Upload the song
Drop an MP3, WAV, M4A, AAC, OGG, Opus, or FLAC file. No account is needed for the preview.
An instrumental maker takes the lead vocal out of a finished song and keeps the drums, bass, guitars, and keys. Upload an MP3 or WAV, hear 30 seconds of the result free, then download the instrumental as a WAV.
Last updated
The preview plays 30 seconds of your song with the vocal taken out. Listen to a chorus, where the voice is loudest. A faint echo of the singer can remain; the drums and chords should sound as they did.
The song as you uploaded it, vocal and all.
The same 30 seconds with the lead vocal and the backing vocals removed.
Most songs never get an official instrumental. Making one yourself takes minutes when the vocal is the only part you need gone.
Practice or record over the original arrangement instead of rebuilding it from a MIDI file.
Take the verse off a track and write your own over the same drums and bass.
A song with lyrics fights a voice-over. Without the vocal it can sit under talking. Check the rights before you post it.
Hear the guitar, keys, and bass lines that the vocal covered, then play along.
It runs htdemucs, the Hybrid Transformer Demucs model that Meta released as open source under the MIT license. It scores 9.00 dB SDR on the MUSDB HQ test set, and it runs on a GPU, so you get one finished file.
The preview is your own song, not a demo clip, so you know how this particular mix splits.
You get the instrumental as one stereo WAV at 44.1 kHz. There is nothing to mix back together.
An old mono recording comes back as mono, so it does not turn into fake stereo.
Separation models guess which sound belongs to the voice. Most of the time they are right; these are the usual misses.
A long echo on the singer can leave a quiet trace after each line, most often in ballads.
Harmonies and a choir count as vocals, so they leave with the lead. You cannot keep them and drop only the lead singer.
A lead saxophone, violin, or synth that sings a melody can come out a little thinner.
An official instrumental is the cleanest when one exists. When it does not, a separation model keeps more of the band than center cancelling.
| Compared on | Official instrumental | Center cancelling (Audacity) | This instrumental maker |
|---|---|---|---|
| Bass and kick drum | All there | Thinned or gone | Kept |
| Mono songs | Depends on the release | Does nothing | Works, stays mono |
| Backing vocals | Depends on the release | Partly kept | Removed with the lead |
| Available for | Few songs | Any stereo song | Any song you can upload |
| Cost | Price of the release | Free | Free preview, then minutes |
Demucs htdemucs was trained on the MUSDB set plus 800 songs. It splits a mix into drums, bass, other instruments, and vocals; this site keeps the vocals, or adds the other three back together.
Demucs on GitHubAny song saved as an audio file. A clean studio mix splits best; a phone recording of a concert splits worst.
The download is a 44.1 kHz WAV. A stereo song stays stereo, and a mono one stays mono. Video files are rejected, so save the soundtrack first.
Save its soundtrack with the free extract tool, which runs in your browser and uploads nothing, then upload that file here.
Drop an MP3, WAV, M4A, AAC, OGG, Opus, or FLAC file. No account is needed for the preview.
Switch between the original and the instrumental on 30 seconds of the song. Pick a chorus if you can.
Make the full instrumental and download it. The file is deleted from our storage after 24 hours.
Rehearse a cover over the real backing, or send it to a vocal coach.
Write over a familiar beat, or study how the drums and bass sit together.
Give students the backing to practice with at home.
The instrumental maker, the acapella extractor, and the karaoke maker run the same split. Pick the page that keeps the part you want.
| Job | Use |
|---|---|
| The music without the singer | Use this page |
| Only the singer, no music | Acapella extractor |
| A backing track to sing along to | Karaoke maker |
| Music under someone talking, not singing | Remove background music |
The upload and the instrumental are deleted 24 hours after you upload. They are not public demos.
Monthly and yearly prices stay visible together. You pay after the preview sounds right and you keep the full file. Pro includes 20 hours a month, not unlimited cleaning.
Free
Try it on your own recordings
Upload and preview$9.99/month
$9.99/month, or $95.88 per year ($7.99 per month)
For weekly podcasts and video creators
Get StartedBuy minutes once. They do not expire.
1 Hour Pack
$2.99
Pay once, use whenever you need
5 Hour Pack
$9.99
Lower price per minute for bigger projects
| Plan | Price | Includes |
|---|---|---|
| Free | $0 | Free 30-second previews, Unlimited silence removal, Files deleted after 24 hours |
| Pro monthly | $9.99/month | 20 hours of processing per month, Audio and video, Noise and echo removal |
| Pro yearly | $95.88 per year ($7.99 per month) | 20 hours of processing per month, Audio and video, Noise and echo removal |
| 1 Hour Pack | $2.99 | 60 minutes of processing, Audio and video, Minutes never expire |
| 5 Hour Pack | $9.99 | 300 minutes of processing, Audio and video, Minutes never expire |
Upload the song, listen to the free 30-second preview with the vocal removed, and download the full instrumental as a WAV if it sounds right.
The 30-second preview is free. The full song uses processing minutes, from a Pro plan or a minute pack. A 1 Hour Pack costs $2.99 and covers about 15 songs of 4 minutes.
No. Backing vocals, harmonies, and choirs are voices too, so they are removed with the lead. If you need them, keep the original for those parts.
Usually it is the reverb or delay on the voice, which the model sometimes leaves as a quiet trace. It is most noticeable in slow songs with a lot of echo.
Less well. In a concert recording the crowd singing along counts as vocals, and the room blurs the instruments together. A studio version splits more cleanly.
No. Each run gives you one WAV: the part this page keeps. To get the other part of the same song, upload it on the acapella extractor page for the vocal. That is a second run, so it uses processing minutes again, and the free preview works there too.
No. Upload a file instead. If the song is in a video you have the rights to, save its soundtrack with the free extract tool first; it runs in your browser and uploads nothing.
Splitting a song does not change who owns it. Practice, study, and singing at home are one thing. Posting the instrumental or the vocal, or selling a cover or remix built on it, still needs permission from the rights holders.
You can hear the 30-second preview 3 times in 24 hours without an account, and 20 times in 24 hours after you sign in. The upload limit is 2 GB. The full song is billed in whole minutes, rounded up, with a minimum of 1 minute, so a 3:20 song uses 4 minutes.
Remove noise from audio
Wind, fans, traffic, and hum
Remove noise from video
Clean the soundtrack of MP4, MOV, WebM
Remove echo
A repeat you can count after a word
Remove reverb
Shorten a dense room wash
Audio enhancer
Make speech easier to hear
Remove background music
Lower music under someone talking
Acapella extractor
Keep only the vocals of a song
Remove vocals from a song
The music stays, the singing goes
Karaoke maker
Turn a song into a backing track
Remove silence
Cut pauses, free and in your browser
Extract audio from video
Save the soundtrack as M4A, MP3, or WAV
Normalize audio
Set loudness to -14 or -16 LUFS, free
Increase video volume
Make a quiet video louder, picture untouched
Remove buzz & hum
Lower electrical hum under a voice
Remove static & hiss
Lower hiss and static under a voice
Remove applause & clapping
Lower claps around a speech
Whether you need to clean a podcast, a meeting, or a video you already shot, these guides show the next step.
Upload one song and hear 30 seconds of it without the vocal.
Upload a song