ryan5453/demucs-test | API reference

don't use this...

Public

27 runs

Run ryan5453/demucs-test with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

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
audio	string		The audio file to separate
model	None	auto	Model to use for separation
format	string	wav	Output audio format, anything supported by FFmpeg
isolate_stem	None	none	Only creates a {stem} and no_{stem} stem/file
shifts	integer	1 Min: 1 Max: 20	Number of random shifts for equivariant stabilization, more increases quality but increases processing time linearly
split	boolean	True	Split audio into chunks to save memory
split_size	integer	Min: 1	Size of each chunk in seconds, smaller values use less GPU memory but process slower
split_overlap	number	0.25 Max: 1	Overlap between split chunks, higher values improve quality at chunk boundaries
clip_mode	None	rescale	Method to prevent audio clipping in output, or None for no clipping prevention

{
  "type": "object",
  "title": "Input",
  "required": [
    "audio"
  ],
  "properties": {
    "audio": {
      "type": "string",
      "title": "Audio",
      "format": "uri",
      "x-order": 0,
      "description": "The audio file to separate"
    },
    "model": {
      "enum": [
        "auto",
        "hdemucs_mmi",
        "htdemucs",
        "htdemucs_ft",
        "htdemucs_6s"
      ],
      "type": "string",
      "title": "model",
      "description": "Model to use for separation",
      "default": "auto",
      "x-order": 1
    },
    "split": {
      "type": "boolean",
      "title": "Split",
      "default": true,
      "x-order": 5,
      "description": "Split audio into chunks to save memory"
    },
    "format": {
      "type": "string",
      "title": "Format",
      "default": "wav",
      "x-order": 2,
      "description": "Output audio format, anything supported by FFmpeg"
    },
    "shifts": {
      "type": "integer",
      "title": "Shifts",
      "default": 1,
      "maximum": 20,
      "minimum": 1,
      "x-order": 4,
      "description": "Number of random shifts for equivariant stabilization, more increases quality but increases processing time linearly"
    },
    "clip_mode": {
      "enum": [
        "none",
        "rescale",
        "clamp",
        "tanh"
      ],
      "type": "string",
      "title": "clip_mode",
      "description": "Method to prevent audio clipping in output, or None for no clipping prevention",
      "default": "rescale",
      "x-order": 8
    },
    "split_size": {
      "type": "integer",
      "title": "Split Size",
      "minimum": 1,
      "x-order": 6,
      "nullable": true,
      "description": "Size of each chunk in seconds, smaller values use less GPU memory but process slower"
    },
    "isolate_stem": {
      "enum": [
        "none",
        "drums",
        "bass",
        "other",
        "vocals",
        "guitar",
        "piano"
      ],
      "type": "string",
      "title": "isolate_stem",
      "description": "Only creates a {stem} and no_{stem} stem/file",
      "default": "none",
      "x-order": 3
    },
    "split_overlap": {
      "type": "number",
      "title": "Split Overlap",
      "default": 0.25,
      "maximum": 1,
      "minimum": 0,
      "x-order": 7,
      "description": "Overlap between split chunks, higher values improve quality at chunk boundaries"
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "object",
  "title": "Output",
  "additionalProperties": {
    "type": "string",
    "format": "uri"
  }
}