Vocal remover & stem splitter
Remove or isolate vocals from a song with AI — split it into vocals, instrumental, drums, bass and other. Private — runs on your device
Powered by Meta's open-source Demucs model running in your browser. checking…
Click to choose or drag & drop a song here
MP3, WAV, M4A/AAC, OGG, FLAC · one track at a time
Notes
How it works: the first time you separate a track, an AI model (~172 MB) downloads to your browser and is cached — later runs skip the download. Separation then happens entirely on your device: on your GPU via WebGPU where available, otherwise on the CPU (slower). A typical song takes from about a minute to several minutes depending on your hardware.
Stems you get: Vocals and Instrumental (the whole backing track), plus Drums, Bass and Other on their own — all as lossless WAV. Nothing is uploaded; your audio never leaves your device.
Heads-up: long tracks use a lot of memory — for very long files a desktop browser works best. Best results come from clear stereo mixes.
How to use the vocal remover
- Drop in a song (MP3, WAV, M4A, FLAC…). On first use the AI model downloads once (~172 MB) and is then cached.
- Click Separate stems — everything runs on your device, so a typical track takes from about a minute to several minutes.
- Preview and download each stem: Vocals, Instrumental, Drums, Bass and Other (lossless WAV).
Common uses
- Make a karaoke or instrumental backing track by removing the vocals.
- Pull an a cappella (vocals only) out of a song.
- Isolate drums or bass to practise, sample or remix.
- Solo individual parts to study how a mix was made.
How it's built & why it's safe
Uses Meta's open-source Demucs (Hybrid Transformer) model, run entirely in your browser with ONNX Runtime Web — on your GPU via WebGPU where available, otherwise multi-threaded WebAssembly. Your audio is never uploaded; only the model is downloaded once to your device. Because this on-device AI needs cross-origin isolation (which ad networks don't support), this page runs ad-free.
Frequently asked questions
Is my music uploaded?
No. The AI runs entirely on your device, so your audio never leaves your browser. Only the model file is downloaded once from Hugging Face and then cached.
How long does separation take?
It depends on your device and the track length. With a recent GPU (WebGPU) a song takes roughly a minute or two; on the WebAssembly fallback it can take several minutes.
Why is there a one-time download?
The Demucs AI model is about 172 MB. It's fetched the first time you use the tool and cached by your browser, so later separations start quickly with no re-download.
Which stems do I get?
Five: Vocals and Instrumental (drums, bass and other combined), plus Drums, Bass and Other on their own — all as lossless WAV.
Is it really free?
Yes. It's open-source AI running on your own device, so there are no accounts, credits or per-song fees.
Why doesn't this page show ads?
On-device AI needs cross-origin isolation, which isn't compatible with our ad provider — so this one page is ad-free. The rest of the site is unaffected.