Handmade AI Music
Authentic MIDI generation powered by Handmade AI, proprietary human datasets, and patented cross-ontology intelligence.
"We are not building a music generator.
We are building a digital luthier—
a maker of fine tools for fine artists."
MusiCo Founding Philosophy · Handmade AI · Local First · Human Data
MusiCo operates at the intersection of musical craftsmanship and algorithmic precision. We reject the black-box approach to AI music generation—instead building transparent, human-centred systems where every creative decision is traceable, intentional, and ethically grounded.
Our methodology is rooted in Small Data, Deep Intelligence: curated datasets from master composers, not mass-scraped internet content. We believe AI should amplify human artistry, not replace it.
Local AI Edge
Run high-performance music generation entirely on your hardware. No latency, total privacy, zero cloud dependency.
Human-First Datasets
Our models train exclusively on premium, proprietary datasets composed by human musicians. No scraping, ever.
Media2Music (Patented)
Our patented cross-ontology technology translates visual and emotional metadata into perfect musical structures.
MusiCo's engine was designed from the ground up by people who understand both music theory and machine learning. The result is an AI that reasons about musical structure rather than mimicking statistical patterns from an opaque corpus.
01 — Patented
Standard AI guesses. MusiCo knows. Our patented technology bridges data domains — linking visual narratives to musical theory. The Media2Music pipeline ensures music evolves with your story, not merely behind it.
Patented Technology02 — Resolution
We generate high-fidelity MIDI, not flat audio. Total control: swap instruments, tweak velocities, rearrange notes. Direct DAW integration with the nuance of human performance.
03 — Philosophy
Small Data, Deep Intelligence. Curated datasets from master composers teach our AI the intent behind the notes — music that feels intentional, not incidental.
04 — Integration
Generated MIDI drops directly into Logic, Ableton, Pro Tools, Reaper. No proprietary lock-in, no format conversion headaches. Your creative environment, amplified.
Our iOS apps are both innovative musical tools and showcases of MusiCo's generative technology — provided in beta to gather feedback for further development. Technology is protected under IP rights; the music produced is not copyrightable.
Wellness · iOS
Personalised orchestral soundscapes for mindfulness, focus, and restoration. Adaptive music that responds to your mental state — neuroscience meets composition.
Fitness · iOS
Create the ultimate workout soundtrack with an app that generates music in real-time sync with your body's movement. Bespoke beats for bespoke performance.
Performance · iOS
Control MusiCo's generative AI with intuitive gestures for live performances that are never twice the same. Real-time, expressive, and endlessly fresh.
Bare-bones UI preliminary release. Free to use. No implied license granted upon download. Available via the MusiCo website.
Bare-bones UI preliminary release. Free to use. No implied license granted upon download. Request access via the MusiCo website.
A suite of purpose-built instruments for composers, media creators, game developers, and wellbeing practitioners.
Core Platform
The flagship Media2Music engine. Feed it video, image, or emotional metadata — receive perfectly structured MIDI that reflects the soul of your content.
Open Demo Portal →Generation
Generative loop construction powered by artisanal MIDI models. Evolving, non-repetitive loops ideal for ambient scoring, game audio, and installation work.
Open GenLooper →Performance
Real-time AI music generation for live performance. Low-latency local processing — no internet dependency, no stage failures. Responsive musical accompaniment.
See LiveAI →Mobile · Wellness
Personalised orchestral soundscapes for mindfulness, focus, and restoration. Adaptive music that responds to your mental state — neuroscience meets composition.
Visit mindkestra.com →Research · AI
Human-AI Creative Understanding — our research framework and patented protocol for quantifying musical novelty and evaluating creative AI output rigorously.
Visit novatrackprotocol.com →Archive · Audio
Historical generative compositions, early experiments, and demo recordings from MusiCo's development journey — available to stream freely on SoundCloud.
Listen on SoundCloud →MusiCo participates in a broader ecosystem of technology, law, and open-source intelligence. Our partnerships reflect our commitment to ethical AI, legal compliance, and open collaboration.
Ethics · Law · AI Act · GDPR
Our strategic partner for Ethical AI governance, AI Act compliance, and GDPR alignment. AssistiveLawTech provides the legal and regulatory intelligence that ensures every MusiCo system is designed not just to perform, but to comply — transparently, rigorously, and by design.
Together we are building frameworks where AI creativity and legal accountability coexist without compromise.
Visit assistivelawtech.com →Open Source · LLM · SLM · Integration
MusiCo actively participates in the SuperAI Studio open-source community — contributing to and integrating state-of-the-art LLM and SLM (Small Language Model) architectures into our music generation pipeline.
This collaboration keeps MusiCo at the frontier of local, open, and efficient AI — aligned with our principle that the best AI should be accessible, transparent, and not dependent on closed infrastructure.
Visit superaistudio.com →Academic Research Collaborations
Machine Learning · Generative MIDI · UNIFI · Ongoing
An ongoing research collaboration spanning nearly a decade of generative MIDI development, advancing from early rhythm models to the current state of the art.
2017 — Origin
EDM Drum Pattern Generation
Early explorations of generative models for EDM drum patterns, establishing the core idea of learning structured latent spaces from which novel musical material could be sampled and interpolated.
