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>

backend/app/config.py

@@ -0,0 +1,65 @@
+from __future__ import annotations
+
+from functools import lru_cache
+from pathlib import Path
+
+import yaml
+from pydantic import Field
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+ROOT = Path(__file__).resolve().parents[2]
+
+
+class AppSettings(BaseSettings):
+    model_config = SettingsConfigDict(
+        env_file=str(ROOT / ".env"),
+        env_file_encoding="utf-8",
+        extra="ignore",
+    )
+
+    tts_model: str = Field(default="cosyvoice", validation_alias="TTS_MODEL")
+    host: str = Field(default="0.0.0.0", validation_alias="TTS_HOST")
+    port: int = Field(default=8000, validation_alias="TTS_PORT")
+    samples_dir: Path = Field(default=ROOT / "samples")
+    outputs_dir: Path = Field(default=ROOT / "outputs" / "api")
+    uploads_dir: Path = Field(default=ROOT / "backend" / "data" / "uploads")
+    default_ref_audio: str | None = Field(default=None, validation_alias="TTS_REF_AUDIO")
+    default_ref_text: str | None = Field(default=None, validation_alias="TTS_REF_TEXT")
+    cosyvoice_model_dir: Path = Field(default=ROOT / "models" / "Fun-CosyVoice3-0.5B")
+    cosyvoice_prompt_prefix: str = (
+        "You are a helpful assistant.<|endofprompt|>"
+    )
+    chunk_max_chars: int = 120
+
+
+@lru_cache
+def get_settings() -> AppSettings:
+    yaml_path = ROOT / "config" / "settings.yaml"
+    data: dict = {}
+    if yaml_path.is_file():
+        with open(yaml_path, encoding="utf-8") as f:
+            raw = yaml.safe_load(f) or {}
+        data["tts_model"] = raw.get("default_model", "cosyvoice")
+        gen = raw.get("generation") or {}
+        data["chunk_max_chars"] = gen.get("chunk_max_chars", 120)
+        cv = raw.get("cosyvoice") or {}
+        if cv.get("model_dir"):
+            data["cosyvoice_model_dir"] = ROOT / cv["model_dir"]
+        if cv.get("prompt_prefix"):
+            data["cosyvoice_prompt_prefix"] = cv["prompt_prefix"]
+        srv = raw.get("server") or {}
+        data["host"] = srv.get("host", "0.0.0.0")
+        data["port"] = srv.get("port", 8000)
+        paths = raw.get("paths") or {}
+        if paths.get("samples_dir"):
+            data["samples_dir"] = ROOT / paths["samples_dir"]
+        if paths.get("outputs_dir"):
+            data["outputs_dir"] = ROOT / paths["outputs_dir"] / "api"
+        if paths.get("uploads_dir"):
+            data["uploads_dir"] = ROOT / paths["uploads_dir"]
+
+    return AppSettings(**{k: v for k, v in data.items() if v is not None})
+
+
+def project_root() -> Path:
+    return ROOT