Stable Audio 3
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909053990469632 |
|---|---|
| author | Evans, Zach Parker, Julian D. Rice, Matthew Carr, CJ Zukowski, Zack Taylor, Josiah Pons, Jordi |
| author_facet | Evans, Zach Parker, Julian D. Rice, Matthew Carr, CJ Zukowski, Zack Taylor, Josiah Pons, Jordi |
| contents | Stable Audio 3 is a family of fast latent diffusion models (small, medium, large) for variable-length audio generation and editing. Since our models can generate several minutes of audio, variable-length generations are key to avoid the cost of producing full-length generations for short sounds. We also support inpainting, enabling targeted audio editing and the continuation of short recordings. Our latent diffusion models operate on top of a novel semantic-acoustic autoencoder that projects audio into a compact latent space, enabling efficient diffusion-based generation while preserving audio fidelity and encouraging semantic structure in the latent. Finally, we run adversarial post-training to both accelerate inference and improve generation quality, reducing the number of inference steps while improving fidelity and prompt adherence. Stable Audio 3 models are trained on licensed and Creative Commons data to generate music and sounds in less than a 2s on an H200 GPU and less than a few seconds on a MacBook Pro M4. We release the weights of small and medium, that can run on consumer-grade hardware, together with their training and inference pipeline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17991 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Stable Audio 3 Evans, Zach Parker, Julian D. Rice, Matthew Carr, CJ Zukowski, Zack Taylor, Josiah Pons, Jordi Sound Artificial Intelligence Stable Audio 3 is a family of fast latent diffusion models (small, medium, large) for variable-length audio generation and editing. Since our models can generate several minutes of audio, variable-length generations are key to avoid the cost of producing full-length generations for short sounds. We also support inpainting, enabling targeted audio editing and the continuation of short recordings. Our latent diffusion models operate on top of a novel semantic-acoustic autoencoder that projects audio into a compact latent space, enabling efficient diffusion-based generation while preserving audio fidelity and encouraging semantic structure in the latent. Finally, we run adversarial post-training to both accelerate inference and improve generation quality, reducing the number of inference steps while improving fidelity and prompt adherence. Stable Audio 3 models are trained on licensed and Creative Commons data to generate music and sounds in less than a 2s on an H200 GPU and less than a few seconds on a MacBook Pro M4. We release the weights of small and medium, that can run on consumer-grade hardware, together with their training and inference pipeline. |
| title | Stable Audio 3 |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2605.17991 |