현재 작업 상태 저장

apps/api/app/services/voice.py

@@ -20,6 +20,7 @@ from __future__ import annotations
 
 import re
 from dataclasses import dataclass
+from pathlib import Path
 from typing import AsyncIterator, Optional
 
 import httpx
@@ -49,6 +50,32 @@ TTS_RESPONSE_FORMAT = "mp3"
 # End-of-turn readiness default for cascaded STT providers.
 EOT_SILENCE_THRESHOLD_MS = 1200
 
+_REPO_ROOT = Path(__file__).resolve().parents[4]
+POC_SAMPLE_TTS_PRESET = "soft-young-fem"
+POC_SAMPLE_TTS_DEFAULT_DIR = (
+    _REPO_ROOT / "docs" / "voice-art" / "p1-seoyeon-higgs-v3-20260627"
+)
+POC_SAMPLE_TTS_CHUNK_SIZE = 4096
+_POC_SAMPLE_TTS_DEFAULT_SAMPLE = "p1_seoyeon_01_depressed_slow"
+_POC_SAMPLE_TTS_KEYWORDS: tuple[tuple[str, tuple[str, ...]], ...] = (
+    (
+        "p1_seoyeon_03_anxious_guarded",
+        ("엄마", "비밀", "말하지", "불안", "무서", "걱정", "들키", "싫", "갈래"),
+    ),
+    (
+        "p1_seoyeon_02_tired_flat",
+        ("잠", "피곤", "무거", "아무것도", "지쳐", "힘들", "에너지"),
+    ),
+    (
+        "p1_seoyeon_05_recovered_lively",
+        ("오늘은", "친구", "웃", "괜찮았", "좋았", "해냈"),
+    ),
+    (
+        "p1_seoyeon_04_rapport_relief",
+        ("괜찮", "들어", "고마", "선생님", "편해", "조금", "말해"),
+    ),
+)
+
 # OpenAI 공식 voice 풀(2026 기준): alloy, ash, ballad, coral, echo, fable,
 #   nova, onyx, sage, shimmer, verse. 페르소나 톤별로 골라 매핑한다.
 _OPENAI_VOICES = {
@@ -240,9 +267,32 @@ def assess_end_of_turn(
 class VoiceService:
     """OpenAI STT/TTS 어댑터. 앱 수명주기 동안 1 인스턴스 재사용(httpx 풀 공유)."""
 
-    def __init__(self, api_key: Optional[str] = None, base_url: Optional[str] = None) -> None:
+    def __init__(
+        self,
+        api_key: Optional[str] = None,
+        base_url: Optional[str] = None,
+        *,
+        poc_sample_tts_enabled: Optional[bool] = None,
+        environment: Optional[str] = None,
+        poc_sample_tts_dir: Optional[str | Path] = None,
+    ) -> None:
         self._api_key = (api_key if api_key is not None else settings.openai_api_key) or ""
         self._base_url = (base_url or settings.openai_base_url or OPENAI_BASE_URL).rstrip("/")
+        self._environment = environment if environment is not None else settings.environment
+        self._poc_sample_tts_enabled = (
+            bool(settings.voice_poc_sample_tts_enabled)
+            if poc_sample_tts_enabled is None
+            else bool(poc_sample_tts_enabled)
+        )
+        sample_dir_value: str | Path = (
+            poc_sample_tts_dir
+            if poc_sample_tts_dir is not None
+            else (settings.voice_poc_sample_tts_dir or POC_SAMPLE_TTS_DEFAULT_DIR)
+        )
+        sample_dir = Path(sample_dir_value)
+        if not sample_dir.is_absolute():
+            sample_dir = _REPO_ROOT / sample_dir
+        self._poc_sample_tts_dir = sample_dir
         self._client: Optional[httpx.AsyncClient] = None
 
     # ── 수명주기 ──────────────────────────────────────────
@@ -264,6 +314,35 @@ class VoiceService:
         """음성 기능 가용 여부(키 설정됨). 라우트가 핸드셰이크에서 검사."""
         return bool(self._api_key)
 
+    def tts_provider(self) -> str:
+        if self._poc_sample_tts_available():
+            return "p1-sample-poc"
+        if self._api_key:
+            return "openai"
+        if self._poc_sample_tts_enabled and self._environment != "dev":
+            return "disabled-non-dev"
+        return "unavailable"
+
+    def poc_sample_tts_available(self) -> bool:
+        return self._poc_sample_tts_available()
+
+    def _poc_sample_tts_available(self) -> bool:
+        return (
+            self._poc_sample_tts_enabled
+            and self._environment == "dev"
+            and self._poc_sample_path(_POC_SAMPLE_TTS_DEFAULT_SAMPLE).is_file()
+        )
+
+    def _should_use_poc_sample_tts(self, voice: VoicePreset) -> bool:
+        return (
+            self._poc_sample_tts_enabled
+            and self._environment == "dev"
+            and voice.preset == POC_SAMPLE_TTS_PRESET
+        )
+
+    def _poc_sample_path(self, sample_id: str) -> Path:
+        return self._poc_sample_tts_dir / f"{sample_id}.mp3"
+
     @property
     def _http(self) -> httpx.AsyncClient:
         if not self._api_key:
@@ -341,6 +420,10 @@ class VoiceService:
         text = speakable_text(text)
         if not text:
             return
+        if self._should_use_poc_sample_tts(voice):
+            async for chunk in self._synthesize_poc_sample_tts(text):
+                yield chunk
+            return
         payload = build_tts_payload(
             text,
             voice,
@@ -375,6 +458,25 @@ class VoiceService:
         except httpx.HTTPError as e:
             raise RuntimeError(f"TTS transport error: {e}") from e
 
+    async def _synthesize_poc_sample_tts(self, text: str) -> AsyncIterator[TTSChunk]:
+        sample_id = self._select_poc_sample_id(text)
+        sample_path = self._poc_sample_path(sample_id)
+        try:
+            data = sample_path.read_bytes()
+        except OSError as e:
+            raise VoiceUnavailable(f"P1 sample TTS asset is missing: {sample_path}") from e
+        for i in range(0, len(data), POC_SAMPLE_TTS_CHUNK_SIZE):
+            chunk = data[i : i + POC_SAMPLE_TTS_CHUNK_SIZE]
+            if chunk:
+                yield TTSChunk(audio=chunk)
+
+    def _select_poc_sample_id(self, text: str) -> str:
+        normalized = text.casefold()
+        for sample_id, keywords in _POC_SAMPLE_TTS_KEYWORDS:
+            if any(keyword.casefold() in normalized for keyword in keywords):
+                return sample_id
+        return _POC_SAMPLE_TTS_DEFAULT_SAMPLE
+
     async def _synthesize_fallback(self, payload: dict[str, object]) -> AsyncIterator[TTSChunk]:
         """tts-1 폴백(비스트림 POST → 전체 바이트를 청크로 분할)."""
         try: