Stable Audio Open

TL;DR

This paper introduces an open-weights text-to-audio model trained on Creative Commons data, demonstrating competitive performance and high-quality stereo sound synthesis at 44.1kHz, facilitating community access and further research.

Contribution

It presents a new open-weights text-to-audio model architecture and training process, enabling accessible high-quality audio generation for artists and researchers.

Findings

Competitive performance across various metrics

High-quality stereo sound synthesis at 44.1kHz

Model is openly available for community use

Abstract

Open generative models are vitally important for the community, allowing for fine-tunes and serving as baselines when presenting new models. However, most current text-to-audio models are private and not accessible for artists and researchers to build upon. Here we describe the architecture and training process of a new open-weights text-to-audio model trained with Creative Commons data. Our evaluation shows that the model's performance is competitive with the state-of-the-art across various metrics. Notably, the reported FDopenl3 results (measuring the realism of the generations) showcase its potential for high-quality stereo sound synthesis at 44.1kHz.