[文档、验收与归档]：完成真实运行说明和OpenSpec归档，包含README、最终门禁和主规范更新

src/owner_voice_pet/tts.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import math
+import base64
 import json
 import socket
 import struct
@@ -166,12 +167,12 @@ class CloudTtsProvider:
             )
         payload = {
             "model": self.config.tts_model,
-            "input": clean,
-            "voice": self.config.tts_voice,
-            "response_format": "mp3",
+            "messages": [{"role": "assistant", "content": clean}],
+            "audio": {"format": "wav", "voice": self.config.tts_voice},
+            "stream": False,
         }
         request = urllib.request.Request(
-            self.config.api_url("/v1/audio/speech"),
+            self.config.api_url("/v1/chat/completions"),
             data=json.dumps(payload).encode("utf-8"),
             headers={
                 "Authorization": f"Bearer {self.config.llm_api_key}",
@@ -181,7 +182,7 @@ class CloudTtsProvider:
         )
         try:
             with self.urlopen(request, timeout=self.timeout_s) as response:
-                data = response.read()
+                payload = json.loads(response.read().decode("utf-8"))
         except urllib.error.HTTPError as exc:
             raise ProviderError(
                 ErrorCode.TTS_SYNTHESIS_FAILED,
@@ -190,7 +191,7 @@ class CloudTtsProvider:
                 "newapi-tts",
                 "tts",
             ) from exc
-        except (urllib.error.URLError, TimeoutError, socket.timeout) as exc:
+        except (urllib.error.URLError, TimeoutError, socket.timeout, json.JSONDecodeError) as exc:
             raise ProviderError(
                 ErrorCode.TTS_SYNTHESIS_FAILED,
                 f"cloud TTS request failed: {exc}",
@@ -198,7 +199,11 @@ class CloudTtsProvider:
                 "newapi-tts",
                 "tts",
             ) from exc
-        if not data:
+        choices = payload.get("choices") or []
+        message = (choices[0].get("message") if choices else {}) or {}
+        audio = message.get("audio") or {}
+        encoded = audio.get("data")
+        if not encoded:
             raise ProviderError(
                 ErrorCode.TTS_EMPTY_AUDIO,
                 "cloud TTS returned empty audio",
@@ -206,4 +211,14 @@ class CloudTtsProvider:
                 "newapi-tts",
                 "tts",
             )
-        return AudioSegment(data, 16000, 1, 0, max(120, len(clean) * 45), {"text": clean, "format": "mp3"})
+        try:
+            data = base64.b64decode(encoded)
+        except (TypeError, ValueError) as exc:
+            raise ProviderError(
+                ErrorCode.TTS_SYNTHESIS_FAILED,
+                f"cloud TTS returned invalid base64 audio: {exc}",
+                True,
+                "newapi-tts",
+                "tts",
+            ) from exc
+        return AudioSegment(data, 24000, 1, 0, max(120, len(clean) * 45), {"text": clean, "format": "wav"})