fix: issue where an error occurs when invoking TTS without selecting a voice (#5046)

api/controllers/web/audio.py

                 app_model=app_model,
                 text=request.form['text'],
                 end_user=end_user.external_user_id,
-                voice=request.form['voice'] if request.form.get('voice') else app_model.app_model_config.text_to_speech_dict.get('voice'),
+                voice=request.form['voice'] if request.form.get('voice') else None,
                 streaming=False
             )
 

api/core/model_manager.py

             except Exception as e:
                 raise e
 
-    def get_tts_voices(self, language: str) -> list:
+    def get_tts_voices(self, language: Optional[str] = None) -> list:
         """
         Invoke large language tts model voices
 

api/services/audio_service.py

             raise ProviderNotSupportTextToSpeechServiceError()
 
         try:
+            if not voice:
+                voices = model_instance.get_tts_voices()
+                if voices:
+                    voice = voices[0].get('value')
+                else:
+                    raise ValueError("Sorry, no voice available.")
+
             return model_instance.invoke_tts(
                 content_text=text.strip(),
                 user=end_user,