Extract the vocals from a song

Extract the vocals from any song in your browser: an AI model separates the acapella from the music on your own computer. Free, no upload.

AudioRinse · vocal isolatorOn-device · 0 B uploaded

Drop a song here

MP3 · WAV · M4A · MP4 · MOV · WEBM — up to 15 min. Nothing is uploaded.

The model downloads once and stays in this browser, so the next song starts at once. Your song is never uploaded.

How it works

  1. Drop a song onto the box above: MP3, WAV, M4A, FLAC, or a video.
  2. An AI model separates the vocals from the music on your computer. The first time, the model downloads once.
  3. Listen to the acapella. Hi-hats or guitar bleeding in? Separate again in Best quality.
  4. Download the vocals, the instrumental, or both in a ZIP, as MP3, M4A or WAV.

How it pulls out the vocals

A source-separation model runs in your browser and writes the song's vocals to their own track: the lead and the backing vocals, with the reverb and delay they were mixed with. The rest of the song goes to the instrumental, and the two add back up to the original exactly.

Standard or Best for an acapella

  • Standard (HTDemucs) works on any computer. Cymbals and bright guitars can leave a faint wash in the vocals.
  • Best (Mel-Band RoFormer) is the one for acapellas: on the MUSDB18 benchmark songs its vocals measured about 3 dB cleaner than Standard's. It needs a fast graphics chip, and the page offers it only where yours is.

Tips for a clean acapella

  • Start from the best copy you have; the model can't tell a low-bitrate MP3's artifacts from the voice.
  • Backing vocals and harmonies come out with the lead. If you need the lead alone, edit them out in your DAW.
  • Reverb stays with the voice. That's usually what a remix wants; for a dry vocal, use a dereverb plugin in your DAW.

What it's for

Remixes and mashups, studying a singer's phrasing, transcribing a melody, or practising harmonies. You can also turn the vocal into MIDI with AnyToMIDI. Separating a song doesn't change who owns it: use the acapella for your own practice, or with the rights holder's permission when you publish.

Questions

Is my song uploaded anywhere?

No. The separation model runs inside your browser, on your own computer. Your song never leaves your device, so there's no upload to wait for and nothing stored on a server. The only download is the model itself, the first time.

Are the backing vocals included?

Yes, with the lead: the model separates all the vocals from the music, not one singer from another.

How clean is the acapella?

On most songs, clean enough for a remix, with faint traces of cymbals or guitar where they're loudest. Measured on the MUSDB18 test songs, Standard's vocals score 8.9 dB and Best's 11.8 dB (signal-to-distortion ratio; higher is cleaner).

Can I get the instrumental too?

Yes. Switch the instrumental on and the vocals off, or download both in a ZIP.

How fast is it?

It depends on your graphics chip. A 4-minute song takes about 50 seconds on a gaming laptop's graphics card and about 3½ minutes on a 2020 laptop's built-in graphics; Best quality takes about three times as long where it's offered. Without WebGPU (some browsers, older computers) it runs on the processor: about 7 minutes on an 8-core laptop. The page shows the time left as it goes.

Why does the first song take longer?

The model downloads once: 126 MB for Standard, 464 MB for Best. It stays in your browser, so the next song starts at once, and it works with Wi-Fi off from then on.

How long can the song be?

Up to 15 min. Free downloads cover songs up to 10 minutes. On a computer with little memory the page takes less, and says so when you drop a longer file.

Is it free?

Separating and listening are free and unlimited. You get 3 free downloads a month for songs up to 10 minutes (1 without an account), and all the stems of one song count as one download. Pro adds unlimited downloads, songs up to 15 min and video.

Other tools