You're looking at a specific version of this model. Jump to the model overview.
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
|
lo-fi hip-hop, laid-back groove, warm analog compression, tape warmth
|
Text description of the music to generate
|
| bpm |
integer
|
80
Max: 240 |
Beats per minute. 0 for auto-detection from prompt.
|
| key_scale |
string
|
Am
|
Musical key (e.g. 'Am', 'C Major', 'Dm'). Leave empty for auto.
|
| time_signature |
string
|
4/4
|
Time signature (e.g. '4/4', '3/4'). Leave empty for auto.
|
| duration |
number
|
60
Min: 10 Max: 240 |
Audio duration in seconds
|
| seed |
integer
|
-1
|
Random seed. -1 for random.
|
| inference_steps |
integer
|
16
Min: 4 Max: 50 |
Number of diffusion steps. More steps = higher quality but slower. 8-20 recommended for turbo.
|
| lora_scale |
number
|
0.8
Max: 1 |
LoRA influence strength. Lower values blend more with the base model. 0 disables LoRA.
|
| output_format |
None
|
mp3
|
Output audio format.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}