Remove background music from a video
Removes the background music from a video and keeps the dialogue, narration and sound effects. It works in Chrome or Edge on a PC that can use the GPU (WebGPU); phones and tablets are not supported. The source separation AI runs in your browser, so the video is never uploaded.
The first run downloads an AI model (about 27 MB); later runs use the copy stored in your browser. Your files are never uploaded.
Processing uses about 3 GB of GPU memory.
Settings
How to use
- 1
Add a video
Drop one video such as MP4, MOV, WebM or MKV. For a long video, first cut out only the part you need with “Trim video” to shorten the wait.
- 2
Choose what to keep and run
The default is “Voices and sound effects (remove the music)”. To remove sound effects too, choose “Voices only (remove sound effects too)”. The first run downloads the AI model (about 27 MB). Keep this tab in the foreground until it finishes.
- 3
Play it back and save
Play the result on the page to check how much music remains, then press “Save”. The picture is unchanged and the video is saved in the same format as the original.
How it works and what to choose in “Keep”
The AI is TIGER-DnR (a model from research presented at ICLR 2025; the weights are licensed under Apache-2.0), which splits the audio into speech, sound effects and music. The default in “Keep” is “Voices and sound effects (remove the music)”. To remove background noises too in a lecture or interview, choose “Voices only (remove sound effects too)”. The picture is not re-encoded: only the audio is replaced, so the image quality does not change. Only one audio track is processed, and subtitle tracks and chapters are not written.
Processing time grows roughly with the length of the video. On the mini PC we tested (integrated GPU), a 1-minute video took about 1 minute, and a video shorter than 12 seconds took about 25 seconds including preparing the AI model. Some GPUs take several times longer. Processing uses about 3 GB of GPU memory, and the first run downloads the AI model (about 27 MB). For a long video, cut out only the part you need with “Trim video” to shorten the wait.
To remove the vocals from a song, use “Vocal remover”; to take out only the singing, use “Acapella extractor”; to reduce noise in a recording, use “Audio noise removal”. To make the background behind a person transparent, use “Video background remover”. To turn a recorded lecture or meeting into text, try Transcriber, a transcription tool from the same operator.
Specifications of this tool
- Input
- MP4, MOV, M4V, WEBM, MKV, TS, 3GP
- Output
- Same as input, MP4, MOV, WEBM, MKV
- Limits
- One file at a time. Output up to 3.5 GB per file (videos expected to exceed it are not accepted)
- Free, no sign-up, no app to install
- Files are never uploaded (processed in your browser)
Frequently asked questions
Is my video uploaded to a server?
No. Removing the music and writing the video happen in the browser on your device, and the video data is never sent anywhere. The AI model (about 27 MB) is downloaded from the internet only the first time. Processing statistics used to fix bugs (device specs, the range of the audio length, error types and so on; never the video itself or its file name) are sent to this site's server, and you can turn this off with the switch under “Help us improve the service” at the bottom of the page.
Can I use it on a phone or tablet?
Not on iPhone or iPad. The AI uses about 3 GB of GPU memory, so this tool is made for Chrome or Edge on a PC that can use the GPU (WebGPU). It can run on Android phones and tablets and in Safari on a Mac, but it may stop partway.
What happens to music with singing and to sound effects?
Music with singing is often removed together with the singing, and part of the singing may remain. This is because the AI is trained to keep spoken voices as “voice”. Sound effects are kept, but sounds that are hard to tell apart from the music may become quieter along with it, and a little music may remain. Play the result on the page to check it before you save.
Can I publish a video after removing its background music?
Yes, if you shot or made the video yourself or have confirmed the rights to it. Removing the music does not remove the rights to the picture, the voices and so on, which stay with the original rights holders. To edit and publish or distribute someone else's video, you need permission from the rights holders.
Help us improve the service
If a conversion fails, sending us the circumstances helps us track down the cause. Knowing which devices and formats fail most often, and how long processing takes, lets us revise the supported formats and fix the bugs behind them. If you don't mind, leaving this on is a real help.
What is sent
- The tool you used and the settings you chose (output format, quality, etc.)
- Your device specs (GPU, memory, core count)
- The input format with a rough size
- How many files succeeded or failed and how long it took
- The error type and details when something fails
What is never sent
- The files themselves and file names
- IP addresses
The data goes only to this site's own server, never to a third-party service.
For the full list, including the details each tool sends, see “Processing statistics” in the privacy policy.
Details sent by this tool (counts, times, kinds and yes/no only)
In addition to “What is sent”, this tool sends the following details.
- Remove music from video
- The range of the audio length, the range of the processing time per minute of audio, and how many times the GPU was prepared again partway.