You're looking at a specific version of this model. Jump to the model overview.
fishaudio /ace-step-1.5:6c68306b
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
|
upbeat electronic dance music with heavy bass and synth leads
|
Text description of the music to generate. Include genre, mood, instruments, style.
|
| lyrics |
string
|
[Instrumental]
|
Lyrics for the song. Use '[Instrumental]' for instrumental tracks. Supports 50+ languages.
|
| duration |
number
|
30
Min: 10 Max: 240 |
Duration of the generated audio in seconds.
|
| bpm |
integer
|
0
Max: 300 |
Beats per minute. Set to 0 for auto-detection by the LM.
|
| key_scale |
string
|
|
Musical key and scale (e.g. 'C major', 'A minor'). Leave empty for auto.
|
| time_signature |
None
|
4/4
|
Time signature.
|
| inference_steps |
integer
|
8
Min: 1 Max: 20 |
Number of denoising steps. Turbo model works best with 4-8 steps.
|
| guidance_scale |
number
|
1
Min: 1 Max: 15 |
Classifier-free guidance scale. Higher values follow the prompt more closely. Turbo model ignores this.
|
| shift |
number
|
3
Min: 1 Max: 5 |
Timestep shift factor. Recommended 3.0 for turbo model.
|
| seed |
integer
|
-1
|
Random seed for reproducibility. Use -1 for random.
|
| thinking |
boolean
|
True
|
Enable LM chain-of-thought reasoning for better metadata generation.
|
| batch_size |
integer
|
1
Min: 1 Max: 4 |
Number of songs to generate in parallel.
|
| audio_format |
None
|
mp3
|
Output audio format.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}