Profanity Remover for Video — AI Censor Online
Tool for censoring profanity in a video — a YouTube upload, a stream clip, a reel or a family recording. Speech recognition listens to the soundtrack, places each spoken word on a timeline beneath the player, and marks every swear word so you can bleep or mute it before the clip goes out. Only the audio track is rebuilt; the video stream is copied frame for frame, so the picture leaves at the same quality it came in. Currently recognizes Russian speech; processing runs in your browser via WebAssembly.
How to remove profanity from a video
Add a video file — MP4, MOV, WebM and more
Let the soundtrack be transcribed; the screen shows progress, time elapsed and time remaining
Scrub the timeline under the player: click a word in the transcript to keep it, or drag over the bar to bleep a missed one
Choose the bleep sound and an optional on-screen cue, then watch it back right in the player
Hit "Download clean file" — the video saves with the picture untouched and only the audio cleaned
Auto-censor swearing in your footage and keep the picture untouched
Keyboard shortcuts
- Space
- pause / play
- J K L
- back 3 s · pause · forward (press L again to go faster)
- I O
- start / end of the selected censor at the playhead; with nothing selected — mark the in and out of a new censor
- ↑ ↓ · [ ]
- previous / next censor
- ← →
- one frame back / forward (Shift — one second)
- , .
- move the selected censor by 10 ms (Shift — 100 ms)
- Shift+K
- play the selected censor with some lead-in
- Delete
- remove the selected censor
- Ctrl+Z · Ctrl+Shift+Z
- undo / redo
- + − · Alt
- zoom the waveform in / out; hold Alt while dragging to turn snapping off
Transcript
Will be muted
Custom word lists (blacklist and whitelist)
Features
Why use this video censor
A single uncensored word can cost a video its monetisation or get a clip pulled, and bleeping by hand in an editor usually means re-rendering the whole file and watching the picture soften. This tool reads the soundtrack, lays every word on a timeline under the player, and bleeps the swearing while copying the video stream untouched — so a stream highlight, a reel, or a re-upload comes out at full quality with only the audio cleaned, and an optional on-screen cue makes each bleep read clearly to viewers.
Frequently Asked Questions
Does censoring lower my video quality?
No. The video stream is copied with no re-encoding (codec copy); only the audio is rebuilt and written back as AAC 192 kbps, so the picture is exactly as sharp as the upload.
Does censoring re-encode the picture?
No. The bleep is applied to the soundtrack and the video stream is copied across untouched, so the image that comes back is bit for bit the one you uploaded — same resolution, same bitrate, same compression artifacts, no second-generation softness. It is also why a long clip finishes far quicker than a filter that has to redraw every frame.
How does it find the words to bleep?
Speech recognition listens to the soundtrack and writes out every word with its exact timing, and those words scroll on a timeline under the player while the clip plays. You decide what goes: the automatic list catches the obvious cases, and you can add a name, a brand or an insult it did not know, or spare a word it flagged by mistake. Nothing is bleeped until you say so.
Can I show something on screen when a word is bleeped?
Yes. Turn on a video cue and the chosen effect — a dim, red border, shake or float — appears on the frame wherever the audio is censored, matching the bleep visually.
What if a swear is missed or a clean word is flagged?
You decide before export: click any word in the transcript to bleep it, or mark a section on the timeline by hand; a wrong flag is cleared in one click, and uncertain matches are highlighted separately.
Experts on this topic
Work through it with a specialist — an online lesson or consultation, times shown in your time zone.
We can! Just send us a quick message with your idea. If you'd like to discuss it in detail, leave your email and we'll get back to you. You can stay anonymous.
How do you rate this tool?
Comments
it is not working it keep saying stalled what is the matter
Thanks for the report — confirmed and fixed. On long videos the recognition health-check gave up too early, which is exactly the "stalled" message you saw. Recognition now shows its real progress ("Analyzing audio…", then "Recognizing speech…" with a time estimate) and long files finish properly. Note that an hour-long video takes a while to process in the browser. Please try again!