Workshop Paper →2018 — Formalisation
VAE/GAN Genre Interpolation
A VAE/GAN-based system generating drum patterns with smooth interpolations between genres — embedding a DJ-like transitional intelligence into a generative model, evaluated by real EDM practitioners.
arXiv Paper →2020 — ISMIR
CONLON
Three simultaneous advances: a lossless pianoroll-like data format; Wasserstein autoencoders as the generative backbone; and latent-space trajectory generation as a widest-path problem — preventing abrupt transitions. Introduced musician-curated datasets ASF-4 and HP-10, opening the door to personalised generators.
CONLON Paper (ISMIR) →April 2026 — Forthcoming Publication
From Latent Trajectories to Diffusion: The Next Generation
The forthcoming paper — with Frasconi and Tibo as leading scientists — replaces the autoencoder latent-space interpolation paradigm with diffusion models. This shift from trajectory-in-latent-space to iterative denoising in the data space offers richer modelling of the full MIDI distribution, better handling of polyphonic multi-instrument structure, and more controllable conditioning across style, genre, and harmonic context. CONLON solved the data representation and latent traversal problems; diffusion solves generative fidelity and diversity.
IP · Novelty Measurement · Protocol · Innovation
MusiCo's proprietary framework for quantifying musical novelty and evaluating creative AI output — now formalised as an independent protocol. NovaTrack provides a rigorous, auditable standard for measuring originality in generative music, bridging intellectual property law and algorithmic creativity.
The protocol underpins MusiCo's HAICU research initiative and offers a foundation for creators, labels, and AI developers seeking defensible, transparent novelty benchmarks.
Visit novatrackprotocol.com →Urban Mobility · Assistive Tech · Multimedia · Montreal Polytechnic · Ongoing
An ongoing interdisciplinary collaboration applying MusiCo's core technology building blocks beyond music — into advanced simulation strategies for assistive urban mobility. The project develops adaptive multimedia storytelling systems, derived from MusiCo's generative and cross-ontology engine, to enhance accessible navigation and wayfinding experiences in complex urban environments.
This collaboration demonstrates the breadth of MusiCo's underlying architecture: the same technology that maps visual narratives to music can map urban contexts to adaptive, assistive media experiences — a direct extension of the Media2Music paradigm into the social and physical world.
In an era of data harvesting, MusiCo stands for the Local AI movement. Your creative work belongs to you — not to a server farm, not to a training corpus, and not to a cloud provider's terms of service.
On-Premise Power
Process complex generative tasks entirely without an internet connection. Full capability, offline, on your hardware of choice.
Data Sovereignty
Your compositions and media assets never touch our servers. What you create is yours — completely, legally, permanently.
AI Act & GDPR Aligned
In collaboration with AssistiveLawTech, MusiCo's architecture is designed for full compliance with the EU AI Act and GDPR — privacy and ethics baked in from day one, not bolted on after.
Ethical Training Data
Our models were never trained on your work without consent. Every dataset is licensed, human-composed, and fully documented. Transparency is a foundation, not a feature.
MusiCo was founded on the belief that AI should be a digital luthier — a maker of fine tools for fine artists. We reject the "one-click" commodification of music. Instead, we provide a sophisticated framework where Human Composition and Algorithmic Precision coexist.
"We are the architects of Handmade AI MUSIC: ethically sourced, technically superior, and artistically driven."
Our team unites composers, music theorists, and machine learning researchers under one roof — a rare combination that produces tools no pure-technology company could build. Every model we ship has been listened to, critiqued, and refined by people who have spent decades studying what makes music move people.
We are not anti-AI. We are pro-craft. The distinction matters enormously.
A rare convergence of composers, engineers, educators, and strategists united by a single conviction: that AI music should be made by people who love music.
Founder & CEO
Lorenzo Brusci
CTO
Stefano Imperiale
CSO
Alessandro Tibo
COO
Andrea Marinelli
CFO & Legal Affairs
Ferdinando Manenti
Technology Integration & AI Usability
Nimrod Adar
MusicFit Division Manager
Wojtek Friediger
Chief Educational Advisor & Co-founder
Simone Conforti
Educational Advisor & Co-founder
Valentijn Borghuis
IP & Blockchain Strategist
Federico Podavini
General Enquiries
info@musi-co.comPress & Media
press@musi-co.comJournalists, partners, and collaborators can access our full media repository — audio samples, visual assets, technical documentation, and press releases. For interviews and partnership enquiries, use the contact details below.
Demo Portal
All In 2 Music
Full interactive demo suite for all MusiCo platforms and services
Audio Archive
SoundCloud
Historical generative compositions, demos, and early MusiCo recordings
Editorial
Blog & Research Notes
Technical writing, industry commentary, and research updates
Contact
Press Enquiries
Interviews, partnerships, speaking engagements, and collaborations
The original LiveAI system — our first public demonstration of real-time generative music in a live performance context. This archive documents the journey from proof-of-concept to production platform.
LiveAI v1 — Proof of Concept
First public demonstration of real-time MIDI generation in live performance
LiveAI v2 — Ensemble Mode
Multi-instrument real-time generation, sub-50ms latency on local hardware
LiveAI — Cross-Ontology Integration
First deployment of patented Media2Music pipeline in live context
LiveAI — Production Platform
Merged into the MusiCo Services suite; standalone system deprecated
Preliminary release • Free to use
VST Plugin • Mac
Preliminary release • Free to use
VST Plugin • Mac
