init

services/tts.py

@@ -0,0 +1,45 @@
+from __future__ import annotations
+
+import logging
+from typing import Optional
+
+import numpy as np
+
+logger = logging.getLogger(__name__)
+
+
+class TTSService:
+    def __init__(self) -> None:
+        self._pipeline = None
+        self._ready = False
+        self._attempted = False
+        self._init_error: Optional[str] = None
+
+    def _ensure_loaded(self) -> None:
+        if self._ready or self._attempted:
+            return
+        self._attempted = True
+        try:
+            import kokoro
+
+            self._pipeline = kokoro.KPipeline(lang_code="z")
+            self._ready = True
+        except Exception as exc:  # pragma: no cover
+            self._init_error = str(exc)
+            logger.warning("TTS fallback mode: %s", exc)
+
+    async def synthesize(self, text: str) -> tuple[np.ndarray, int]:
+        self._ensure_loaded()
+        if self._ready and self._pipeline is not None:
+            chunks = []
+            for _, _, audio in self._pipeline(text, voice="zf_xiaoxiao"):
+                chunks.append(audio)
+            if chunks:
+                return np.concatenate(chunks), 24000
+
+        # 0.5s silence fallback for flow verification
+        return np.zeros(12000, dtype=np.float32), 24000
+
+    @property
+    def health(self) -> dict:
+        return {"ready": self._ready, "attempted": self._attempted, "error": self._init_error}