[连续对话判断]：完成自动持续对话和播报打断，包含回复意图判断、免唤醒追问和打断回归测试

src/owner_voice_pet/tts.py

@@ -9,6 +9,7 @@ import subprocess
 import tempfile
 import urllib.error
 import urllib.request
+import wave
 from collections.abc import Callable
 from pathlib import Path
 from typing import Any
@@ -104,8 +105,9 @@ class MacSayTtsProvider:
                 "tts",
             )
         with tempfile.TemporaryDirectory() as tmp:
-            output = Path(tmp) / "speech.aiff"
-            command = ["say", "-o", str(output)]
+            aiff_output = Path(tmp) / "speech.aiff"
+            wav_output = Path(tmp) / "speech.wav"
+            command = ["say", "-o", str(aiff_output)]
             if self.voice:
                 command.extend(["-v", self.voice])
             command.append(clean)
@@ -119,7 +121,23 @@ class MacSayTtsProvider:
                     "macos-say",
                     "tts",
                 ) from exc
-            data = output.read_bytes()
+            try:
+                subprocess.run(
+                    ["afconvert", "-f", "WAVE", "-d", "LEI16@16000", "-c", "1", str(aiff_output), str(wav_output)],
+                    check=True,
+                    stdout=subprocess.PIPE,
+                    stderr=subprocess.PIPE,
+                )
+                with wave.open(str(wav_output), "rb") as handle:
+                    sample_rate = handle.getframerate()
+                    channels = handle.getnchannels()
+                    data = handle.readframes(handle.getnframes())
+                metadata = {"text": clean}
+            except (FileNotFoundError, subprocess.CalledProcessError, wave.Error):
+                data = aiff_output.read_bytes()
+                sample_rate = 16000
+                channels = 1
+                metadata = {"text": clean, "format": "aiff"}
         if not data:
             raise ProviderError(
                 ErrorCode.TTS_EMPTY_AUDIO,
@@ -128,7 +146,8 @@ class MacSayTtsProvider:
                 "macos-say",
                 "tts",
             )
-        return AudioSegment(data, 16000, 1, 0, max(120, len(clean) * 45), {"text": clean, "format": "aiff"})
+        duration_ms = int(len(data) / max(1, sample_rate * channels * 2) * 1000)
+        return AudioSegment(data, sample_rate, channels, 0, max(120, duration_ms, len(clean) * 45), metadata)
 
 
 class CloudTtsProvider: