Add audio-to-MIDI import via Basic Pitch (MP3, WAV, M4A, OGG, FLAC, AAC), fix piano remount on view change

This commit is contained in:
Fabricio Giglio
2026-05-17 08:10:03 +02:00
parent 9d2991a916
commit 6de3c8d98e
6 changed files with 134 additions and 47 deletions
@@ -30,6 +30,7 @@ export function TransportControls() {
loadMidiFile,
loadMusicXmlFile,
loadPdfFile,
loadAudioFile,
isLoadingDocument,
loadingMessage,
exportMidi,
@@ -87,6 +88,7 @@ export function TransportControls() {
if (file.name.match(/\.midi?$/i)) loadMidiFile(file);
else if (file.name.match(/\.(xml|mxl)$/i)) loadMusicXmlFile(file);
else if (file.name.match(/\.pdf$/i)) loadPdfFile(file);
else if (file.name.match(/\.(mp3|wav|m4a|ogg|flac|aac)$/i)) loadAudioFile(file);
};
const total = doc?.totalDuration ?? 0;
@@ -209,8 +211,8 @@ export function TransportControls() {
>
{/* ── Zone 1: File import - accent-styled to stand out ── */}
<label
title="Open MIDI, MusicXML, or PDF sheet music"
aria-label="Import MIDI, MusicXML, or PDF file"
title="Open MIDI, MusicXML, PDF sheet music, or audio recording (MP3/WAV/etc.)"
aria-label="Import MIDI, MusicXML, PDF, or audio file"
style={{
display: "inline-flex",
alignItems: "center",
@@ -243,7 +245,7 @@ export function TransportControls() {
)}
<input
type="file"
accept=".mid,.midi,.xml,.mxl,.pdf"
accept=".mid,.midi,.xml,.mxl,.pdf,.mp3,.wav,.m4a,.ogg,.flac,.aac"
className="hidden"
onChange={(e) => {
const f = e.target.files?.[0];
+45
View File
@@ -140,6 +140,7 @@ export interface AppState {
loadMidiFile: (file: File) => Promise<void>;
loadMusicXmlFile: (file: File) => Promise<void>;
loadPdfFile: (file: File) => Promise<void>;
loadAudioFile: (file: File) => Promise<void>;
generateFingering: () => Promise<void>;
exportMidi: () => void;
exportMusicXml: () => void;
@@ -436,6 +437,50 @@ export const useAppStore = create<AppState>((set, get) => {
}
},
loadAudioFile: async (file: File) => {
const id = crypto.randomUUID();
const rawTitle = file.name.replace(/\.(mp3|wav|m4a|ogg|flac|aac)$/i, "");
const title = rawTitle.replace(/[\x00-\x1f\x7f/\\]/g, "").slice(0, 200) || "Untitled";
set({
isLoadingDocument: true,
loadingMessage: "Transcribing audio…",
loadError: null,
});
try {
const form = new FormData();
form.append("file", file, file.name);
// Basic Pitch can take 10-60 s on the backend; no client-side fetch
// timeout - the server's subprocess timeout is the effective limit.
const res = await fetch("/api/transcribe/mp3", { method: "POST", body: form });
if (!res.ok) {
const body = (await res.json().catch(() => ({}))) as { detail?: string };
throw new Error(body.detail ?? `Server error ${res.status}`);
}
// Endpoint returns a raw MIDI file (audio/midi) - parse it through the
// same Web Worker pipeline as a regular .mid import.
const midiBuffer = await res.arrayBuffer();
const bufferForDoc = midiBuffer.slice(0);
const doc = await parseMidiInWorker(midiBuffer, id, title);
set({ document: { ...doc, midiBuffer: bufferForDoc } });
await syncEngine.loadDocument({ ...doc, midiBuffer: bufferForDoc });
// Kick off MusicXML transcription so the sheet-music view eventually
// populates, mirroring loadMidiFile's pattern. Fire-and-forget.
