MASTER MUSIC STUDIO · ISOLATED EXPERIMENT

Stem Lab Hardware Test

iPhone-first · No MMS integration · Your audio stays local

Proof of concept, not a production tool. Test 1 runs a lightweight real AI vocal/instrumental model in Safari. Test 2 opens an independent open-source four-stem reference. Neither sends your song to an MMS server. First use needs internet to download the model.
01

Choose a track

02

Make a short test clip

No need to trim the song in another app. Start with 15 or 30 seconds; choose a section containing multiple instruments.

0:00
30 seconds
03

Run the lightweight AI test

Real ONNX inference: a ~30 MB MDX-Net model splits vocals from accompaniment. The model and runtime download on first use; separation happens on your phone.

2 stemsWASM / WebGPU fallbackFree open-source engine
0%
Choose a song and create a clip first.
04

Four-stem Demucs reference

For drums, bass, vocals and other, use the open-source sdemux web demonstration. It runs Demucs on your device, but downloads a substantially larger (~172 MB) model. Upload the WAV clip you just saved in step 02.

Open four-stem reference test ↗

Independent third-party site, not part of this ZIP. Phone/Safari compatibility and performance are not verified by us. Stay on that page during inference.

05

Compatibility report

There is no telemetry, login, or MMS database connection in this package. Your report is only copied or saved when you choose.