aodianyun/demucs | API reference

Public

5 runs

Run aodianyun/demucs 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		Upload the file to be processed here.
model	None	htdemucs	Choose the demucs audio that proccesses your audio. The readme has more information on what to choose.
stem	None	none	If you just want to isolate one stem, you can choose it here.
output_format	None	mp3	Choose the audio format you would like the result to be returned in.
mp3_bitrate	integer	320	Choose the bitrate for the MP3 output. Higher is better quality but larger file size. If MP3 is not selected as the output type, this has no effect.
mp3_preset	None	2	Choose the preset for the MP3 output. Higher is faster but worse quality. If MP3 is not selected as the output type, this has no effect.
wav_format	None	int24	Choose format for the WAV output. If WAV is not selected as the output type, this has no effect.
clip_mode	None	rescale	Choose the strategy for avoiding clipping. Rescale will rescale entire signal if necessary or clamp will allow hard clipping.
shifts	integer	1	Choose the amount random shifts for equivariant stabilization. This performs multiple predictions with random shifts of the input and averages them, which makes it x times slower.
overlap	number	0.25	Choose the amount of overlap between prediction windows.
split	boolean	True	Choose whether or not the audio should be split into chunks.
segment	integer	0	Choose the segment length to use for separation.
jobs	integer	0	Choose the number of parallel jobs to use for separation.

{
  "type": "object",
  "title": "Input",
  "required": [
    "audio"
  ],
  "properties": {
    "jobs": {
      "type": "integer",
      "title": "Jobs",
      "default": 0,
      "x-order": 12,
      "description": "Choose the number of parallel jobs to use for separation."
    },
    "stem": {
      "enum": [
        "none",
        "drums",
        "bass",
        "other",
        "vocals",
        "guitar",
        "piano"
      ],
      "type": "string",
      "title": "stem",
      "description": "If you just want to isolate one stem, you can choose it here.",
      "default": "none",
      "x-order": 2
    },
    "audio": {
      "type": "string",
      "title": "Audio",
      "format": "uri",
      "x-order": 0,
      "description": "Upload the file to be processed here."
    },
    "model": {
      "enum": [
        "htdemucs",
        "htdemucs_ft"
      ],
      "type": "string",
      "title": "model",
      "description": "Choose the demucs audio that proccesses your audio. The readme has more information on what to choose.",
      "default": "htdemucs",
      "x-order": 1
    },
    "split": {
      "type": "boolean",
      "title": "Split",
      "default": true,
      "x-order": 10,
      "description": "Choose whether or not the audio should be split into chunks."
    },
    "shifts": {
      "type": "integer",
      "title": "Shifts",
      "default": 1,
      "x-order": 8,
      "description": "Choose the amount random shifts for equivariant stabilization. This performs multiple predictions with random shifts of the input and averages them, which makes it x times slower."
    },
    "overlap": {
      "type": "number",
      "title": "Overlap",
      "default": 0.25,
      "x-order": 9,
      "description": "Choose the amount of overlap between prediction windows."
    },
    "segment": {
      "type": "integer",
      "title": "Segment",
      "default": 0,
      "x-order": 11,
      "description": "Choose the segment length to use for separation."
    },
    "clip_mode": {
      "enum": [
        "rescale",
        "clamp",
        "none"
      ],
      "type": "string",
      "title": "clip_mode",
      "description": "Choose the strategy for avoiding clipping. Rescale will rescale entire signal if necessary or clamp will allow hard clipping.",
      "default": "rescale",
      "x-order": 7
    },
    "mp3_preset": {
      "enum": [
        2,
        3,
        4,
        5,
        6,
        7
      ],
      "type": "integer",
      "title": "mp3_preset",
      "description": "Choose the preset for the MP3 output. Higher is faster but worse quality. If MP3 is not selected as the output type, this has no effect.",
      "default": 2,
      "x-order": 5
    },
    "wav_format": {
      "enum": [
        "int16",
        "int24",
        "float32"
      ],
      "type": "string",
      "title": "wav_format",
      "description": "Choose format for the WAV output. If WAV is not selected as the output type, this has no effect.",
      "default": "int24",
      "x-order": 6
    },
    "mp3_bitrate": {
      "type": "integer",
      "title": "Mp3 Bitrate",
      "default": 320,
      "x-order": 4,
      "description": "Choose the bitrate for the MP3 output. Higher is better quality but larger file size. If MP3 is not selected as the output type, this has no effect."
    },
    "output_format": {
      "enum": [
        "mp3",
        "flac",
        "wav"
      ],
      "type": "string",
      "title": "output_format",
      "description": "Choose the audio format you would like the result to be returned in.",
      "default": "mp3",
      "x-order": 3
    }
  }
}

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"
  }
}