Separate stems · Demucs

Node catalog Artificial intelligence

On this page

Separate vocals, drums, bass and accompaniment locally.

Usage and specifics

Supply the required audio input or text and provider credential. Text and audio outputs depend on the operation; preserve MIME types when mapping. Demucs runs locally and needs installed dependencies; remote models depend on account access.

Technical type : separate_audio_demucs. Runtime : nodulz.

Credentials and prerequisites

This node defines no dedicated external credential. Remote sources or execution targets may still need their own access credentials.

See the credentials guide if a remote source or execution target requires access.

Parameters

Names below are technical keys. Defaults are not a ready-to-run configuration: complete fields required by your operation. Paths containing [] describe list items; some fields depend on the selected mode.

Parameter	Type	Default	Values / limits
`input`	`string`	`""`	-
`model`	`enum`	`"htdemucs"`	`htdemucs`, `htdemucs_ft`, `mdx_extra`
`stem`	`enum`	`"vocals"`	`all`, `vocals`, `drums`, `bass`, `other`
`device`	`enum`	`"cpu"`	`cpu`, `cuda`
`timeoutSeconds`	`number`	`600`	-; ≥ 1, ≤ 3600

Configuration help

timeoutSeconds Timeout (seconds): Maximum AI request time, within the overall workflow timeout.

Initial configuration

Initial catalog configuration example, to adapt before running. Keep secrets in credentials.

json

{
  "input": "",
  "model": "htdemucs",
  "stem": "vocals",
  "device": "cpu",
  "timeoutSeconds": 600
}

Verification

Test with representative data. Check node output in the inspector and logs, then use editor mapping for downstream fields. A trigger test with a simulated payload does not validate external service delivery.