Free tool
Background Music Remover
Strip the music out of a recording and keep the voice — same length, same timing, ready to drop back into your edit.
This runs inside your browser, not on our servers. Your file never leaves your machine and is never used to train ANYANO models.
Choose an audio file to separate
MP3, WAV, FLAC, M4A, AAC or OGG — up to 100.0 MB and 8 minutes. Processed on your own machine.
Where voice and music share the same frequencies, separation leaves artifacts. Speech over sparse music separates far more cleanly than speech under a full mix.
Detail
How this works
Removing background music is a separation problem, not a subtraction. The model predicts the voice and the music as two signals, and where they occupy the same frequencies at the same moment the result is an estimate. That is why quiet, sparse backgrounds come away almost invisibly and busy mixes leave a residue in the voice.
Both halves are returned at the original timing, so the voice track can go straight back onto a video timeline or into a podcast edit without re-syncing anything.
One thing worth saying plainly: removing music from a recording does not license it. Use this on material you own or have permission to work with.
FAQ
Frequently asked questions
Toolbox
Related tools
Train your sound. Generate your song.
ANYANO is the bigger version of this: prepare music you own, train a Sound that stays private to your account, then generate from it.