Live Music Models
This enables AI-assisted music creation with human-in-the-loop interaction for live performance, addressing a domain-specific need for musicians and creators.
The authors tackled the problem of real-time, controllable music generation by introducing live music models that produce continuous music streams with synchronized user control. They released Magenta RealTime, which outperforms other open-weights models on music quality metrics despite using fewer parameters and offering live generation capabilities.
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.