The plug-in
$149 one-time- Where it runs
- In your DAW, on the 2-bus.
- Control
- All 32 parameters under your hand.
- Cost detail
- No per-minute cost and no connection required once it is activated.
AI Music Artifact Remover
de-artifact
Bring rough AI audio into your mix. Reduce metallic shimmer and watery textures in generated tracks and separated stems. Shape harmonic and percussive cleanup in your DAW.
$149Regular price $179
Improves sound. Not a tool for passing AI detectors.
Hear it on a demo track
0:00 / 0:00Suno 032mix
Diff: The removed signal can include musical detail. It is not proof of pure AI artifacts.
Harmonic & percussive control. In your DAW.Hear it on real tracksPreview your track free
Specifications
Specifications last reviewed against the shipping build.
Full documentation — every control, preset and workflow, with screenshots.
Product details and community feedback on KVR Audio (opens in a new tab)
- Formats
- VST3 · AU · CLAP · AAX (Apple Silicon) Audio Unit is macOS only. For Pro Tools, the macOS installer includes an AAX build on Apple Silicon Macs (stereo inserts only); there is no AAX build for Intel Macs or Windows, and no standalone application.
- Latency
- ≈ 300 ms at 44.1 kHz About 325 ms at 48 kHz. Measured on macOS with 512-sample blocks (13,126 samples); a larger host buffer adds about 11.6 ms per extra 512 samples. Reported to the host, so plug-in delay compensation lines the session back up.
- Presets
- 14 factory Every preset sets all controls at once; save your own with Save As…. See all 14
- Platform
- macOS 11+ (Universal) · Windows 10 2004+ x64, AVX2 Apple Silicon + Intel in one .pkg. Windows needs a CPU with AVX2 + FMA (Intel Haswell 2013+ / AMD Ryzen 2017+) and the Microsoft Visual C++ 2015–2022 x64 runtime. Linux is on the roadmap.
- Min. spec
- Apple M1 / Intel i5 / Ryzen 5 · 8 GB Recommended: Apple M2 or later / Intel Core i7 / AMD Ryzen 7, and 16 GB+ for comfortable multi-instance use.
- Processing
- On your machine, in real time ArtifactUNet (3.6M params) runs on the audio thread alongside HPSS analysis. No connection required once the plug-in is activated.
Hear it on real tracks
Watch the plug-in in action
Two short comparisons with the working plug-in. Turn sound on; no upload needed.
Recorded with de-artifact AU 0.4.4. Offline processing replay; these clips do not demonstrate live latency. English and Korean captions available.
Compare Original, Cleaned and Diff
Pick a track and tap Original / Cleaned / Diff to A/B in place. Playback is synchronized across all three — no re-buffer, no click, no time jump. Diff plays only what de-artifact removed.
0:00/0:00
Suno 032 · change the track
Click this comparison panel or Tab into it to use shortcuts:
- 1
- Original
- 2
- Cleaned
- 3 or D
- Diff
- M
- Mix/Vocal
- Space
- play / pause
- ←/→
- ±5 s
Tip: if Diff sounds like music, the preset is too aggressive — lower Strength in the plug-in. Mix is the full bounce; Vocal is the htdemucs-separated vocal stem.
Diff: The removed signal can include musical detail. It is not proof of pure AI artifacts.
10 kHz1 kHz
10 kHz1 kHz
10 kHz1 kHz
Spectrograms are rendered for the Suno 032 demo track only. This track plays without them.
Spectrograms of the Suno 032 demo track (mix), rendered from the same Original, Cleaned and Diff files the player streams. Log frequency 150 Hz–20 kHz, time left to right, brighter is louder. Click or drag to move the playhead.
New to de-artifact? Start with your own track.
Watch the 3-minute walkthrough: upload, process, compare Original and Cleaned, then choose browser cleanup or the 14-day DAW plug-in trial. The no-account listening preview is up to 30 seconds.
More demos
Mixes, stems and older samples, before and after. Scroll sideways for more.
What does de-artifact do?
de-artifact is a VST3 / AU / CLAP plug-in that removes the artifacts AI music generators leave in a full mix: RVQ ghosting, codec residue and high-frequency aliasing from Suno, Udio, Stable Audio, MusicGen and Riffusion. It splits the audio into harmonic and percussive parts and applies a learned mask to each, on the master bus, with a 14-day free trial.
