You're looking at a specific version of this model. Jump to the model overview.

ardianfe /stable-audio-2:b8ff74f1

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
prompt
string
None
negative_prompt
string
None
seconds_start
integer
0
None
seconds_total
integer
8

Max: 90

None
cfg_scale
number
6
None
steps
integer
100
None
seed
integer
-1
None
sampler_type
string
dpmpp-3m-sde
None
sigma_min
number
0.03
None
sigma_max
integer
500
None
init_noise_level
number
1
None
batch_size
integer
1
None
output_format
string (enum)
mp3

Options:

wav, mp3

Output format for generated audio.
song_id
integer
song id to store to GCS

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'title': 'Output', 'type': 'object'}