Free AI Music Detector
AI Music Detector checks songs for evidence of AI generation without uploading them. It validates C2PA Content Credentials offline, reads ID3, Vorbis, MP4, RIFF and XMP tags for traces of Suno, Udio, ElevenLabs, Stable Audio and many more services, and measures the sound as context. A whole batch of songs exports as a JSON report or a CSV table.
- Evidence:
- C2PA, AI tags, sound analysis
- Formats:
- MP3, WAV, FLAC, M4A, OGG, Opus, AIFF, videos
- Batch:
- Up to 100 files, JSON or CSV report
- Price:
- Free
- Runs:
- Locally, in your browser
- Uploads:
- None: files never leave your device
- Account:
- Not needed
Quick answers
Can this tool prove that a song was made by people?
No tool can. It reports what the file says about its origin: signed Content Credentials, tags naming AI services and some sound measurements. When nothing is found, the song may still be AI-generated, because most services write little metadata and uploads and conversions strip it.
How does it recognize songs from Suno, Udio or other generators?
First from C2PA Content Credentials, which some services now sign into their downloads; then from names, song-page links and 'made with AI' labels in ID3, Vorbis, MP4, RIFF and XMP tags.
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 AI Music Detector
- Drop one or many songs (MP3, WAV, FLAC, M4A, OGG, Opus, AIFF…) or video files.
- Read the verdict of each file: Content Credentials, AI tags or no provenance data.
- Open Details to see the signed history, every tag, the spectrogram and the sound measurements.
- Export the results of the whole batch as a JSON report or a CSV table.
Credits & open source
Our own code plus open-source libraries. Thank you to the people who make these projects.
- music-metadataReads tags and technical metadata of audio files (ID3, Vorbis, MP4, RIFF...). © Borewit and contributors · MIT
- c2pa-web (Content Credentials)Reads and validates C2PA Content Credentials in images (WebAssembly, self-hosted from /vendor/c2pa). © Adobe and the Content Authenticity Initiative; built on c2pa-rs (MIT OR Apache-2.0) · MIT
- fflateFast ZIP compression for batch downloads. © Arjun Barrett · MIT
- MediabunnyReads, writes and converts media files with WebCodecs (MP4, WebM, MKV, MOV, MP3, WAV, Ogg...). © Vanilagy and contributors · MPL-2.0
Web platform APIs used: Web Workers, WebAssembly, Web Audio API, Canvas 2D, File API, Clipboard API.
- C2PA trust list by Coalition for Content Provenance and Authenticity (C2PA) (CC-BY-4.0) — certificate authorities used to validate Content Credentials signers offline
Full license texts: third-party notices · all credits
Frequently asked questions
Are my files uploaded?
No. Tags, Content Credentials and the sound are read in your browser. Links found in the tags are listed but never opened.
Why is there no AI classifier?
The open models for detecting AI music are trained on non-commercial data or rely on patent-pending methods, and they only recognize the generators they were trained on. This tool sticks to the evidence stored in the file and shows sound traits only as hints.
Can it detect SynthID or other invisible watermarks?
No. Audio watermarks such as Google's SynthID can only be checked with the detectors of the companies that embed them. This tool reads the provenance data stored in the file and measures the sound.
Does it work with videos?
Yes. Drop an MP4, MOV, WebM or MKV file: its metadata and Content Credentials are read and its sound track is decoded and measured like a song.