Is this the right tool?
de-artifact is a restoration tool, not a tone shaper. It looks for the specific damage that generative models and lossy codecs leave in a signal, and subtracts it. Everything below is what that does and does not cover.
Reach for it when
- A full mix came out of Suno, Udio, Stable Audio, MusicGen or Riffusion.
- You pulled stems out of a mix with htdemucs, Spleeter or similar — vocals especially.
- The only copy you have is a low-bitrate MP3, AAC or Opus file.
- You want a final polish pass on a master that contains any of the above.
Reach for something else when
- The problem is bleed — a vocal audible in the drum stem, content that does not belong to that track at all. That is de-leak. The two are frequently used on the same source.
- You are chasing one ringing resonance rather than a broadband residue. That is ENZYME.
- You want to rebalance harmonic against percussive content deliberately. That is Intrect HPSS, which is free and macOS-only.
- Your host is Pro Tools on an Intel Mac or on Windows. The AAX build is Apple Silicon only, so it will not load there.
What it will not do
- Rescue a badly written track
- It removes codec residue. Arrangement, performance and mix decisions are untouched, and a cleaned generation still sounds like the generation it came from.
- Work hard on clean material — by design
- Artifacts concentrate above roughly 3 kHz, where natural music has comparatively little energy, so the model is conservative on genuine acoustic sources by construction. On a bass stem it peaks at around 0.8 dB of reduction even at Strength 100 %. A near-flat reduction curve is a result, not a fault — reading it as a broken plug-in and cranking Strength is the most common way to damage a track.
- Separate stems
- It processes what you give it. Splitting a mix into parts is a separator's job, and cleaning the parts afterwards is what de-artifact is for.
- Run everywhere
- VST3, CLAP and Audio Unit on macOS 11+; VST3 and CLAP on Windows 10 2004 or later with an AVX2 + FMA CPU and the Microsoft Visual C++ 2015–2022 x64 runtime. AAX on Apple Silicon Macs only, as stereo inserts. No standalone application and no Linux build.
How it works
de-artifact runs three stages in series. The audio path stays the model's domain until the very end — clean residual subtraction with no manual EQ tricks.
- SplitHPSS splits the spectrum into tonal and transient components.
- MaskEach is masked independently by ArtifactUNet, a 3.6M-parameter forensic network trained on AI-generated music.
- SubtractThe masks drive adaptive spectral subtraction — energy below the noise floor is removed, music above it is preserved.
Audio in 44.1 kHzSTFTHPSS median filter
Harmonic
ArtifactUNet mask
Spectral subtraction
Percussive
ArtifactUNet mask
Spectral subtraction
SumISTFTAudio out
Per frame, in real time.
Features
Host-compensated latency
About 300 ms at 44.1 kHz (13,126 samples with 512-sample blocks, measured on macOS) and about 325 ms at 48 kHz. A larger host buffer adds about 11.6 ms per extra 512 samples. Reported to the host, so plug-in delay compensation lines the session back up.
4-band emphasis EQ
Drag spectrum handles to tell the model where to focus. The boost is fed only to the model — listener audio is auto-inverse-EQ'd, so tone is preserved.
Two monitor toggles
Bypass for A/B with the reported latency preserved, so the comparison stays sample-aligned. Residual plays only what is being subtracted — if you hear musical content in it, you are over-processing.
Dynamic resonance suppression
A soothe-style stage that tames narrow ringing peaks standing above the local spectral baseline. Depth, Selectivity and Threshold set how tight a peak must be and how far it has to rise before it counts — sibilance and harshness handled musically, rather than by a fixed band.
Separate harmonic and percussive control
The HPSS split gives the harmonic channel (vocals, synths, sustains) and the percussive channel (drums, transients) their own reduction strengths. Separation switches the median kernel between Normal (17) and Strong (31) for dense mixes.
