Recent years have seen the rapid development of large generative models for text; however, much less research has explored the connection between text and another "language" of communication -- music. Music, much like text, can convey emotions, stories, and ideas, and has its own unique structure and syntax. In our work, we bridge text and music via a text-to-music generation model that is highly efficient, expressive, and can handle long-term structure. Specifically, we develop Mo\^usai, a cascading two-stage latent diffusion model that can generate multiple minutes of high-quality stereo music at 48kHz from textual descriptions. Moreover, our model features high efficiency, which enables real-time inference on a single consumer GPU with a reasonable speed. Through experiments and property analyses, we show our model's competence over a variety of criteria compared with existing music generation models. Lastly, to promote the open-source culture, we provide a collection of open-source libraries with the hope of facilitating future work in the field. We open-source the following: Codes: https://github.com/archinetai/audio-diffusion-pytorch; music samples for this paper: http://bit.ly/44ozWDH; all music samples for all models: https://bit.ly/audio-diffusion.

翻译：近年来，面向文本的大型生成模型取得了快速发展，但探索文本与另一“语言”沟通媒介——音乐之间联系的研究却相对较少。音乐与文本相似，能够传递情感、叙事和思想，并具有独特的结构和句法。在本研究中，我们通过一种高效、富有表现力且能处理长期结构的文本到音乐生成模型，将文本与音乐联系起来。具体而言，我们开发了Moûsai，一种级联式两阶段潜在扩散模型，能够从文本描述生成数分钟长、48kHz采样率的高质量立体声音乐。此外，该模型具有高效性，可在单块消费级GPU上以合理速度实现实时推理。通过实验与性质分析，我们证明了该模型在多项指标上优于现有音乐生成模型。最后，为推广开源文化，我们提供了一系列开源库，以期推动该领域的后续研究。我们开源了以下内容：代码：https://github.com/archinetai/audio-diffusion-pytorch；本文音乐样本：http://bit.ly/44ozWDH；所有模型的完整音乐样本：https://bit.ly/audio-diffusion。