Free Audio Noise Remover
Audio Noise Remover cleans fans, hum, traffic and room chatter from voice recordings and from the sound of videos. Choose the Standard, High quality or Light engine, compare original and cleaned audio, then save WAV, MP3 or the video with its new soundtrack. The open-source RNNoise and GTCRN models are small WebAssembly files that run on your device.
- Engines:
- RNNoise, GTCRN hybrid, SpeexDSP
- Output:
- WAV, MP3 or video with clean audio
- Live mode:
- Real-time microphone cleanup
- Price:
- Free
- Runs:
- AI model in your browser
- Uploads:
- None: files never leave your device
- Account:
- Not needed
Quick answers
Is my audio uploaded?
No. The noise-removal models are small WebAssembly files that run in your browser; your recording never leaves your device.
What kind of noise can it remove?
Background noise behind speech: fans, air conditioning, traffic, hum, hiss, keyboard clicks and room chatter. It is designed for voices, not for removing instruments from music.
Processed on your device: your files are never uploaded. How it works
Network activity in this tab
What this page has requested since you opened the site in this tab. An upload is any request that sends data: POST, PUT, PATCH or a request with a body.
No uploads: nothing has been sent from this page.
No network requests yet.
To see every request, open your browser's developer tools (Network tab).
How to use the Audio Noise Remover
- Drop a voice recording or a video (or switch to Live microphone to hear the effect in real time).
- Choose the engine: Standard for steady noise, High quality for voices in busy places, Light for a gentle clean-up.
- Click Remove noise, then compare A (original) and B (cleaned) while listening; adjust strength, high-pass or the gate and clean again.
- Download WAV or MP3, or the video with its sound replaced.
Credits & open source
Open-source AI model running in your browser. Thank you to the people who make these projects.
- web-noise-suppressorAudioWorklet noise suppression (RNNoise, GTCRN, Speex) compiled to WebAssembly. © 翠 / green (sapphi-red); includes RNNoise (Xiph.Org, Jean-Marc Valin; BSD-3-Clause), SpeexDSP (Xiph.Org; BSD-3-Clause), GTCRN (Rong Xiaobin; MIT) and the PFFFT FFT library (Julien Pommier; FFTPACK-derived BSD-like license) · MIT
- wavesurfer.jsAudio waveform display with selectable regions. © katspaugh and contributors · BSD-3-Clause
- MediabunnyReads, writes and converts media files with WebCodecs (MP4, WebM, MKV, MOV, MP3, WAV, Ogg...). © Vanilagy and contributors · MPL-2.0
- lamejsMP3 encoder (port of LAME), loaded as a separate unmodified chunk. © LAME project; JavaScript port by Alex Zhukov; ESM fork by Breezystack · LGPL-3.0
Web platform APIs used: Web Workers, WebAssembly, AudioWorklet, Web Audio API, Media Capture (getUserMedia), WebCodecs, File API, localStorage.
- RNNoise model weights by Jean-Marc Valin / Xiph.Org Foundation (rnnoise-wasm build by Shiguredo Inc.) (BSD-3-Clause (rnnoise-wasm Apache-2.0)) — Standard engine and the high band of the High quality engine
- GTCRN speech enhancement model by Rong Xiaobin (GTCRN); WebAssembly build by sapphi-red (MIT) — High quality engine (band below 7 kHz)
- SpeexDSP preprocessor by Xiph.Org Foundation, Jean-Marc Valin and contributors (BSD-3-Clause) — Light engine
Full license texts: third-party notices · all credits
Frequently asked questions
The voice sounds a bit processed: what can I do?
Lower the strength to 70–85% to mix some of the original back in, or try the Light engine.
Can I clean the sound of a video?
Yes. Drop the video, remove the noise and use Video with clean audio: the picture is copied untouched and only the soundtrack is replaced.
Does it work live?
Yes: Live microphone mode lets you hear the cleaned microphone in real time with headphones, with a bypass switch to compare.