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>

scripts/workers/cosy_infer.py

@@ -0,0 +1,73 @@
+#!/usr/bin/env python3
+"""CosyVoice3 zero-shot 추론 워커 (cosyvoice venv에서 실행)."""
+from __future__ import annotations
+
+import argparse
+import sys
+from pathlib import Path
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="CosyVoice3 inference worker")
+    parser.add_argument("--ref-audio", required=True)
+    parser.add_argument("--prompt-text", default="", help="Text spoken in ref audio (with prefix)")
+    parser.add_argument("--gen-text", required=True)
+    parser.add_argument("--out", required=True)
+    parser.add_argument(
+        "--model-dir",
+        default=None,
+        help="Path to Fun-CosyVoice3-0.5B (default: PROJECT/models/Fun-CosyVoice3-0.5B)",
+    )
+    parser.add_argument(
+        "--prompt-prefix",
+        default="You are a helpful assistant.<|endofprompt|>",
+    )
+    args = parser.parse_args()
+
+    root = Path(__file__).resolve().parents[2]
+    repo = root / "external" / "CosyVoice"
+    model_dir = Path(args.model_dir or root / "models" / "Fun-CosyVoice3-0.5B")
+    ref = Path(args.ref_audio)
+    out = Path(args.out)
+
+    if not repo.is_dir():
+        print(f"CosyVoice repo missing: {repo}. Run ./scripts/setup_cosyvoice.sh", file=sys.stderr)
+        return 1
+    if not model_dir.is_dir():
+        print(f"Model dir missing: {model_dir}", file=sys.stderr)
+        return 1
+    if not ref.is_file():
+        print(f"ref audio not found: {ref}", file=sys.stderr)
+        return 1
+
+    sys.path.insert(0, str(repo))
+    sys.path.append(str(repo / "third_party" / "Matcha-TTS"))
+
+    try:
+        import torchaudio
+        from cosyvoice.cli.cosyvoice import AutoModel
+    except ImportError as e:
+        print("CosyVoice import failed. Run ./scripts/setup_cosyvoice.sh", file=sys.stderr)
+        print(e, file=sys.stderr)
+        return 1
+
+    prompt = args.prompt_prefix + (args.prompt_text or "")
+    out.parent.mkdir(parents=True, exist_ok=True)
+
+    cosyvoice = AutoModel(model_dir=str(model_dir))
+    for i, result in enumerate(
+        cosyvoice.inference_zero_shot(
+            args.gen_text,
+            prompt,
+            str(ref),
+            stream=False,
+        )
+    ):
+        path = out if i == 0 else out.with_stem(f"{out.stem}_{i}")
+        torchaudio.save(str(path), result["tts_speech"], cosyvoice.sample_rate)
+        print(f"OK: {path}")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

scripts/workers/f5_infer.py

@@ -0,0 +1,47 @@
+#!/usr/bin/env python3
+"""F5-TTS 추론 워커 (f5tts venv에서 실행)."""
+from __future__ import annotations
+
+import argparse
+import sys
+from pathlib import Path
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="F5-TTS inference worker")
+    parser.add_argument("--ref-audio", required=True, help="Reference WAV path")
+    parser.add_argument("--ref-text", required=True, help="Transcript of reference audio")
+    parser.add_argument("--gen-text", required=True, help="Text to synthesize")
+    parser.add_argument("--out", required=True, help="Output WAV path")
+    parser.add_argument("--model", default="F5TTS_v1_Base")
+    args = parser.parse_args()
+
+    ref = Path(args.ref_audio)
+    if not ref.is_file():
+        print(f"ref audio not found: {ref}", file=sys.stderr)
+        return 1
+
+    out = Path(args.out)
+    out.parent.mkdir(parents=True, exist_ok=True)
+
+    try:
+        from f5_tts.api import F5TTS
+    except ImportError as e:
+        print("f5-tts not installed. Run: ./scripts/setup_f5tts.sh", file=sys.stderr)
+        print(e, file=sys.stderr)
+        return 1
+
+    tts = F5TTS(model=args.model)
+    tts.infer(
+        ref_file=str(ref),
+        ref_text=args.ref_text,
+        gen_text=args.gen_text,
+        file_wave=str(out),
+        remove_silence=True,
+    )
+    print(f"OK: {out}")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())