A free music remover that takes the background music out of a video and keeps the voice, in your browser, with nothing uploaded.
Drop a video or a recording, and the voice and the music come apart. Turn the music off or down, hear it, and save it. It all happens in this browser.
Add your video or audio
The video's picture is copied as it is, not re-encoded, so it looks the same. The model downloads from our server once, and your file never leaves this browser.
This free music remover takes the background music out of a video and keeps the voice, in your browser.
Turn the music off or down, then save the video with its picture untouched. Nothing is uploaded, and there's no watermark.
Here's how it works, how well it works, and how to get the cleanest voice.
What is a music remover?
A music remover splits a recording into two tracks: the voice, and everything else. Keep the voice alone, or mix the music back in as quietly as you like.
This one runs Demucs, a separation model from Meta AI, on your own device.
How it works
Demucs listens to the sound in overlapping pieces of about 8 seconds and writes out the voice it hears. The music is what's left: the file less the voice.
So the two sliders add back up to the original exactly. Music at 0% removes it, and 100% is the file as it was.
How well it works
We tested it on 23 seconds of me talking with a Chopin nocturne under it. Before, the piano was louder than the voice, by 4.8 dB.
After, what was left of it sat 10.3 dB under the voice. A faint trace can stay where the music is loud.
- Play it before you save – listen to the loudest music first, where a trace is most likely.
- Try a little music under the voice – 10 to 25% can sound more natural than none.
- Keep the voice at 100% – turn it up only if it sounds quiet, since a louder voice can clip.
How fast it is
On a MacBook Pro with an M1 Max, the 23 seconds took 3 to 6 seconds on the graphics card, with WebGPU, depending on what else the computer was doing. On the processor alone, in a browser without WebGPU, it took 43 to 70 seconds.
The model is 181 MB and downloads the first time only. Your browser keeps it for next time.
Save the video, the audio, or each track
A video saves with its picture copied as it is, not re-encoded, and the new sound. An audio file saves as MP3, WAV or M4A.
The voice and the music also save on their own, as WAV files, to mix in your own editor.
- Expecting the singing to go – a song's vocals count as voice, so they stay with yours.
- Files over 10 minutes – trim them first, or do them in parts.
Credits
Demucs is open source from Meta AI, under the MIT license. Its htdemucs model is by Simon Rouard, Francisco Massa and Alexandre Défossez.
It runs in the browser with demucs-web by timcsy, MIT, and ONNX Runtime Web. The example's piano is Chopin's Nocturne Opus 9, Number 2, played by Peter Johnston, from Musopen, in the public domain.
After you remove the music
Add captions with the video caption generator, or resize it for TikTok, Reels and Shorts with the video resizer.
Edit your video
Edit it with
Music Remover FAQs
Questions about the music remover? Here's what to know.
A music remover splits a recording into its voice and its music, so the music can be taken out or turned down.
This one runs Demucs in your browser.
Drop the video, click Remove the music, and set Music to 0%.
Then click Save the video.
Yes, set the Music slider anywhere between 0 and 100%.
The preview plays the mix as you move it.
Mostly: in our test, the piano went from louder than the voice to 10.3 dB under it.
A faint trace can stay where the music is loud, so play it before you save.
No, the picture is copied as it is, not re-encoded.
Only the sound is new.
Yes, it's free, with no account, no watermark and no limit on how many files.
No, your file stays in your browser from start to finish.
Only the model downloads, once, from our server.
Without WebGPU, the model runs on the processor alone, several times slower.
Chrome and Edge on a recent computer use the graphics card.
This music remover is for anyone who needs the voice without the music:
- Video resizer – creators posting the same video on every platform.
- Video caption generator – anyone adding captions after.
- Text-based audio editor – podcasters cutting a recording by its words.
Teachers and course creators use it to take the music out of a lesson they recorded.
I did.
I'm Navid Moazzez, and the music remover is one of my free tools on navid.me.
Read more about me.
There's a video resizer, a video caption generator, a filler word remover, an MP4 to MP3 converter and a video to text converter.
The rest are in free tools.
Navid Moazzez
AI business strategist & AI OS builder
Navid Moazzez helps creators and founders master AI and build their own AI Operating System (AI OS) to automate their business and life.
Navid.me is reader-supported. When you buy through links on this site, I may earn an affiliate commission. Learn more.
More free tools
TikTok
Instagram
X
Bluesky
LinkedIn
Threads
Mastodon
Pinterest
YouTube
Amazon KDP
Apple Books
Amazon
Spotify
Apple Podcasts
Free AI newsletterThe most actionable AI newsletter for founders
Every week, get proven AI strategies, curated tools, and step-by-step systems to grow your audience, create better content, and build a profitable creator business.
No fluff, no filler, no BS. Just five minutes each week that might level up your online business and life.
P.S. Sign up now to get free access to my ultimate AI tools guide for creators.
