Add to Chrome

AI Noise Reducer

Clean hiss, fan noise and room hum out of a voice recording with an AI model — processing stays in your browser.

Audio tool

Remove background noise from speech

Runs in your browser

Drop a voice recording here

or click to choose from your computer

MP3 · WAV · FLAC · AAC · M4A · OGG

✓ Local processing in your browser · Files are not uploaded to our servers

What is the AI Noise Reducer?

The AI Noise Reducer takes a voice recording and removes the background noise around the voice: hiss from a microphone preamp, fan and computer noise, air conditioning, traffic and the empty-room sound between sentences. It is meant for podcasts, voice-overs, interviews, lectures, voice notes and screen recordings.

Drop in a file, listen to Original and Cleaned one after the other, adjust Strength, and download the version you like. There is no account, no upload queue and no server round trip.

Noise reduction is different from simply turning the volume down or using an equalizer. An equalizer cuts a fixed frequency range for the whole file, which also dulls the voice. The AI model decides frame by frame which part of the sound is speech and which is noise, so the voice stays clear while the hiss and hum between words fade out.

Typical results: a laptop or phone recording with a constant fan or hiss drops by several decibels in the pauses, while the speech itself stays almost unchanged. Very loud, non-stationary noise such as a passing siren or a dog barking in the middle of a sentence is reduced less, so check the result by ear before you publish.

Good to know

  • Works best on speech. Music with vocals is better handled by the Vocal Remover or a dedicated mastering tool.
  • Start with Strength around the middle and raise it only until the pauses sound clean. Higher values can make the voice sound slightly thin.
  • Keep the original file. Export the cleaned version as WAV for editing or as MP3 192 kbps for sharing.

How the AI noise reduction works

The tool uses RNNoise, a small neural network published by Xiph.Org. It was trained on speech mixed with many kinds of noise, so it learned to tell the two apart in real time.

01

Analyze every 10 ms

The recording is converted to mono 48 kHz and cut into 10-millisecond frames. For each frame the network estimates how much of every frequency band is speech and how much is noise.

02

Suppress the noise

Bands that are mostly noise are turned down. Bands that carry voice are left alone, so consonants and the tone of the voice stay natural.

03

Blend by Strength

The cleaned signal is mixed with the original according to the Strength slider. Optional normalization brings the peak level back to a healthy volume before you export.

Which setting should I use?

  • Light (35%) — for recordings that are already fairly clean and only need a little polish. Keeps the room feel.
  • Standard (70%) — the best starting point for most voice recordings. Removes most of the hiss and fan noise and keeps the voice natural.
  • Strong (100%) — for noisy phone calls, laptop recordings and rough field audio. Check the quiet parts for a slightly processed sound.
  • Strength — a manual slider from 0% (untouched) to 100% (full model output).
  • Normalize output — raises the level after cleaning, because noise removal makes the recording quieter.

Which recordings work best, and which will not

The model is trained on speech, so it works best on voice. It can also help with noisy background audio, but it is not a music tool.

  • Voice with steady background noise — podcasts, voice-overs, lectures and voice notes recorded in a room with a fan, a heater or street noise. This is the ideal case.
  • Laptop and phone recordings — usually very good results, especially with the Standard preset.
  • Steady 50 or 60 Hz hum — only partly removed. Use the Equalizer to cut frequencies below about 80 Hz as well.
  • Full music mixes — cymbals, reverb and quiet instruments can sound dull or watery. Use Light if you must.

Start with the highest quality source you have. Heavily compressed audio gives the model less to work with.

AI Noise Reducer tips

Compare Original and Cleaned during a pause between sentences, where the noise is easiest to hear. If the voice starts to sound thin, lower Strength by 10–20%. If you still hear noise, raise it, or cut low rumble with the Equalizer.

After cleaning, you can trim the silence with the Audio Trimmer, adjust the speed with the Speed Changer, or raise the final loudness with the Volume Booster.

Frequently asked questions

Is this an AI noise reducer?

Yes. It runs RNNoise, a small neural network trained to tell speech from background noise. The model is compiled to WebAssembly and runs inside your browser tab, so no audio leaves your device.

What kinds of noise does it remove best?

Broadband noise: hiss from a preamp or tape, computer and fan noise, air conditioning, traffic and room tone. Steady mains hum at 50 or 60 Hz is only partly removed. For hum, use the Equalizer to cut the lowest frequencies.

Does it work on music?

It is built for speech. On a full mix it can make cymbals and reverb sound dull or watery, so use the Light setting and check the result on the chorus before you export.

What does the Strength setting do?

It blends the original with the cleaned version. 0% is the untouched recording and 100% is the full model output. Light, Standard and Strong are quick presets. Standard keeps most of the natural sound of the voice while removing the worst noise.

Why does my voice sound a little robotic at Strong?

Full strength removes more of the noise but can also take small pieces of quiet speech with it, especially breaths and soft consonants. Drop to Standard or Light and the voice usually sounds more natural.

Are my recordings uploaded anywhere?

No. The file is decoded, resampled and cleaned on your device. The cleaned file is encoded in the browser as MP3 or WAV and downloaded directly. Nothing is sent to Sound Booster servers.

How long does processing take?

The model runs faster than real time: in our tests a 10-second clip took under a second on a desktop browser. Longer files take proportionally longer, and the progress bar shows how far along the process is.

Which output format should I choose?

MP3 at 192 or 320 kbps is fine for podcasts, voice notes and video. Choose WAV if you will keep editing the file in a DAW or another audio editor, so the audio is not compressed twice.

Related tools

Keep editing in the browser after you clean the audio.