranging from the production of structured material within a compositional process to the design of autonomous agents for improvised interaction.

Playlist IRCAM Videos Tutorials: Dicy2 generative musical agents

Dicy2 integrates scientific and musical research results accumulated through productions and experiments with Rémi Fox, Steve Lehman, the Orchestre National de Jazz, Alexandros Markeas, Pascal Dusapin, Le Fresnoy - Studio National des Arts Contemporains, Vir Andres Hera, Gaëtan Robillard, Benoît Delbecq, Jozef Dumoulin, Ashley Slater, Hervé Sellin, Rodolphe Burger, Marta Gentilucci… After having evolved research prototypes crystallising the contributions of these various projects for several years, a collaborative work carried out during the year 2022 has led to the finalisation of a release of Dicy2 as a plugin for Ableton Live and a library for Max.

Dicy2 is a library for Max and a device for Ableton Live designed and developed by Jérôme Nika, Augustin Muller,Joakim Borg, and Matthew Ostrowski for Ircam’s Musical Representations team as part of the ANR-DYCI2, ANR-MERCI, ERC-REACH projects directed by Gérard Assayag, and the UPI-CompAI Ircam project. The audio use cases have been designed and developed with Diemo Schwarz and Riccardo Borghesi, and use the MuBu and CataRT environments by Ircam’s ISMM team. Max4Live plugin by Manuel Poletti. Contributions / thanks : Serge Lemouton, Jean Bresson, Thibaut Carpentier, Georges Bloch, Mikhaïl Malt, Axel Chemla–Romeu-Santos, Tristan Carsault, Vincent Cusson, Tommy Davis, Dionysios Papanicolaou, Greg Beller, Markus Noisternig.