cinemasetfree
← Back to all generators
stability-ai/stable-audio-2.5
OfficialView on Replicate →
Generate high-quality music and sound from text prompts
Capabilities
Seed
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
prompt* | string | Text prompt describing the desired audio | — | — |
cfg_scale | number | Classifier-free guidance scale (higher = more prompt adherence) | 1 | min: 1, max: 25 |
duration | integer | Duration of generated audio in seconds | 190 | min: 1, max: 190 |
seed | integer | Random seed for reproducible results. Leave blank for random seed. | — | — |
steps | integer | Number of diffusion steps (higher = better quality but slower) | 8 | min: 4, max: 8 |
promptrequiredstringText prompt describing the desired audio
cfg_scalenumberClassifier-free guidance scale (higher = more prompt adherence)
Default:
1min: 1, max: 25durationintegerDuration of generated audio in seconds
Default:
190min: 1, max: 190seedintegerRandom seed for reproducible results. Leave blank for random seed.
stepsintegerNumber of diffusion steps (higher = better quality but slower)
Default:
8min: 4, max: 8Version:
a61ac8edbb27Updated: 8/1/202681.2K runs