Blur faces in a video
Faces found and covered frame by frame, on your own device, for children, bystanders and anyone who did not agree to be filmed. Always watch the result before you share it.
- Nothing is uploaded
- Works offline after first use
- Open source
- No watermark · limit is your device’s memory; phones hold less
Finds the faces that look towards the camera in a video (MP4, MOV, WebM) and blurs or pixelates them frame by frame; you check the result before sharing. It is free, needs no account and adds no watermark, and your files are not uploaded: everything runs in your browser on your device. The first run downloads the face detector (about 4 MB) and the WebAssembly engine that runs it to your browser, and after that the tool works offline.
Done
Open the network tab. Your files never appear in it.
Add files and run the tool to see every request this tab makes.
Your files are processed on this device and never sent to a server. Reload the page to clear everything from memory.
How it works
- Drop one or more videos from your phone or camera.
- Choose how to cover the faces: blur, pixelate, a black box or an emoji, and how strong.
- Run it. Every frame is scanned for faces and covered; then watch the result through before you share it.
In your browser, not on a server
Mediabunny (MPL-2.0) reads the video and your browser’s WebCodecs decoder turns it into frames. About ten times a second, Google’s MediaPipe face detector (BlazeFace, Apache-2.0) scans the frame on your device, whole and in overlapping halves for small faces. Each face is covered on a canvas, and kept covered for half a second after it was last seen, before the frame goes to the browser’s own H.264 encoder (VP9 or AV1 where H.264 is missing). The sound is copied as it is.
Compared with upload-based tools: Online face-blurring services upload the whole video to run their AI, and video editors make you draw and move a mask by hand, frame by frame. Here the detection is automatic and happens on your device, so the faces you are hiding are never sent anywhere.
Verify it yourself. Give the page a short while after your first run to save itself for offline use, then turn off Wi-Fi or switch to airplane mode and run the tool again. Or open your browser's developer tools (F12, or Cmd-Option-I on a Mac), pick the Network tab, and watch it while you convert. The panel above does the same count for you.
Questions
Is the video uploaded?
No. The video is decoded, scanned and written again by code in this tab, with a face detector that runs on your device. That matters most for exactly the videos you would blur: children, a protest, a witness, people at work.
Will it catch every face?
It finds faces that look towards the camera, including small ones, about ten times a second, and keeps each one covered for half a second after it was last seen. Faces in profile, turned away, very small or behind glasses and masks can be missed for a moment, so always watch the result before you share it. The note under the result says how many frames had a face covered.
Blur, pixelate or black box: which hides best?
A black box or an emoji hides a face completely. Blur and pixelate at a high strength make a face unrecognisable to people, and look softer, but at a low strength someone who knows the person may still recognise them.
Does it keep the sound?
Yes, unless you tick Remove the sound. Voices, names said aloud and background noises can identify people too, so consider removing it for sensitive footage.
How long does it take?
Every frame is decoded, scanned and encoded again, so on a laptop a one-minute clip takes roughly one to a few minutes, depending on its resolution. Phones are slower. Keep the tab open until it finishes.
More video and audio tools
Remove silence
Shorter recordings without the dead air, made on your own device. Interviews and lectures stay private.
Transcribe audio to text
Speech to text and subtitles made by an AI model running in this tab. Interviews, lectures and voice notes are never uploaded.
Add subtitles to video
Captions written from the speech and burned into the picture, on your own device. Or bring an SRT and burn in that.
Vocal remover
Split a song into the music and the voice with an AI model running in this tab. Karaoke tracks and acapellas without uploading anything.
Popular conversions
Guides
- How to blur a face in a videoBlurring a face in one photo is easy. In a video the face moves, so the cover has to follow it. Here are the options, and a way that never uploads the clip.