14 factory presets
Every preset sets all controls at once; nudging a control afterwards marks the preset modified rather than snapping back. Save your own with Save As….
| Preset | Use it for | Character |
|---|---|---|
| Conservative | Subtle lossy-codec residue (MP3/AAC/Opus hash) | Barely touches the signal. Maximum transparency. |
| Balanced | General polish with a gentle hand | Light, even cleanup. |
| Default | General AI-generated / AI-separated material | The starting point — Strength 60 %. |
| Aggressive | Heavily artefact-laden AI tracks | Full strength plus resonance suppression. |
| Vocal | AI-separated vocal stems | Harmonic-weighted, transient- and sibilance-aware. |
| Gentle Reduction | Cleanup where transparency matters most | Very light touch with a soft mask floor — minimal colouration. |
| More Harmonics | Watery sustains and vocal smear | Maximum harmonic-channel reduction. |
| Soft Master Bus | Light artefact control on a finished mix | Wide, gentle cleanup — soft knee, slow release, strong resonance suppression. |
| Bring Your Breaks Bright Again | Old break / loop / acapella samples whose top octave was cut off | Strong separation, maximum harmonic reduction, no spectral floor, Brightness +0.54. |
| Nicerizer | AI-generated full mixes that need both the shimmer removed and the air put back | Firm reduction with Brightness +0.88 — the bandwidth-extension stage regenerating the top band. |
| Bmore | Break / loop material that needs the separation without added top end | Strong separation, percussive channel closed, no spectral floor, no Brightness. |
| de-chirp | Swept, tonal residue — chirp-like codec artefacts | Percussive-weighted reduction with a soft floor and Brightness +0.80. |
| Suno V6 | A full Suno V6 mix with generation residue across the whole track | Strongest of the set (Strength 1.60), full HF air, no spectral floor, 12 dB knee. |
| Stem Separation | A stem you already separated, where heavy processing would show | Gentle (Strength 0.60), Strong separation, percussive channel closed, soft floor. |
Three ways to run it
Same engine in all three. What changes is where it runs and how much of it you get to steer.
| The plug-in$149 one-time | Free onlineFree · no account | de-artifact CloudFrom $0.18 / minute | |
|---|---|---|---|
| Where it runs | In your DAW, on the 2-bus. | Upload one track and hear the result. | Full-length cleaning on our GPUs, from the browser. |
| Control | All 32 parameters under your hand. | Good for deciding whether this is the right tool before you spend anything. | One tuned preset rather than the full control surface — that part is what the plug-in sells. |
| Cost detail | No per-minute cost and no connection required once it is activated. | Free · no account. | Prepaid dollar credit, and Artist+ subscribers get $25 a month of credit included, shared with detection. An optional Clean + restore highs mode also generates the missing high end, at $0.75 per audio minute. |
| Try a track | See rates |
Free online
Free · no account- Where it runs
- Upload one track and hear the result.
- Good for
- Deciding whether this is the right tool before you spend anything.
de-artifact Cloud
From $0.18 / minute- Where it runs
- Full-length cleaning on our GPUs, from the browser.
- Control
- One tuned preset rather than the full control surface — that part is what the plug-in sells.
- Cost detail
- Prepaid dollar credit, and Artist+ subscribers get $25 a month of credit included, shared with detection. An optional Clean + restore highs mode also generates the missing high end, at $0.75 per audio minute.
Try it on your own audio
Drop any AI-generated audio and hear a 30-second A/B preview — free, no account needed. For full-length files there is de-artifact Cloud, or the plug-in itself.
WAV / MP3 / FLAC · max 50 MB · first run may take ~60s to warm up the GPU
Try it free for 14 days, buy when you're sold
14-day full trial — every preset, every parameter, no gaps. After 14 days the plug-in inserts a brief silent gap every 60 seconds until you activate.
de-artifact-0.4.10.pkg
macOS Universal · 118 MB
de-artifact-windows-x86_64-0.4.10-setup.exe
Windows installer · 22 MB
de-artifact-windows-x86_64-0.4.10.zip
Windows portable · 44 MB
macOS — Apple Silicon + Intel · Windows — x86_64 with AVX2 · Linux — roadmap
Not sure yet whether your track was AI-generated? Run it through the free AI music detector — no account, no upload of the master.
System requirements
ArtifactUNet (3.6M params) runs on the audio thread alongside HPSS analysis, keeping a generous real-time margin even on entry-level Apple Silicon.
- macOS
- Universal Binary — Apple Silicon (arm64) + Intel (x86_64) in one .pkg · macOS 11 (Big Sur) or later
- Windows
- Windows 10 2004 or later, 64-bit · CPU with AVX2 + FMA (Intel Haswell 2013+ / AMD Ryzen 2017+) · Microsoft Visual C++ 2015–2022 x64 runtime · .exe installer · VST3 + CLAP
- CPU
- Minimum Apple M1 / Intel Core i5 (4-core, 2.0 GHz+) / AMD Ryzen 5 · Recommended Apple M2 or later / Intel Core i7 / AMD Ryzen 7
- RAM
- Minimum 8 GB · Recommended 16 GB+ (multi-instance comfortable)
- Disk space
- Minimum ~150 MB (plug-in + ONNX models)
- Audio buffer
- Minimum ≥ 256 samples · Recommended 1024 samples for tracking
- Sample rate
- Any — rubato resampler 8 k–384 k. Internal model runs at 44.1 kHz.
