Bookmark Saya

arXiv Open Access 2025

Live Music Models

Lyria Team Antoine Caillon Brian McWilliams Cassie Tarakajian Ian Simon +31 lainnya
Lihat Sumber

Abstrak

We introduce a new class of generative models for music called live music models that produce a continuous stream of music in real-time with synchronized user control. We release Magenta RealTime, an open-weights live music model that can be steered using text or audio prompts to control acoustic style. On automatic metrics of music quality, Magenta RealTime outperforms other open-weights music generation models, despite using fewer parameters and offering first-of-its-kind live generation capabilities. We also release Lyria RealTime, an API-based model with extended controls, offering access to our most powerful model with wide prompt coverage. These models demonstrate a new paradigm for AI-assisted music creation that emphasizes human-in-the-loop interaction for live music performance.

Topik & Kata Kunci

cs.SD cs.HC cs.LG

Penulis (36)

Lyria Team

A

Antoine Caillon

B

Brian McWilliams

C

Cassie Tarakajian

I

Ian Simon

I

Ilaria Manco

J

Jesse Engel

N

Noah Constant

Y

Yunpeng Li

T

Timo I. Denk

A

Alberto Lalama

A

Andrea Agostinelli

C

Cheng-Zhi Anna Huang

E

Ethan Manilow

G

George Brower

H

Hakan Erdogan

H

Heidi Lei

I

Itai Rolnick

I

Ivan Grishchenko

M

Manu Orsini

M

Matej Kastelic

M

Mauricio Zuluaga

M

Mauro Verzetti

M

Michael Dooley

O

Ondrej Skopek

R

Rafael Ferrer

S

Savvas Petridis

Z

Zalán Borsos

Ä

Äaron van den Oord

D

Douglas Eck

E

Eli Collins

J

Jason Baldridge

T

Tom Hume

C

Chris Donahue

K

Kehang Han

A

Adam Roberts

Format Sitasi

APA MLA BibTeX
Team, L., Caillon, A., McWilliams, B., Tarakajian, C., Simon, I., Manco, I. et al. (2025). Live Music Models. https://arxiv.org/abs/2508.04651

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