Refactor TTS module loading in `audio_generator/manager.py`: replace `importlib.import_module` with `importlib.util` for improved dynamic import handling and error logging.

src/VoiceDialogue/services/audio/audio_generator/manager.py

@@ -154,9 +154,12 @@ def register_all_tts():
             
         module_name = py_file.stem
         try:
-            # 动态导入模块
-            module = importlib.import_module(f".runtime.{module_name}", 
-                                           package="VoiceDialogue.services.audio.audio_generator")
+            spec = importlib.util.spec_from_file_location(
+                f"runtime.{module_name}", 
+                py_file
+            )
+            module = importlib.util.module_from_spec(spec)
+            spec.loader.exec_module(module)
             logging.info(f"Successfully imported TTS module: {module_name}")
         except ImportError as e:
             logging.warning(f"Failed to import TTS module {module_name}: {e}")