← All models
Generate music from a simple prompt using ACE-Step
Details
- Accepts
- text
Pricing
- Price
- 0.025 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Random seed for reproducibility. If not provided, a random seed will be used. |
| promptrequired | string | Prompt to control the style of the generated audio. This will be used to generate tags and lyrics. |
| duration | number | The duration of the generated audio in seconds. |
| scheduler | stringenum: euler, heun | Scheduler to use for the generation process. |
| instrumental | boolean | Whether to generate an instrumental version of the audio. |
| guidance_type | stringenum: cfg, apg, cfg_star | Type of CFG to use for the generation process. |
| guidance_scale | number | Guidance scale for the generation. |
| number_of_steps | integer | Number of steps to generate the audio. |
| granularity_scale | integer | Granularity scale for the generation process. Higher values can reduce artifacts. |
| guidance_interval | number | Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps) |
| tag_guidance_scale | number | Tag guidance scale for the generation. |
| lyric_guidance_scale | number | Lyric guidance scale for the generation. |
| minimum_guidance_scale | number | Minimum guidance scale for the generation after the decay. |
| guidance_interval_decay | number | Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The random seed used for the generation process. |
| tags | string | The genre tags used in the generation process. |
| audio | — | The generated audio file. |
| lyrics | string | The lyrics used in the generation process. |