An abstract pigment painting shaped by the sound, its dynamics and its structure.
RHYTHMENERGYSPECTRUMHARMONY
Generative Music Analysis
Turn any song into visual DNA.
MusicDNA turns a track into a 3D sound genome, painted in real time from rhythm, energy, spectrum, and structure. A 2D mode is also available for clean share cards.
No random dataAnalyzed in the browserNo account
🎵
No tracks found.
Add an audio file to /public/music and update manifest.json to start.
- 1Add an .mp3, .wav, .ogg, or .m4a file to /public/music
- 2Add an entry to /public/music/manifest.json
- 3Reload the app
- 4Select the track and click Analyze
Seven visualization modes
Each mode is driven by real, deterministic analysis.
A DNA-like helix written by the song. Opens in 3D by default with rotate, zoom, auto-rotate, and camera reset. A 2D mode is available for clean share cards. Beat rungs, energy pulses, and section markers are all driven by real analysis.
RHYTHMSTRUCTUREENERGY
A layered audio terrain. Amplitude ridges become mountains, RMS energy forms foothills, spectral bands paint the slopes, and beats pin the horizon.
DYNAMICSSTRUCTURE
Onsets become stars on a bar-phase × time map. Downbeats anchor the sky, syncopation draws arcs, density forms clouds, sections tint the regions.
MOTIFSRHYTHM
Bass, mids, and highs flow as three aurora curtains. A centroid line traces brightness, harmonic peaks glow, and highs scatter as shimmering particles.
TIMBRESPECTRUM
Chroma vector paints a wheel of tonal weight. Layers grow with harmonic density.
TONALITYHARMONY
Rhythm, timbre and dynamics shape different cities: streets, squares, gardens or waterfronts.
STRUCTURESONG
How MusicDNA works
Four steps from sound to signature.
- 1
Choose a track
Pick any audio file from your music folder.
- 2
Decode the audio
We decode the file with the Web Audio API in your browser.
- 3
Extract real features
Rhythm, energy, spectrum, harmony, and structure are extracted from the signal.
- 4
Generate visual DNA
Deterministic visualizations are rendered from the real analysis.
Visualizations are deterministic. The same file always produces the same DNA.
Compare two tracks
Analyze two tracks side by side and compare BPM, energy, brightness, dynamics, structure, mood, and key moments. MusicDNA helps you understand how two pieces of audio differ, locally in your browser, without uploading your files.
A
Track A
Track A
Start from the selected track
B
Track B
Pick or upload a second track
- BPM, energy, brightness and dynamics, side by side
- Normalized 0-100% timeline alignment
- Real similarities and differences from the audio
What MusicDNA reads
Every visual is rooted in measured signal features.
Waveform
01Downsampled peaks and RMS envelope across the track.
Signal analysis method
Downsampled peaks and sliding window RMS power envelope
Rhythm
02Onset strength, beat times, and BPM estimate via autocorrelation.
Signal analysis method
Spectral flux onset detection with autocorrelation tempo tracking
Spectrum
03FFT frames, spectral centroid, flux, and low/mid/high balance.
Signal analysis method
Short-Time Fourier Transform (STFT) with spectral centroid and flux
Harmony
04Chroma vector and key estimate via Krumhansl-Schmuckler profiles.
Signal analysis method
12-bin Chroma vectors matched against Krumhansl-Schmuckler profiles
Structure
05Section boundaries from spectral and energy novelty.
Signal analysis method
Novelty curve self-similarity matrix for section boundaries
Dynamics
06Loudness curve, dynamic range, loudest and quietest moments.
Signal analysis method
EBU R128 integrated loudness curve and crest factor dynamics
Not every feature is available for every track. Uncertain values are clearly labelled as estimates.
How this signal is extractedWhy visual DNA matters
What music looks like changes how you listen.
See the structure
Discover where a track builds tension, slows down, and reaches its peak.
Compare sounds
Spot differences between versions, mixes, and tracks at a glance.
Create visual artifacts
Generate cards, posters, and DNA images from the songs you love.
Analyze without guessing
Every metric is derived from the real audio signal, not invented.
About MusicDNA
MusicDNA turns sound into a visual fingerprint, built entirely from real audio analysis on your device.
No account
No sign-up. No tracking. No upload step.
No random data
Every metric is derived from the real signal.
Analyzed in the browser
Decoding and feature extraction happen on this device.
Export on your terms
Share cards and JSON only when you choose to.
All metrics come from analysis of the selected audio file. Estimated values are labelled. If a value cannot be computed reliably, we do not show it as a fact.
Start Exploring
Ready to turn sound into visual DNA?
Select any track from your library or experiment with our analysis algorithms in real time.