ACE-Step v1.5 XL SFT

Identifier for the type of task being performed

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

Audio output type.

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

• `MP3`: Compressed audio, smaller file size.
• `WAV`: Uncompressed, high-quality audio.
• `FLAC`: Lossless compression.
• `OGG`: Open-source compressed audio format (Vorbis codec).

Audio encoding settings for controlling the bitrate, number of channels, and sample rate of the generated audio. Only applicable for lossy output formats (MP3 and OGG). When using lossless formats (WAV or FLAC), this parameter must not be provided.

The available sample rates and valid bitrate ranges depend on the output format. For OGG, bitrate limits also vary by the number of channels.

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Determines how the API delivers task results.

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

Common use cases:

• Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
• CDN integration: Upload to content delivery networks for immediate distribution.

// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg

The content data will be sent as the request body to the specified URL when generation is complete.

Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

Include task cost in the response.

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

Audio input (UUID or URL).

Identifier of the model to use for generation.

Text prompt describing elements to include in the generated output.

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

Length of the generated audio track in seconds.

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

Total number of denoising steps. Higher values generally produce more detailed results but take longer.

Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt.

Fraction of steps using the input source instead of generated output.

Beats per minute. If not set, the model decides automatically.

Diffusion ratio where CFG ends (1.0 = last step).

Diffusion ratio where CFG begins (0.0 = first step).

Controls how guidance is applied during generation.

Musical key and scale in '{Note}{Accidental} {Mode}' format (e.g. 'C major', 'F# minor', 'Bb major').

Song lyrics, typically formatted like a lyrics website.

End time in seconds for repaint region. Requires input audio. Values beyond audio duration append new audio.

Start time in seconds for repaint region. Requires input audio. Negative values prepend audio before the start.

Beats per measure. If not set, the model decides automatically.

ISO 639-1 language code for vocals. unknown for instrumental or auto detection.

Manual scheduler configuration for fine-grained control over the diffusion process (sampler, modifiers, etc.).