Vocal Remover & Stem Splitter

This vocal remover and stem splitter makes karaoke tracks, a cappellas and separate drum, bass and instrument stems from your songs, entirely in your browser. Choose the AI engine and it downloads Demucs, Meta's music separation model, once from Hugging Face into your browser, then splits any song — stereo or mono, with reverb and backing vocals — into drums, bass, other and vocals, using your GPU where available; you can delete the model at any time. Or choose the instant engine, which needs no download and uses centre-channel cancellation: in almost every studio mix the lead vocal sits dead centre, so subtracting one stereo channel from the other removes it, while guitars, keys and backing parts panned to the sides remain. Plain cancellation also wipes out the centred bass and kick drum, so this tool puts the low end back through a filter whose cut-off you can adjust. Drop a single song or a folder of them, preview each result in the page, and download 16-bit WAV files one by one or as a ZIP. A rough vocals-only output is there too. Either way it is free, works on a whole folder of songs, lets you preview each result, downloads 16-bit WAV files or a ZIP, and your music never leaves your device.

What centre cancellation keeps and removes

Part of the mixUsual positionIn the instrumental
Lead vocalCentreRemoved
Bass guitar and kickCentreKept (restored below the cut-off)
SnareCentreMostly removed
Guitars and keysPanned left or rightKept
Backing vocalsOften panned wideKept
Vocal reverbSpread across stereoPartly kept

When to use it

  1. Make a karaoke track for a party from your own music files.
  2. Create a practice backing track to sing or play the melody over.
  3. Hear the instruments clearly to learn a guitar or keyboard part.
  4. Prepare instrumental versions of several songs at once.
  5. Check how a mix is panned by listening to the side signal.

How to Use

  1. Choose Instrumental or Vocals.
  2. Set how much bass to keep.
  3. Drop songs or a folder.
  4. Click Process, preview, and download the WAV files or a ZIP.

Features

  1. AI engine: Demucs with drums, bass, other and vocals stems
  2. One-time model download, removable any time
  3. Instant engine with no download
  4. Instrumental (vocals removed) and vocal outputs
  5. Adjustable bass restore
  6. Mono file detection
  7. Loudness normalisation
  8. Batch processing
  9. Preview player
  10. 16-bit WAV output
  11. ZIP download
  12. 100% client-side

FAQs

What is the difference between the AI and instant engines?

The AI engine (Demucs) has learned what voices and instruments sound like, so it separates them cleanly even with reverb, backing vocals or a mono file, and can output four stems. It needs a one-time download of about 172 MB and takes about a minute per song on a GPU. The instant engine needs no download and works in seconds, but only removes what is mixed dead centre.

Can I delete the AI model afterwards?

Yes. Use Clear downloaded models; after confirming, it is removed from your browser and would be downloaded again next time.

How does the vocal remover work?

Lead vocals are usually mixed equally into both stereo channels. Subtracting one channel from the other cancels anything in the centre, which removes the voice; the bass is then restored from the low frequencies.

Why can I still hear some vocals?

Reverb and echo on the voice, and backing vocals panned to the sides, are not in the exact centre, so they survive. Live recordings and some modern mixes cancel less cleanly.

Why is the result silent or very thin?

The file is mono or nearly mono, so both channels are the same and almost everything cancels. Use a stereo version of the song.

Are my songs uploaded?

No. Decoding, processing and WAV encoding happen in your browser.

What format is the output?

16-bit WAV at the song's own sample rate, which any player or editor can open.

Technical Details

Songs are decoded by the browser at their own sample rate. Lead vocals are almost always mixed in the centre, equally loud in both channels, so the side signal (left − right) ÷ 2 cancels them. That also cancels centred bass and kick drum, so the low end of the mid signal (left + right) ÷ 2 is restored through a fourth-order low-pass filter (two cascaded RBJ biquads) at an adjustable cut-off, 120 Hz by default. The vocals option does the reverse: the mid signal high-passed above the cut-off, a rough centre extraction. A stereo check measures the correlation between channels and the side-to-mid level, and warns when a file is effectively mono. The AI engine runs HTDemucs, Meta's hybrid transformer source-separation model (MIT), exported to ONNX with the STFT outside the graph and executed with ONNX Runtime Web on WebGPU or WebAssembly in a Web Worker. The model (about 172 MB) downloads only when the visitor asks, straight from Hugging Face into the browser's Cache Storage, and can be removed from the Downloaded models panel. Audio is resampled to 44.1 kHz and cut into 7.8-second segments with 25% overlap; each segment's waveform and its 4096-point STFT (hop 1024) go in, the model returns a time-domain branch and a complex spectrogram branch per source, the spectrogram is inverted and the two are summed, and segments are overlap-added with tapered weights into drums, bass, other and vocals. Instrumental is drums + bass + other. Output can be peak-normalised and is written as a 16-bit PCM WAV.

Audio Tools

Audio Tools

  • Chord Transposer and Capo Finder
  • Delay and Reverb Time Calculator
  • Scale and Chord Finder
  • Song Key Finder
  • Neural Text to Speech
  • Audio Noise Remover
  • Audio to MIDI Converter
  • Audio Trimmer