Clean up RepAnnouncer: remove TTS code, play pre-generated audio only

- RepAnnouncer now only plays audio files, no TTS generation
- Removed pyttsx3 dependency, rate/volume params from constructor
- Audio generation delegated to app/audio/generate.py (called at startup)
- Default audio dir changed to resources/audio/reps
- Added resources/ to .gitignore

configs/models.py

@@ -54,7 +54,7 @@ class AudioConfig:
         """返回语音文件目录的绝对路径"""
         if self.rep_audio_dir:
             return Path(self.rep_audio_dir)
-        return Path(__file__).resolve().parent.parent / "app" / "audio" / "reps"
+        return Path(__file__).resolve().parent.parent / "resources" / "audio" / "reps"
 
 
 @dataclass