Update app.py

app.py

@@ -60,17 +60,16 @@ async def tts_interface(text, voice, rate, pitch, background_music):
         return None, None, gr.Warning(warning)
     
     # Verificar si se proporcionó un archivo de fondo musical
-    if background_music is None or background_music == "":
-        return speech_file, None, None
+    if background_music and background_music != "":
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
+            output_file = tmp_file.name
+            add_background_music(speech_file, background_music, output_file)
+        # Eliminar el archivo temporal del speech original
+        os.remove(speech_file)
+        return output_file, None, None
     
-    # Agregar el fondo musical
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
-        output_file = tmp_file.name
-        add_background_music(speech_file, background_music, output_file)
-    
-    # Eliminar el archivo temporal del speech original
-    os.remove(speech_file)
-    return output_file, None, None
+    # Si no hay fondo musical, devolver el speech original
+    return speech_file, None, None
 
 async def create_demo():
     voices = await get_voices()
@@ -99,7 +98,7 @@ async def create_demo():
             gr.Dropdown(choices=[""] + list(voices.keys()), label="Select Voice", value=""),
             gr.Slider(minimum=-50, maximum=50, value=0, label="Speech Rate Adjustment (%)", step=1),
             gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1),
-            gr.Audio(label="Background Music", type="filepath", optional=True)
+            gr.Audio(label="Background Music", type="filepath")  # Sin el argumento 'optional'
         ],
         outputs=[
             gr.Audio(label="Generated Audio", type="filepath"),