Musical Agent Systems: MACAT and MACataRT

TL;DR

This paper introduces MACAT and MACataRT, two innovative AI-driven musical agent systems designed to support real-time, co-creative music performance and improvisation, emphasizing personalized data and ethical AI practices.

Contribution

The paper presents two novel musical agent systems, MACAT and MACataRT, tailored for autonomous and collaborative music creation with real-time, personalized AI interactions.

Findings

MACAT enables autonomous, agent-led performances with real-time synthesis.

MACataRT facilitates collaborative improvisation through audio mosaicing.

Both systems successfully support personalized, ethical AI in live music contexts.

Abstract

Our research explores the development and application of musical agents, human-in-the-loop generative AI systems designed to support music performance and improvisation within co-creative spaces. We introduce MACAT and MACataRT, two distinct musical agent systems crafted to enhance interactive music-making between human musicians and AI. MACAT is optimized for agent-led performance, employing real-time synthesis and self-listening to shape its output autonomously, while MACataRT provides a flexible environment for collaborative improvisation through audio mosaicing and sequence-based learning. Both systems emphasize training on personalized, small datasets, fostering ethical and transparent AI engagement that respects artistic integrity. This research highlights how interactive, artist-centred generative AI can expand creative possibilities, empowering musicians to explore new forms of artistic expression in real-time, performance-driven and music improvisation contexts.