Stable Audio Open
Stable Audio Open is Stability AI's open text-to-audio model for sound effects, samples and production elements, generating up to 47 seconds of 44.1kHz stereo audio from a prompt. Its 1.21B parameters were trained only on Creative Commons audio from Freesound and the Free Music Archive, and it can be fine-tuned on a custom sample library locally.
- Type
- Audio
- Weights
- Closed
- Downloads
- 2k
- Likes
- 1.6k
- Pipeline
- text to audio
- License
- other
Model hub
stabilityai/stable-audio-open-1.0
- Repo
- stabilityai/stable-audio-open-1.0
- Library
- stable-audio-tools
- Access
- Gated
Technical tags and languages
Papers
1
More from Stability AI
11
-
7 DreamShaper
Image
DreamShaper 7 is a versatile SD checkpoint that balances realism and illustration for all purpose concepting.
-
18 DL
Absolute Reality 1.6
Image
Absolute Reality 1.6 is a photoreal model tuned for natural skin, believable materials, and grounded lighting.
-
AlbedoBaseXL (SDXL)
Image
AlbedoBaseXL is a neutral SDXL foundation checkpoint favored for fine tuning and on brand image generation.
-
DeepFloyd IF
Image
AI model by Stability AI
-
SDXL 1.0
Image
AI model by Stability AI
-
1M DL
SDXL Turbo
Multimodal
AI model by Stability AI
-
99k DL
Stable Audio 3 Medium
Multimodal
Stable Audio 3 Medium is Stability AI’s 2B text-to-audio diffusion model for higher-capacity music, sound-eff…
-
16k DL
Stable Audio 3 Small Music
Multimodal
Stable Audio 3 Small Music is Stability AI’s 0.6B text-to-audio diffusion model for fast variable-length musi…
About Stability AI
1
We’ll help you make it like nobody’s business. No creative challenge too big, no timeline too tight. Get to production with Stability AI, your enterprise-ready creative partner.