[Wake/VAD/STT 与 Live runtime]：完成真实重复语音运行，包含云端ASR/TTS开关、run-live和临时上下文测试

src/owner_voice_pet/tts.py

@@ -1,11 +1,18 @@
 from __future__ import annotations
 
 import math
+import json
+import socket
 import struct
 import subprocess
 import tempfile
+import urllib.error
+import urllib.request
+from collections.abc import Callable
 from pathlib import Path
+from typing import Any
 
+from .config import AppConfig
 from .models import AudioSegment, ErrorCode, ProviderError
 
 
@@ -121,3 +128,82 @@ class MacSayTtsProvider:
                 "tts",
             )
         return AudioSegment(data, 16000, 1, 0, max(120, len(clean) * 45), {"text": clean, "format": "aiff"})
+
+
+class CloudTtsProvider:
+    def __init__(
+        self,
+        config: AppConfig,
+        timeout_s: float = 60.0,
+        urlopen: Callable[..., Any] | None = None,
+    ) -> None:
+        self.config = config
+        self.timeout_s = timeout_s
+        self.urlopen = urlopen or urllib.request.urlopen
+        self.loaded = False
+
+    def load(self) -> None:
+        self.config.require_llm_credentials()
+        self.loaded = True
+
+    def synthesize(self, text: str) -> AudioSegment:
+        if not self.loaded:
+            raise ProviderError(
+                ErrorCode.TTS_SYNTHESIS_FAILED,
+                "cloud TTS provider is not loaded",
+                False,
+                "newapi-tts",
+                "tts",
+            )
+        clean = text.strip()
+        if not clean:
+            raise ProviderError(
+                ErrorCode.TTS_EMPTY_AUDIO,
+                "cannot synthesize empty text",
+                True,
+                "newapi-tts",
+                "tts",
+            )
+        payload = {
+            "model": self.config.tts_model,
+            "input": clean,
+            "voice": self.config.tts_voice,
+            "response_format": "mp3",
+        }
+        request = urllib.request.Request(
+            self.config.api_url("/v1/audio/speech"),
+            data=json.dumps(payload).encode("utf-8"),
+            headers={
+                "Authorization": f"Bearer {self.config.llm_api_key}",
+                "Content-Type": "application/json",
+            },
+            method="POST",
+        )
+        try:
+            with self.urlopen(request, timeout=self.timeout_s) as response:
+                data = response.read()
+        except urllib.error.HTTPError as exc:
+            raise ProviderError(
+                ErrorCode.TTS_SYNTHESIS_FAILED,
+                f"cloud TTS HTTP error {exc.code}",
+                exc.code >= 500,
+                "newapi-tts",
+                "tts",
+            ) from exc
+        except (urllib.error.URLError, TimeoutError, socket.timeout) as exc:
+            raise ProviderError(
+                ErrorCode.TTS_SYNTHESIS_FAILED,
+                f"cloud TTS request failed: {exc}",
+                True,
+                "newapi-tts",
+                "tts",
+            ) from exc
+        if not data:
+            raise ProviderError(
+                ErrorCode.TTS_EMPTY_AUDIO,
+                "cloud TTS returned empty audio",
+                True,
+                "newapi-tts",
+                "tts",
+            )
+        return AudioSegment(data, 16000, 1, 0, max(120, len(clean) * 45), {"text": clean, "format": "mp3"})