This is a copy. Use Snipmill at snipmill.com.

Skip to content

An AI takes the noise out of a video's sound and the voice is made clearer; an H.264 or HEVC picture is copied untouched.

Settings

Settings

NoiseBehind a voice; not for music
VoiceCuts rumble, lifts speech
LoudnessWhole file at −16 LUFS
Runs on Snipmill's server: only the sound is sent, and deleted after. How we keep it private

Good to know

What happens to the video

Only the sound is cleaned; the rest of the file is handled like this:

Picture in H.264 or HEVC
What happens: Copied as it is, frame for frame
Picture in another codec (VP8, VP9, AV1, MPEG-4)
What happens: Encoded again as H.264
Sound
What happens: Cleaned and put back as AAC at 192 kbps, in mono with Noise on
Other sound tracks, subtitles
What happens: Left out: the first picture and sound track are kept
Length
What happens: Kept as it is

What goes to our server

Only the sound goes to Snipmill's server, when you press the button that starts the job; the line under it says so. The server deletes it once it has answered and keeps no copy. A video's picture isn't sent, and with Noise on Keep the sound isn't either. The voice, the loudness and the file you save are made in your browser by the built-in copy of FFmpeg.