fetchMusicXml(bufferForDoc.slice(0), doc, id).catch(console.warn);
} catch (err) {
const msg = err instanceof Error ? err.message : String(err);
set({ loadError: msg });
} finally {
set({ isLoadingDocument: false, loadingMessage: null });
}
},
generateFingering: async () => {
const { document: doc } = get();
if (!doc?.musicXml) return;
+27 -34
View File
@@ -32,6 +32,7 @@ export function PracticeView() {
loadMidiFile,
loadMusicXmlFile,
loadPdfFile,
loadAudioFile,
settings,
updateSettings,
status,
@@ -117,8 +118,9 @@ export function PracticeView() {
if (file.name.match(/\.midi?$/i)) loadMidiFile(file);
else if (file.name.match(/\.(xml|mxl)$/i)) loadMusicXmlFile(file);
else if (file.name.match(/\.pdf$/i)) loadPdfFile(file);
else if (file.name.match(/\.(mp3|wav|m4a|ogg|flac|aac)$/i)) loadAudioFile(file);
},
[loadMidiFile, loadMusicXmlFile, loadPdfFile]
[loadMidiFile, loadMusicXmlFile, loadPdfFile, loadAudioFile]
);
const handleDrop = useCallback(
@@ -265,40 +267,31 @@ export function PracticeView() {
</div>
</header>
{/* ── Main content - layout-aware ────────────────────────────────────── */}
{/* ── Main content - layout-aware ──────────────────────────────────────
PianoKeyboardView is a SINGLETON at the bottom of the main column so
PixiJS doesn't re-init on every view switch (skeleton flash + perf cost).
Same for FallingNotesView in falling/all modes - kept mounted across
the two modes that show it. Only the conditional top-content elements
(PianoModeBackground / SheetMusicView / sheet sidebar) mount and
unmount on layoutMode change. */}
<main className="flex flex-1 overflow-hidden min-h-0 relative">
{layoutMode === "piano" && (
<div className="flex flex-col flex-1 min-h-0 overflow-hidden">
<PianoModeBackground />
<PianoKeyboardView />
</div>
)}
{layoutMode === "falling" && (
<div className="flex flex-col flex-1 min-h-0 overflow-hidden">
<FallingNotesView />
<PianoKeyboardView />
</div>
)}
{layoutMode === "sheet" && (
<div className="flex flex-col flex-1 min-h-0 overflow-hidden">
<SheetMusicView />
<PianoKeyboardView />
</div>
)}
{/* Optional sheet sidebar (only in "all" mode) */}
{layoutMode === "all" && (
<>
<div
className="flex flex-col flex-shrink-0 min-h-0 overflow-hidden relative"
style={{ flex: "0 0 42%", minWidth: 260, maxWidth: 440 }}
>
<SheetMusicView />
</div>
<div className="flex flex-col flex-1 min-h-0 overflow-hidden">
<FallingNotesView />
<PianoKeyboardView />
</div>
</>
<div
className="flex flex-col flex-shrink-0 min-h-0 overflow-hidden relative"
style={{ flex: "0 0 42%", minWidth: 260, maxWidth: 440 }}
>
<SheetMusicView />
</div>
)}
{/* Main column: top content varies, piano persists across all modes */}
<div className="flex flex-col flex-1 min-h-0 overflow-hidden">
{layoutMode === "piano" && <PianoModeBackground />}
{(layoutMode === "falling" || layoutMode === "all") && <FallingNotesView />}
{layoutMode === "sheet" && <SheetMusicView />}
<PianoKeyboardView />
</div>
</main>
{/* ── Empty state overlay ────────────────────────────────────────────── */}
@@ -362,7 +355,7 @@ function EmptyState({ onImport }: { onImport: (file: File) => void }) {
No file loaded
</div>
<div style={{ fontSize: 13, color: "var(--color-text-muted)", lineHeight: 1.6 }}>
Import a MIDI, MusicXML, or PDF sheet music file to start practicing
Import a MIDI, MusicXML, PDF sheet music, or audio recording to start practicing
</div>
</div>
@@ -406,7 +399,7 @@ function EmptyState({ onImport }: { onImport: (file: File) => void }) {
<input
ref={fileInputRef}
type="file"
accept=".mid,.midi,.xml,.mxl,.pdf"
accept=".mid,.midi,.xml,.mxl,.pdf,.mp3,.wav,.m4a,.ogg,.flac,.aac"
className="hidden"
onChange={(e) => {
const f = e.target.files?.[0];