Voice isolator

Isolate speech from everything around it: noise, room sound and background chatter. Runs privately in your browser, free to try.

AudioRinse · voice cleanerOn-device · 0 B uploaded

Drop audio or video here

MP3 · WAV · M4A · MP4 · MOV · WEBM — up to 60 min. Nothing is uploaded.

How it works

  1. Drop a recording with speech in it.
  2. AudioRinse separates the voice from the rest, on your device.
  3. Set the strength to 100% for a fully isolated voice, or lower to keep some ambience.
  4. Download the isolated voice.

Before / after

Hear it before you drop anything

“After” is AudioRinse at its default settings. The voice is synthetic, so we can share it freely.

A desk fan was added to this recording.

Voice isolation, not vocal removal

A voice isolator keeps the speech in a recording and removes the rest: noise, room sound and distant background sounds. It's made for interviews, podcasts, lectures and videos. A second person talking close to the microphone counts as voice, so it's kept.

It isn't for songs. Separating a singer from a band is a different problem that needs a different kind of model; on music, this one would treat the instruments as noise. For singing, use the vocal isolator, which runs a music separation model.

What people isolate voices for

  • A usable interview from a noisy location
  • Dialogue for a video edit, ready to mix with new music
  • Clean voice-overs and narration
  • Voice notes and recordings to share or archive

Full isolation or a little room

At 100% strength you get the voice on its own, as dry as the model can make it. Most people prefer a little less: at the default (70%) the background can drop by up to about 28 dB, which sounds clean but still natural. You hear both before you download.

Questions

Can I turn the isolated vocal into MIDI?

Yes. Download the clean vocal, then turn the vocal into MIDI with AnyToMIDI, which transcribes the melody note by note. A clean vocal transcribes far better than a noisy one.

Is my recording uploaded anywhere?

No. AudioRinse runs the cleaning model inside your browser, on your own computer. Your file never leaves your device, so there's no upload to wait for and nothing stored on a server.

Can it isolate vocals from a song?

Not this one: it's made for speech, in interviews, podcasts, videos and voice notes. Separating singing from music is a different job, which the vocal isolator does.

What if two people talk at once?

Both voices are kept. It separates speech from non-speech, not one speaker from another.

Is it free?

Cleaning and listening are free and unlimited. You get 3 free downloads a month for audio files up to 10 minutes (1 without an account). Pro adds unlimited downloads, files up to 1 hour and video.

Other tools