Local audio analysis

AI Music Detector

Inspect a song’s frequency spectrum, dynamics, rhythm, and metadata for patterns sometimes associated with AI-generated music. See the measurements behind every score.

Private audio analysis with a heuristic score

Analysis runs entirely in your browser. Your audio never leaves your device. The score summarizes clues from this file. It gives no calibrated probability of AI generation and cannot serve as forensic or legal proof.

Drop an audio file here

MP3, WAV, FLAC, M4A, or OGG · Up to 50 MB

A short browser-synthesized clip for exploring the tool.

How it works

  1. 1

    Choose a file

    Drop a supported recording or try the synthetic demo. Your browser decodes it locally.

  2. 2

    Inspect the signals

    Play the preview and follow it on the spectrogram. Read the four cards to see which measurements contributed to the score.

  3. 3

    Keep a record

    Copy the report with the measurements and caveats. For attribution, compare it with release credits, project files, or a documented source.

Heuristic signals guide

High-frequency cutoff & artifacts

The spectrum shows where energy falls away. A sharp drop near 15–16 kHz can follow generation, an MP3 export, resampling, or a filter applied during mastering.

Dynamic range & compression

A low peak-to-RMS ratio and a narrow loudness spread suggest a consistently dense signal. Limiters and modern pop or EDM mastering can produce the same pattern.

Rhythm regularity & stereo coherence

Repeating onsets, close agreement between channels, and stable high-frequency phase can also come from drum machines, quantization, or centered mixing.

Metadata & encoder

Generator names in software or comment fields are leads worth checking. Generic encoders describe how a file was packaged. Studio tags and ISRCs describe its production or catalog context. Any of these tags can be edited.

Compare AI music detectors

Choose based on the audio you can share, the measurements you need, and how many tracks you plan to review.

This Local Heuristic Inspector

Method
Signal measurements and embedded tag rules.
Privacy & upload
Audio stays in your browser.
Access & cost
Free, with no account. Up to 50 MB per file.
Strengths
Shows the measured values, spectrogram, and matched tags.
Limitations
Codec, mastering, and editing can mimic the signals. No trained classifier or generator attribution.

SubmitHub AI Song Checker

Method
Combines spectral and temporal models.
Privacy & upload
Accepts streaming links or direct uploads. SubmitHub says direct uploads stay on its servers until you delete them.
Access & cost
Limited free checks. SubmitHub Plus raises usage limits.
Strengths
Song-level score, with vocal and instrumental results when available.
Limitations
Requires at least 30 seconds. Mixed and heavily processed tracks can be harder to interpret.

IRCAM Amplify

Method
AIMD analyzes audio for artifacts and model indicators.
Privacy & upload
Hosted processing and API integration. Handling depends on the service agreement.
Access & cost
Business access by application. Pay-as-you-go starts at 2,000 tracks.
Strengths
Designed for high-volume catalogs and distributor workflows.
Limitations
Onboarding and contract terms apply. Results support human review.

Hive Moderation

Method
Music and vocal classifiers return timestamped confidence scores and supported generator labels.
Privacy & upload
Send audio or video to Hive through its demo or API.
Access & cost
Public detection demo. Ask Hive about production music detection access and pricing.
Strengths
Shows how scores vary through a clip and separates music and vocal classification.
Limitations
Attribution is limited to supported classes. Hosted use requires sending the media to Hive.
FAQ

AI music detector FAQ

Can this tell me for sure if a song is AI-generated?

No. The score summarizes measurable patterns that can also appear in human recordings. A low score does not establish human authorship. For attribution, look for production records, credits, and original project files.

Does my audio get uploaded or saved?

The detector reads, decodes, and analyzes audio in your browser. It does not upload or persist the audio or report. Copying a report places the text on your device’s clipboard.

Which files and lengths can I analyze?

Use an MP3, WAV, FLAC, M4A, or OGG file up to 50 MB. Decoding depends on browser codec support. The detector samples up to 60 seconds across long recordings and gives clips under one second less weight.

What does a cutoff near 16 kHz mean?

A cutoff shows a drop in high-frequency energy. Compression codecs, sample-rate conversion, recording equipment, and mastering filters can all cause it. Try an earlier lossless export if you have one.

What if there are no tags or I only see FFmpeg or Lavf?

Tags can be stripped during export. FFmpeg and Lavf describe how a file was encoded or packaged and do not raise the score. A generator tag raises the indicator, but tags can be edited.

Will this identify Suno, Udio, or a song with AI vocals?

The metadata panel can show a generator name if an available tag mentions it. The audio heuristics do not identify a model or isolate vocal stems, so hybrid recordings can get any score.