Initial commit: Korean voice-cloning TTS prototype

FastAPI backend, web UI, CosyVoice3/F5-TTS setup scripts, and handoff docs for GPU PC continuation.

Co-authored-by: Cursor <cursoragent@cursor.com>

web/app.js

@@ -0,0 +1,101 @@
+const $ = (id) => document.getElementById(id);
+
+async function fetchHealth() {
+  try {
+    const res = await fetch("/api/health");
+    const data = await res.json();
+    $("healthInfo").textContent = `모델: ${data.model} · 샘플 ${data.samples_count}개`;
+  } catch {
+    $("healthInfo").textContent = "API 서버에 연결할 수 없습니다.";
+  }
+}
+
+async function loadSamples() {
+  const select = $("sampleSelect");
+  try {
+    const res = await fetch("/api/voice-samples");
+    const data = await res.json();
+    for (const s of data.samples) {
+      const opt = document.createElement("option");
+      opt.value = s.path;
+      opt.textContent = `${s.label}/${s.id}${s.has_transcript ? "" : " (대본 없음)"}`;
+      select.appendChild(opt);
+    }
+  } catch (e) {
+    console.warn("samples load failed", e);
+  }
+}
+
+async function uploadIfNeeded() {
+  const fileInput = $("fileUpload");
+  if (!fileInput.files?.length) return null;
+
+  const form = new FormData();
+  form.append("file", fileInput.files[0]);
+  const refText = $("refText").value.trim();
+  if (refText) form.append("ref_text", refText);
+
+  const res = await fetch("/api/voice-sample", { method: "POST", body: form });
+  if (!res.ok) {
+    const err = await res.json().catch(() => ({}));
+    throw new Error(err.detail || "업로드 실패");
+  }
+  const data = await res.json();
+  return data.path;
+}
+
+$("generateBtn").addEventListener("click", async () => {
+  const text = $("text").value.trim();
+  if (!text) {
+    $("status").textContent = "텍스트를 입력하세요.";
+    return;
+  }
+
+  const btn = $("generateBtn");
+  btn.disabled = true;
+  $("status").textContent = "음성 생성 중… (GPU 추론은 수십 초 걸릴 수 있습니다)";
+  $("resultSection").hidden = true;
+
+  try {
+    let refAudio = $("sampleSelect").value || null;
+    const uploaded = await uploadIfNeeded();
+    if (uploaded) refAudio = uploaded;
+
+    const body = {
+      text,
+      preprocess: true,
+      ref_text: $("refText").value.trim() || null,
+      ref_audio: refAudio,
+    };
+
+    const res = await fetch("/api/tts", {
+      method: "POST",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify(body),
+    });
+
+    if (!res.ok) {
+      const err = await res.json().catch(() => ({}));
+      const detail =
+        typeof err.detail === "string"
+          ? err.detail
+          : JSON.stringify(err.detail || err);
+      throw new Error(detail || res.statusText);
+    }
+
+    const data = await res.json();
+    const url = data.audio_url + "?t=" + Date.now();
+    $("player").src = url;
+    $("downloadLink").href = url;
+    $("downloadLink").download = `${data.job_id}.wav`;
+    $("resultSection").hidden = false;
+    $("status").textContent = `완료 (모델: ${data.model}, job: ${data.job_id})`;
+  } catch (e) {
+    $("status").textContent = `오류: ${e.message}`;
+  } finally {
+    btn.disabled = false;
+  }
+});
+
+fetchHealth();
+loadSamples();