VERA Model V-1.1 · audio analyser Checking on her

An audio engine with a music writer's ears. Tune her to a song.

Measured on signal
Read by ear
Checked against the catalogue
Vera, a little VU meter with a face
Standing byTune me
Vera
Audio analyser · V-1.1
---BPM
--KEY
---LUFS
-/-TIME
Energy
Headroom
 

How she works, and how sure she is.

Vera is my own audio engine. I built her because I wanted to work out how and why a track hits the way it does. She runs on my laptop on free everything, and she labels every single thing she tells you.

Measured

Tempo, key, loudness, the energy curve. Straight signal processing, so trust these.

Her read

Genre from sound, the feel, danceability, the notes. Model and rule based: check them against your ears.

Catalogue fact

Year, album, credits, catalogue BPM and genre tags, looked up in Deezer and MusicBrainz.

Her blind exam
1,137 songs · 18 genres · six decades · 30 second clips · no catalogue help
Tempo, exact75%
Tempo, half or double ok92%
Genre in the right family68%
Key, test chords in all 24 keys24/24
Key follows a pitch shift84%

Tempo is marked against the catalogue BPM (510 of the songs have one). Genre is checked on songs her genre model never saw during training. Published as measured, misses and all. When she recognises a song, tempo, year and genre come from the catalogue instead, which is why searching is the best way in.

What changed in November 2026

She was giving every song the same tags, because the model behind her has favourite words it reaches for whatever it hears. Billie Jean and Adele both came back as blues and "good for meditation". Now each tag is measured against how typical songs score (about 230 chart previews across 18 genres), so she only says what's distinctive about this one.

She also used to guess the decade from the sound and got it right 1 time in 5 (Bohemian Rhapsody went in the 1950s). Now the year only comes from the actual release. And she stopped calling pop songs 5/4.

Then she sat a blind exam of 1,137 songs. It caught her calling 27% of everything "latin" and 21% "blues", so genre is now learned from about 900 labelled songs instead of guessed from word prompts: right family 68%, and no single genre takes over. A new tempo picker stopped her hearing 120 BPM as 81. And she no longer calls a song "programmed", because her timing measure couldn't tell a drum machine from a tight band.

How she improved, before and after

Updated 17 November 2026. Same test each time, old version of her against new, so you can see what actually moved.

  • Genre: right family 63% when she guessed from word prompts, 68% once she learned it from 898 labelled songs, checked on songs she never trained on (12 November). Her favourite label used to be "latin" on 27% of songs. Now no label tops 7%.
  • Tempo: on my fixed set of 30 songs, within 5 BPM with half or double time allowed: 71% in July, 86% after the new tempo picker (12 November). Average miss down from 6.98 BPM to 3.64.
  • Key: key and major or minor right on the same 30 songs: 60% to 70% once she listened to the harmony without the drums in the way (July).
  • Tags: every tag is now measured against a baseline of 234 chart songs, so she only tells you what's unusual about this one.

The exam above is the big one: 1,137 songs she'd never heard. The 30-song set is small, so treat it as a trend, not a trophy.

Identity and credits

Search results come straight from Deezer's public catalogue with a 30 second preview, which she listens to. Uploads are fingerprinted and matched against AcoustID and MusicBrainz. Credits and community genre tags come from MusicBrainz where its editors have filled them in, so a missing credit means undocumented, not that nobody did the job. Listen links go to Apple Music and Deezer directly and to a search on Spotify and YouTube Music. No Spotify anywhere in her analysis.

Chord lineage

She detects the chord progression and matches it against a curated list of historically significant progressions, naming the family and where it comes from. She runs it twice, on the whole mix and on the bass alone, to catch a twelve bar blues under a wall of guitars. It only shows when she finds a confident match.

Where else she works

She's the engine inside everysong, where she finds free music that sounds like the song your edit was cut to, maps the beat for the whole track and checks whether a swap will keep your cuts on time.

The JSON, versions and licensing

Every readout is the same versioned JSON shape (vera.version), signed so you can prove it came from her. Built on permissively licensed open source, no GPL. Her algorithms, prompt sets and taxonomies are mine.

Running your own copy of the engine? Point this page at it: