CodexPluginStats
← Plugin catalog
Creativity

StemConsole

Dan Murtagh v1.0.0

Split, mix and practise music

Create a free account to save this plugin.

Competitor profile

Developer declarations; not independently tested. Listing last checked Nov 4, 2026. Package observed Nov 3, 2026.

Declared capabilities

  • Separate audio into stems
  • Make backing tracks
  • Mix, loop and practise

Cost & access

Nothing is sold inside ChatGPT. Splits use the connected account's existing plan, allowance or credits. Unavailable entitlements are explained without an upgrade or checkout flow.

Declared limitations · 3
  • A streaming-service page is not a supported direct audio source.
  • An ambiguous permanent deletion must not choose an arbitrary library item.
  • The plugin cannot access another account private library without authorization.
Onboarding example
Remove the vocals from my recording so I can sing along.

View package source →

Description

From the marketplace listing

Turn your recording into a backing track you can practise with inside ChatGPT. StemConsole separates a song into vocals, drums, bass and other, or adds guitar and piano with Full Separation, using your existing StemConsole account and allowance. Attach an audio file or provide a supported audio-file link. When processing finishes, mix and practise with the stems directly in ChatGPT: mute or solo parts, balance the mix, loop a section, find the key and BPM, and export a mix, stems, a MIDI tempo map or a click track. Available separation modes, formats and practice controls depend on your account entitlements. Your songs remain in your StemConsole library so you can reopen them on stemconsole.ai. Separation quality varies with the recording; use audio you have the right to process.

Language: English · Automatically detected from descriptions.

ChatGPT marketplace listing ↗Website ↗Privacy policy ↗Terms ↗Support ↗Repository ↗

Matches for “split”

Exact text from the indicated source. A mention alone does not establish support for your task.

Publisher subtitle

Split, mix and practise music

Changes

No changes recorded yet. Follow this plugin to keep track of future changes.

First seen Oct 31, 2026. Last seen Nov 4, 2026.

Keywords

Files & skills

File archives

Plugin package5 files · 9.96 KBBrowse files →
Skill instructions
make-practice-track2.09 KB

View saved version →

---
name: make-practice-track
description: Use StemConsole to turn an audio attachment, supported audio-file link, or song in the connected StemConsole library into a backing track for practice. Use for stem separation and practising with a recording, rather than music recommendations or generating a new composition.
---

Turn your recording into a backing track you can practise with inside ChatGPT.

Use the connected StemConsole tools for the source the user supplied:

- For an audio attachment, use split_song_file with the attachment reference supplied by ChatGPT. Do not invent attachment IDs or download addresses.
- For a supported audio-file URL, use split_songs. A streaming-service page is not an audio file; ask for a supported file or link when necessary.
- For an existing library song, use list_my_songs to find its ID, then open_player; avoid creating another split unnecessarily.

Choose the separation mode that fits the request: vocals for vocals and instrumental, fast for vocals/drums/bass/other, or full when separate guitar or piano stems are needed. Explain unavailable account entitlements neutrally, without offering a purchase or upgrade.

After starting a split, check get_split (or get_batch for a batch) until it finishes or fails. When processing remains in progress, report that state and use the existing job ID on subsequent checks. Do not start another split to retry a status check. If processing fails, explain the returned error and stop; do not automatically spend another allowance.

Open a completed song with open_player. The user can mute their part, balance stems, loop a passage, use the available speed/key controls, and export a practice mix. These controls run in the widget; do not claim to have changed a fader, saved a file, or measured key/BPM merely by opening it. Prepared downloads require the user to choose Prepare download and then Save file.

Act on the connected account only. Confirm the identified song and intent before permanent deletion; clarify ambiguous targets. Use song IDs returned by tools, not guessed IDs. Processing audio does not grant rights to the recording.

Release notes

Initial packaged release of StemConsole for ChatGPT: attachment and supported audio-link separation, an embedded mixer, practice controls, key/BPM analysis and exports. Includes corrected Vocal Remover filenames, centred tabs and responsive layout, temporary downloadable exports, OAuth resource binding and MCP transport validation. Review cases use the Cash for Gold demo and include a matching reviewer-accessible recording.

Declared in the saved package. Remote tools may change independently.

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package author
Dan Murtagh
Keywords
See keywords
Commerce declaration
Does not support commerceThis does not establish whether access is free or paid.
Review scenarios
5 positive · 3 negativeScenario counts, not test results.

Declared capabilities

  • Separate audio into stems
  • Make backing tracks
  • Mix, loop and practise
  • Find key and BPM
  • Export audio and tempo maps

Package observed Nov 3, 2026.

plugin.json
Technical details
First seen
Oct 31, 2026 · 00:00 UTC
Last seen
Nov 4, 2026 · 00:00 UTC
Collection status
Collected

plugin_asdk_app_6ad84c437ecc81918d72db95d4119903

Download plugin data (JSON)