Turn your singing voice into printable notes (in the browser)

busssard2 pts1 comments

Voice → Notation

Voice → Notation

Sing into the mic. The metronome sets the grid; whatever pitch you hold in each subdivision gets written down.

Start listening<br>Stop<br>Clear score

0.0 Hz

&minus;50&cent;in tune+50&cent;

Your fundamental, drawn against staff positions. Vertical lines are beats; darker ones are downbeats. Dots are pitches committed to the score; a red stem through a dot means it heard a re-attack and wrote a new note rather than tying.

Score

MusicXML<br>ABC<br>SVG<br>Print

Clef

Auto (fewest ledger lines)<br>Treble<br>Treble 8vb (tenor / male voice)<br>Bass

Key

Auto-detect<br>C / a — no accidentals<br>G / e — 1 sharp<br>D / b — 2 sharps<br>A / f# — 3 sharps<br>E / c# — 4 sharps<br>B / g# — 5 sharps<br>F / d — 1 flat<br>Bb / g — 2 flats<br>Eb / c — 3 flats<br>Ab / f — 4 flats<br>Db / bb — 5 flats

Nothing written yet.

Copy<br>Download<br>Close

Metronome & detection

Tempo 90 BPM

Grid

quarter notes<br>eighth notes<br>sixteenth notes

Beats per bar

2346

Pitch tolerance &plusmn;50 &cent;

Noise gate 0.003

Click volume 40%

Re-attack sensitivity 0.45

Re-attack sensitivity decides whether two same-pitch cells are one held note<br>or two repeated notes. It listens for the dip in volume between them: a note is split when the<br>quietest moment at the boundary falls below this fraction of the note's own loudness. Raise it to<br>split more eagerly, drop it to 0 to never split — everything then becomes one long tied note, as before.<br>Sing repeated notes on separate syllables ("ta-ta") and it works; sing them legato on one vowel and<br>nothing in the signal distinguishes them from a held note.

Use headphones — otherwise the click bleeds into the mic. The noise gate ignores anything quieter than the threshold; the tolerance rejects pitches further than that from a real semitone, which cuts slides and scoops.

Input device & signal analysis

Input device<br>Default input

Scan inputs for signal

Secure context—

Inputs found—

Mic track—

Sample rate—

Input peak—

Input RMS—

Detector—

notes note input voice sharps flats

Related Articles