- Hosts (macOS)
- VST3: Live, Reaper, Bitwig, Studio One · AU: Logic Pro, GarageBand, MainStage · CLAP: Reaper, Bitwig · AAX: Pro Tools (Apple Silicon, stereo)
- Hosts (Windows)
- VST3: Live, Reaper, Bitwig, Studio One, FL Studio · CLAP: Reaper, Bitwig
- Logic / Pro Tools
- AU supported, so Logic and GarageBand are covered. For Pro Tools, the macOS installer includes an AAX build on Apple Silicon Macs (stereo inserts only); there is no AAX build for Intel Macs or Windows.
- Linux
- Roadmap.
FAQ
- Why does the first ~1 second go silent on a freeze / bounce?
- The plug-in reports about 300 ms at 44.1 kHz for host PDC (a little more at higher sample rates or with a larger host buffer). During Live's freeze the host signals offline mid-stream, and the worker thread re-primes for one block. Output is correct from the first audible frame onward.
- The Residual monitor sounds different on each play. Bug?
- Phase of the residual depends on chunk-grid alignment — same SR + same transport start gives bit-identical phase. Spectrum and RMS are stable across runs; only the per-sample residual rotates.
- The result sounds dull. What knob fixes that?
- Raise Brightness. The model removes energy in the highs because that is where artefacts live, and de-artifact already measures how much it took out and restores it automatically. Above 0, Brightness adds neural bandwidth extension on top of that — a small network regenerates the 8–22 kHz band from the cleaned signal. Negative values darken instead, scaling the automatic recovery down. If it still sounds dull, lower Strength from its 60 % default, or load Gentle Reduction, which uses a soft mask floor for minimal colouration.
- I'm getting dropouts on an M1 8 GB.
- Lower Strength first — it is the cheapest change that reduces work — then raise your host's audio buffer (512 → 1024 or higher), which is almost always the simplest fix on a lower-power machine. Setting Separation back to Normal costs less CPU than Strong. Freeze or bypass other heavy plug-ins on the chain; total plug-in latency feeds back into the host's buffer math. Since 0.4 the build runs the artifact model frame by frame on the CPU on every platform, Apple Silicon included, and reports about 300 ms at 44.1 kHz. The 0.3.4-era Neural Engine chunk path — 2.7× to about 31× real-time headroom on an M1 Max — is still reachable, but it is no longer the default.
- Will de-artifact lower ArtifactNet's AI probability?
- No. de-artifact is designed to improve sound, not to minimize ArtifactNet or any other detector score. Processing changes the signal a detector receives, so the reported probability can move either up or down. A higher post-processing score does not mean the track became more AI-generated, and the score is not a measure of sound quality or how many audible artifacts were removed.
- Is there a free trial?
- Yes — 14 days of full quality with no gaps, every preset, every parameter. The same installer becomes the licensed build the moment you drop in a key. After the 14-day trial the plug-in inserts a brief silent gap every 60 seconds until you activate.
- Do I need a plug-in to remove AI artifacts?
- No. de-artifact also runs as de-artifact Cloud — full-length cleaning on our GPUs, driven from the browser — so you can remove AI artifacts from a full-length track without installing anything. The plug-in is the option for working inside your DAW with all 32 parameters under your hand.
Further reading
Learning resources
Symptom guide and listening checklist
Pick the symptom you can hear, then check whether cleanup is subtracting music.
Press kit
Fact sheet and coverage
Specifications, official screenshots and third-party release coverage.
Guide
How to Fix AI Music Artifacts
RVQ ghosting, codec residue, HF aliasing — causes and fixes.
Guide
How to Detect AI-Generated Music
Listening cues, spectrogram tools, and ArtifactNet benchmark.
Comparison
Best AI music detection tool (2026)
Eight public detectors on one 2,104-file test set, at fixed thresholds.
Try it on your next AI track
One license, all formats. Free updates within v1.x.