How do I detect if a song was made by AI?

Upload the audio file (MP3, WAV, FLAC, etc.) or paste a YouTube URL at demo.intrect.io. ArtifactNet separates the track into harmonic and percussive components, computes a spectral residual with a U-Net, and scores every 4-second segment with a 7-channel CNN. The page shows a verdict (AI / Human-Made / Partial AI) with a probability, per-segment scores, and a forensic feature radar — all in a few seconds.

Which AI music generators can ArtifactNet detect?

ArtifactNet is trained on tracks from Suno, Udio, Stable Audio, Riffusion, MusicGen, and a residual 'other' class, and it generalises to AI models it has not seen because it targets spectral-residual artefacts left by STFT-domain generators rather than model-specific fingerprints.

Is ArtifactNet free? Do I need to sign up?

The demo is free and requires no signup. Rate limits apply per IP (5 tracks/day, 3/hour, 1/min). Sign in for 10 tracks/month free. A paid API (api.intrect.io) is available for batch processing and integrations.

Does ArtifactNet store my uploaded audio?

No. The demo operates on a zero-retention policy. Your audio is streamed to a GPU worker, analysed in memory, and discarded. Only if you press the Report button to tell us a verdict is wrong do we save the spectral analysis (and, if you tick the optional box, the original audio) to investigate.

How accurate is ArtifactNet?

ArtifactNet reports 99.82% accuracy on its internal balanced evaluation set (2026 Q2, v9.5). False positive rate on real human music — including rare genres — is the main target of ongoing retraining. The demo lets you report suspected misclassifications so they can be used to improve the detector.

Can I analyse a YouTube song without downloading it?

Yes. Switch to the 'YouTube URL' tab at demo.intrect.io, paste the link, and press Analyze. The server downloads up to 50 MB of audio via yt-dlp, analyses it, and discards the file. Only the verdict and forensic numbers are kept in a 1-hour server-side cache so you can submit a Report.

What does the forensic feature radar show?

The radar plots six summary signals from the analysis: mean and median AI probability across segments, consistency (how uniform the verdict is), high-frequency residual energy, U-Net mask strength, and harmonic share. Together they reveal why the model reached a given verdict and expose edge cases.

Why did ArtifactNet flag my own song as AI?

Heavy spectral processing (strong multi-band limiting, resampling through AI-era codecs, aggressive stereo widening) can produce residuals that resemble AI-generated artefacts. Hit the Report button and choose 'Human-Made' with a short note — a human reviewer will look at the spectral residual and the case can be used to improve the classifier.

Free AI Music Detector — ArtifactNet Demo by Intrect

About ArtifactNet

ArtifactNet is a free online tool that detects AI-generated music. Upload an audio file or paste a YouTube URL and get an AI-vs-Human verdict in seconds, with per-segment probabilities and forensic feature readings. 99.82 % accuracy on the internal balanced evaluation set (2026 Q2, v9.5). Zero-retention — audio is not stored unless you submit a Report.

What it detects

ArtifactNet is trained on tracks from Suno, Udio, Stable Audio, Riffusion, and MusicGen, with a residual other class for unseen generators. It targets STFT-domain residual artefacts rather than model-specific fingerprints, so it generalises to AI models it has not seen during training.

How it works

Decode the track to 44.1 kHz mono and split into 4-second overlapping chunks.
A codec-aware U-Net predicts a spectral residual mask that isolates AI artefacts.
HPSS (median-filter harmonic/percussive separation) runs on the residual.
A 7-channel CNN scores every chunk — 0 means clearly human, 1 means clearly AI.
The median across chunks becomes the track verdict. Outlier distributions are labelled Partial AI.

FAQ

How do I detect if a song was made by AI?: Upload the audio file at the top of this page or paste a YouTube URL. The demo returns a verdict with probability, a per-segment timeline, and a forensic feature radar in a few seconds. No signup.
Is this free?: Yes. The demo is free and does not require an account. Anonymous use is rate-limited per IP — 5 tracks/day, 3/hour, 1/minute. Signing in with Google lifts the cap to 10 tracks/month. For batch processing or integrations, see the paid ArtifactNet API.
Do you store my audio?: No. The demo operates on a zero-retention policy. Your file is streamed to a GPU worker, analysed in memory, and discarded. Only if you press the Report button is the (anonymised) spectral analysis saved — and only then. Full details in the Privacy Policy.
Which AI generators does it detect?: Trained explicitly on Suno, Udio, Stable Audio, Riffusion, MusicGen. Generalises to unseen generators via residual-artefact targeting.
Can I analyse a YouTube song?: Yes — switch to the YouTube URL tab above, paste the link, press Analyze. The server downloads up to 50 MB of audio, analyses it, and discards the file.
How accurate is it?: 99.82 % accuracy on the internal balanced evaluation set (2026 Q2, v9.5 CNN + v9.4 codec-aware U-Net). False positives on rare human-made genres are the main retraining target — please Report any you find.
Why did it flag my own song as AI?: Heavy spectral processing (aggressive limiting, AI-era codec resampling, extreme stereo widening) can mimic AI residuals. Use the Report button with Human-Made and a short note so we can investigate and improve the detector.
Is there an API?: Yes. api.intrect.io exposes the same detector as a REST API with batch processing, designed for distributors, labels, and streaming platforms.

AI Music Detector — Forensic Analysis

1. Choose input

2. Result

Think this is wrong?

About ArtifactNet

What it detects

How it works

FAQ