Give it a melody and it returns a higher-voice harmony, produced by specialized agents.
- Tasks
- Harmonization
- Survey access
- Not stated
Model card
Source-reported facts from the research snapshot. Availability and capabilities are scoped to that observation.
- Input → output
- Melody → Harmony
Findings & evidence
arXiv:2610.38252v1; artifacts observed . Paper version . These dates describe the survey evidence, rather than a fresh model review.
Derived from "A Tutorial on Generative Models for Music Audio: From Text-to-Music to Live Performance" by Mateusz Modrzejewski, Joanna Kurkowska, Dorien Herremans (arXiv 2610.38252v1, https://arxiv.org/abs/2610.38252v1), licensed CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/). Changes: Maru parsed the TeX source into structured records, normalized cell values and added review states. Distributed under CC BY-SA 4.0. No endorsement by the authors is implied. The paper's license does not cover the models, datasets or recordings it discusses. This research adaptation is offered under CC BY-SA 4.0. This does not license the models, datasets or recordings. The paper’s authors have not endorsed this adaptation.