Update app.py

app.py

@@ -156,7 +156,7 @@ def convert_text_to_speech(input_text: str, source_language: str, target_languag
         
         # Initialize variables
         translated_text = ""
-        new_file_path = ""
+        audio_file_path = ""
 
         # Process each item in the result
         for item in result:
@@ -167,23 +167,16 @@ def convert_text_to_speech(input_text: str, source_language: str, target_languag
                 # Assign the first non-URL string as the translated text
                 if not translated_text:
                     translated_text = item
-            elif os.path.isdir(item):
-                # Find the first MP3 file in the directory
-                for file in os.listdir(item):
-                    file_path = os.path.join(item, file)
-                    if os.path.isfile(file_path) and file_path.endswith('.mp3'):
-                        # Return the path of the MP3 file directly without renaming
-                        new_file_path = file_path
-                        break
-                if new_file_path:
-                    break
-
-        return new_file_path, translated_text
+            elif isinstance(item, tuple) and len(item) == 2:
+                # Assuming the item is a tuple containing sample rate and audio data
+                audio_file_path = save_audio(item)  # Save the audio file
+                break
+
+        return audio_file_path, translated_text
 
     except Exception as e:
         return f"Error in text-to-speech conversion: {str(e)}", ""
 
-
 def process_image(image_input):
     # Initialize the Gradio client with the URL of the Gradio server
     client = Client("https://adept-fuyu-8b-demo.hf.space/--replicas/pqjvl/")