Update app.py

app.py

@@ -174,7 +174,7 @@ def process_video(voice, model, text, audio_file, progress=gr.Progress()):
         # Handle audio input (either text-to-speech or uploaded file)
         if audio_file is not None:
             progress(0.1, desc="Processing uploaded audio...")
-            audio_path = process_uploaded_audio(audio_file.name, session_id)
+            audio_path = process_uploaded_audio(audio_file, session_id)
             if not audio_path:
                 return None, "Failed to process uploaded audio file."
         elif text:
@@ -262,8 +262,8 @@ def create_interface():
                 with gr.Group() as audio_group:
                     audio_input = gr.Audio(
                         label="Upload Audio",
-                        source="upload",
-                        type="filepath"
+                        type="filepath",
+                        format="mp3"
                     )
                 
                 model_dropdown = gr.Dropdown(