correct endpoint description

gradio_app.py

@@ -382,8 +382,7 @@ def gradio_infer(source_image, driven_audio):
     """
     Generate a talking-head video from a static source image and an audio file.
 
-    This function serves as the main entry point for MCP (Machine Code Protocol) mode. 
-    It uses a pre-trained motion and lip-sync model to animate a face image so that it 
+    This function uses a pre-trained motion and lip-sync model to animate a face image so that it 
     appears to speak in sync with a given audio clip. The resulting video is saved 
     and returned.