a music model does exactly what you ask, which is the problem. ask for "cool" and you get someone else's idea of cool. the gap isn't the model, it's that you can't name the thing in your head. so we go aspect by aspect. you hear two versions back to back, you feel the difference, you learn the word for it. then you watch that word go into a prompt and change the output. hear it, name it, prompt it.
most people write bad music prompts because they can't hear what they want, so they type "make it cool". TYPE / TEACHER trains your ear one aspect at a time, then hands you the words to steer a model. hear it, name it, prompt it.
Why this exists
three blocks per aspect. hear it plays two or more versions where one thing changes and everything else is frozen, so your ear can only blame that one thing. name it gives you the words producers actually use. prompt it shows a weak prompt rewritten with those words. it all runs on the same synth the instrument uses, client side, no signup.
The aspects
The modules
Common sounds
the aspects above are how a sound behaves. these are the parts themselves, the building blocks you stack in a track. name the part, then name its timbre and feel, and a model knows what to reach for.
In a real song
the aspects don't live in a vacuum, they're all in every song at once. pick a track you know and see how each one shows up, in the same words the lessons taught. the audio is a synthetic sketch, not the record, so you hear the feel without the copyright.
Visualizer
the real recorded stems of a phonk beat, played in the browser. up top the visualizer listens to the audio and each instrument fires on its own hit; below, the song-map sweeps the piano roll, arrangement, chords and frequency map off one playhead. solo or mute any part, click anywhere to scrub.
Can you hear it?
two clips, the same except for one thing. play A, play B, then call which one is brighter, faster, busier, darker. it's the hear-it drill with the answer hidden. build a streak, then go learn the word behind each one.
Train
two halves in one trainer. the ear drills name what you hear: the interval between two notes, a scale degree against a key, a chord's quality, a short melody. the read drills name what you see and play it: sight-read a note on the staff, then read a one or two-bar rhythm and clap it against a click. your call each time, and it keeps your best streak per drill.
Rhythm
drummers learn to read rhythm with words, not math. each fruit is one beat: Lemon is two even notes, Watermelon packs in four, Banana is a triplet. tap a fruit to hear it, then take the quiz and name the rhythm you heard.
Speak in music
in 1827 François Sudre tried to build a whole language out of the seven notes. this is a toy that runs with the idea: type anything and hear it sung back as a melody, one note per letter, in rainbow solfege. it's a party trick, not a lesson.
The Golden Ratio
experience the Golden Phyllotaxis Mode: an 8-tone microtonal scale mapped around the spiral geometry of the Golden Ratio. it divides the octave into dual-interval "Large" and "Small" irrational steps. play the keyboard, hear the organic intervals of nature, and see the spiral grow.