MotionShine01 / Drop
Choose a video
A vlog, a clip or a recording with music under the voice.
Free tool
Remove music from a video, keep the voice.
Take copyrighted or loud background music out of a vlog, a clip or a screen recording and keep what people say. The AI separates voices from music in this tab; the picture is copied as it was. Nothing is uploaded, no sign-up, no watermark.
This runs in your browser. Your files are never uploaded.
How it works
Three steps, nothing to install.
02 / Separate
Let the AI split it
The voices are kept, the music goes, about 8 seconds at a time.
03 / Save
Download the video
Same picture, now with the voices only.
Questions
Good to know.
Is my video uploaded?
No. The AI model is downloaded to your browser, from Hugging Face, the open model library, and runs there, so the video never leaves your computer.
Which AI model is it?
HTDemucs, the music separation model by Meta AI researchers, released under the MIT licence, in a browser version by the demucs-web project. It splits a song into vocals, drums, bass and the rest.
How clean is the result?
Usually clean when the music is under clear speech. Singing counts as voice and stays, and a trace of the music can remain, especially drums or loud parts. Listen through before you post.
How long does it take?
It depends on your computer. With WebGPU, which uses the graphics card, a 20 second test clip took about 5 seconds; without it, the processor is much slower. The first time, the model downloads, 181 MB. Songs up to 15 minutes.
Will this stop copyright claims?
Not for sure. It removes most of the music, but traces can remain, and platforms match more than sound. Use music you have the rights to when you can.