← All models
Modify a portion of provided audio with lyrics and/or style using ACE-Step
Details
- Accepts
- audio
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. |
| tagsrequired | string | Comma-separated list of genre tags to control the style of the generated audio. Can also be supplied as `prompt`. |
| lyrics | string | Lyrics to be sung in the audio. If not provided or if [inst] or [instrumental] is the content of this field, no lyrics will be sung. Use control structures like [verse], [chorus] and [bridge] to control the structure of the song. |
| end_time | number | end time in seconds for the inpainting process. |
| variance | number | Variance for the inpainting process. Higher values can lead to more diverse results. |
| audio_urlrequired | string | URL of the audio file to be inpainted. |
| scheduler | stringenum: euler, heun | Scheduler to use for the generation process. |
| start_time | number | start time in seconds for the inpainting process. |
| 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. |
| end_time_relative_to | stringenum: start, end | Whether the end time is relative to the start or end of the audio. |
| lyric_guidance_scale | number | Lyric guidance scale for the generation. |
| minimum_guidance_scale | number | Minimum guidance scale for the generation after the decay. |
| start_time_relative_to | stringenum: start, end | Whether the start time is relative to the start or end of the audio. |
| 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. |