Mashups and ciphers with a beat grid: sdsp-mash
Pick pairs by BPM and key, split stems, stretch only the beat, and render one beat with verses from other songs, or a beat switch per verse, from a TOML file.
Use the sdsp-mash skill. I have a beat {beat.wav} and a vocal {vocal.wav}. Measure BPM and key of both (with the half-tempo check), tell me whether the pair works by the rules (BPM 1:1, 2:1 or a stretch within 8 percent, stretch the beat, never the vocal), split the vocal with Demucs, write mash.toml, render, and report loudness per stage.
In Claude Code, paste the prompt as a message.
Install
npx skills add fortunto2/superduper-dsp --skill sdsp-mash# or the whole set as a Claude Code plugin (commands then look like /superduper-dsp:sdsp-mash):
claude plugin marketplace add https://github.com/fortunto2/superduper-dsp
claude plugin install superduper-dsp@superduper-dsp --scope userSteps
- Install the skill. The engine is a Rust tool in the superduper-dsp repo (cargo build tools/sdsp-mash); stems come from Demucs via uvx.
- Paste the prompt with the two files.
- Listen to the join, then ask for one change at a time.
Tips
- Vocal about 3 LU under the backing and ducking ratio 2 to 2.5 keeps it from shouting over the beat.
- A club master is about -10.5 LUFS and -1 dBTP; -13 LUFS sounds dull.
- The skill is written in Russian.
| works with | Claude Code: Runs as a skill or a prompt in the terminal; can read your files and write the result. |
| cost | Free. No API, no key. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| source | sdsp-mash skill in superduper-dsp (MIT) |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-10 |
| for agents | sdsp-mash-mashups-and-ciphers.md |
Related
Nine agent skills for mixing, mastering and making music (superduper-dsp)
A Claude Code plugin that teaches an agent to mix by measurement, build songs in REAPER, render plugin chains headless, turn audio into MIDI and tear down a reference track.
Strip other people's music before upload with Demucs and ffmpeg
Car radio, shop speakers and festival stages trigger Content ID. Split the soundtrack into stems, find the music on drums plus bass, keep the voice, replace the music, rebuild audio only.
Beat-sync cutting: cut on the beat, not on every beat
A rule and an agent prompt for cutting to music from a list of beat timestamps: cuts land on beats, phrases get room to breathe, and the best shot is held through the hook.
Tear down a reference track by numbers: tempo, key, groove, balance
The agent reads a spectrogram instead of listening, splits stems with Demucs, fits tempo and phase to the kick, and rebuilds the vibe until the numbers match the reference.
Music brief: describe the track you need before you search for it
A fill-in brief that names mood as harmony, a BPM range, genre, length and where the drop must land relative to your hook, so a library search or a composer returns something that fits the cut.
Separate vocals, music and drums from a recording (/solo-stem-split)
Separate a song or a film's soundtrack into stems (vocals, drums, bass, other) with Demucs, locally, on the Apple GPU when there is one.