Agent skill · Backend & API

audioshake-stem-separation

Operate AudioShake's cloud source-separation service (developer.audioshake.ai) to split a recording into stems. Use when a task involves isolating vocals, drums, bass, guitar, piano, keys, strings, or winds from music; separating dialogue / music / effects (DME) for film-TV post-production, localization, and dubbing; splitting a mixed recording into one stem per speaker; lyric transcription or word-level alignment; music detection/identification; or speech denoise/dereverb. Covers the Tasks API job lifecycle (assets, targets, formats, polling vs webhooks, credits, limits), choosing which st

Calesthio43,316★ · +2,384/wk · 2 repos on radarProfile →
claude-codecodexcopilotcursorMIT
Install
npx skills add calesthio/generative-media-skills --skill audioshake-stem-separation --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 22 KB
Bundled scripts: none
Path: skills/providers/source-separation/audioshake-stem-separation/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 112 · +8 this week
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Operates AudioShake's cloud source-separation service to split a recording into stems. It covers driving the developer API, selecting appropriate stem targets for a production task, reviewing stems for bleed and artifacts, and addressing rights, consent, and when to prefer a local open model over the API. It explicitly notes not to generate, synthesize, mix, or master audio and to avoid working with copyright-infringing content without proper rights.

How it works

  • Use the Tasks API to upload or reference the source audio (via url or assetId).
  • Create a task with POST /tasks, listing one or more targets as { "model": "<name>", "formats": ["<fmt>", ...] } (1–20 targets per task).
  • Wait for completion by polling GET /tasks/{id} or via webhooks; each target moves through processingcompleted | error.
  • Download outputs from the output array; presigned URLs expire ~1 hour after task completion.
  • Consider reviewing stems for bleed, artifacts, transient smearing, or phase problems, and repair as described (e.g., add a residual/other target, or reprocess with denoise/dereverb before multi-voice). Ensure responsible handling of rights and privacy.

When to use it

Use when the job requires pulling apart a recording into music stems (vocals, drums, bass, etc.), separating dialogue/music/effects for DME, creating multi-speaker stems, lyric transcription/alignment, or content analysis like music detection.

What it can touch

  • API endpoints: https://api.audioshake.ai with authentication header x-api-key: <key>.
  • Task definitions including assets/assetId, url, targets, and formats.
  • Outputs available via URLs in the output array of the task response.

Caveats

  • Not for generating/synthesizing audio, mixing, or mastering.
  • Outputs are subject to bleed and artifacts; repairs may require additional strategies (residual targets, denoise/dereverb, etc.).
  • Rights and privacy considerations apply: you must have rights to uploaded audio; stems are derivatives; data handling policies may affect confidentiality.
  • Output URLs expire ~1 hour after task completion; store promptly.
From the SKILL.md

# AudioShake stem separation AudioShake is a hosted audio **source-separation** service: it takes one mixed recording and returns isolated component tracks ("stems"). It does not generate, synthesize, mix, or master audio — it decomposes an existing mix. This skill covers driving its developer API, choosing the right separation targets for a production job, judging and repairing the resulting stem

More from generative-media-skills
All skills →
About this skill
What does the audioshake-stem-separation skill do?

Operate AudioShake's cloud source-separation service (developer.audioshake.ai) to split a recording into stems. Use when a task involves isolating vocals, drums, bass, guitar, piano, keys, strings, or winds from music; separating dialogue / music / effects (DME) for film-TV post-production, localization, and dubbing; splitting a mixed recording into one stem per speaker; lyric transcription or word-level alignment; music detection/identification; or speech denoise/dereverb. Covers the Tasks API job lifecycle (assets, targets, formats, polling vs webhooks, credits, limits), choosing which st

How do I install it?

Run `npx skills add calesthio/generative-media-skills --skill audioshake-stem-separation --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going