I'm back from last weeks post and so today I'm releasing a SOTA text-to-sample model built specifically for traditional music production. It may also be the most advanced AI sample generator currently available - open or closed.

An independent developer known as RoyalCities has launched a new AI model that pushes the boundaries of audio generation for music creators. The model is described as a state-of-the-art (SOTA) text-to-sample generator, meaning it can create short, usable audio clips—like drum hits, synth stabs, or melodic loops—directly from a text description. What sets it apart is its specific training and optimization for the needs of 'traditional music production,' suggesting it's fine-tuned on datasets of professional-grade samples across genres like hip-hop, electronic, rock, or pop, rather than general sound effects.

RoyalCities makes a bold claim that this model 'may also be the most advanced AI sample generator currently available - open or closed.' This positions it as a potential competitor to both open-source community projects and proprietary tools from major AI labs. By releasing it openly, the developer is providing producers with a powerful, accessible tool for sound design, enabling rapid prototyping of ideas, overcoming creative blocks, and generating unique samples that might be difficult to source or create manually. The release follows a previous post from the developer, indicating ongoing work in this niche AI audio space.