For any video with speech
Remove background noise from video
Drop a video and get the same video back with a clean voice. The picture is copied as it is, so nothing is lost and nothing has to re-render.
Cleaned on your own device — the file is never uploaded.
The problem
What gets in the way
A phone or camera records everything around you: the fan, the street, the fridge, the room next door. Re-shooting is rarely an option, and a noise gate only mutes the pauses, so the noise is still there under every word.
- Fans, air conditioning and computer hiss
- Traffic and street noise
- Keyboard and mouse clicks
- Murmur and chatter in the background
What you get
A clean voice, ready to use
- The same video file back, in its own container
- The picture copied packet for packet: no re-encode, no quality loss
- A new voice track that stays in sync with lips from start to end
- Loudness set for where the video will play
How it works
Four steps, one clean file
Step 1: Pick your settings
Before you add the video, set Loudness (YouTube −14 LUFS suits most online video) and leave Output format on Same as original to get a video back.
Step 2: Drop the video
Drag an MP4, MOV, WebM or MKV file onto the tool, or choose it from your files.
Step 3: Let it clean
Your browser cleans the video on your own computer and it is never uploaded. The first file takes a little longer while our speech AI loads.
Step 4: Compare and keep it
The clean video downloads by itself when it is ready. Play the A/B preview to switch between original and cleaned at the same moment, or change a setting and choose Download again.
For this recording
Recommended settings
- Loudness
- YouTube (−14 LUFS)
- Output format
- Same as original
YouTube loudness matches the level of other online videos, and the built-in voice clarity adds the presence small phone and laptop speakers need. Same as original keeps the video.
Set them in the tool before you add the file: they are used for the automatic download, and you can change them afterwards and download again.
Good to know
- Music is turned down under the voice rather than removed, so it never cuts in and out between words.
- Echo and room reverb stay as recorded: it removes noise, not the sound of the room.
Formats & limits
What goes in, what comes out
- MP4
- MOV
- WebM
- MKV
Same as original: the same container with the picture copied; MP4 and MOV get AAC audio, WebM and MKV get Opus. Or save only the audio as WAV, MP3 or M4A.
- MP3, M4A and video audio tracks are written in mono at about the source bitrate (at least 160 kbps): the cleaned voice sits in the centre.
A free account cleans 30 minutes a month, no card needed. The paid plans, Creator (9 hours), Pro (30 hours) and Studio (100 hours) a month, take files up to 3 hours and 4 GB each. See pricing
FAQ
Common questions
Will the video quality change?
No. The video stream is copied without re-encoding, so resolution, frame rate and bitrate stay exactly as they were. Only the audio track is replaced with the cleaned one.
Will the voice stay in sync with the picture?
Yes. The cleaned track starts at the same moment as the original, and the processing delay is compensated, so lips and voice line up for the whole video.
Can I get only the cleaned audio?
Yes. Set Output format to WAV, MP3 or M4A and you get the cleaned audio without the picture, for example to edit in a separate audio app.
What happens to background music in my video?
Our speech AI keeps voices and treats everything else as noise. Where it hears music it turns the music down under the voice instead of cutting it out, so it doesn’t stutter between words. It isn’t made for music videos.
Can I get a transcript or subtitles for my video?
Yes, on a paid plan. Save the cleaned video to your library, or upload one there, and choose Transcribe: you get plain text, timestamped text, and .srt or .vtt subtitles to add in your editor or video platform, in 30 languages, or automatic detection. Only then is the audio sent to our speech AI, which keeps nothing; copy or download the result, because we don’t store it.
Is my file uploaded?
No. The cleaning runs inside your browser, on your own computer. Your audio and video never leave your device; our server only receives the file’s length and format to check your allowance.
Is it free?
A free account cleans 30 minutes a month, no card needed. The paid plans, Creator (9 hours), Pro (30 hours) and Studio (100 hours) a month, take files up to 3 hours and 4 GB each. See the pricing page for details.
Related
Other recordings we clean
Clean audio for YouTube videos
Clean the voice and hit −14 LUFS, ready to upload with the picture untouched.
See howMP4 noise removal
MP4 in, MP4 out: the voice cleaned, the H.264 or HEVC video copied as is.
See howClean up Zoom and meeting recordings
Take typing, fans and room noise out of recorded Zoom, Teams and Meet calls.
See how
Ready for a clean take?
Drop a recording and hear the difference in seconds. Create a free account, no card needed.
Try it free