Update app.py

app.py

@@ -196,13 +196,15 @@ def process_speech(input_language, audio_input):
 
 
 def convert_text_to_speech(input_text: str, source_language: str, target_language: str) -> tuple[str, str]:
+    if not input_text or not source_language or not target_language:
+        return None, "Invalid input parameters."
+
     client = Client("https://facebook-seamless-m4t.hf.space/--replicas/8cllp/")
 
     try:
-        # Make a prediction request to the client
         result = client.predict(
             "T2ST",
-            "text",  # Since we are doing text-to-speech
+            "text",
             None,
             None,
             input_text,
@@ -210,27 +212,28 @@ def convert_text_to_speech(input_text: str, source_language: str, target_languag
             target_language,
             api_name="/run"
         )
+    except Exception as e:
+        return None, f"Error during prediction: {str(e)}"
 
-        # Initialize variables
+    try:
         translated_text = ""
         audio_file_path = ""
 
-        # Process the result
         if result:
             for item in result:
                 if isinstance(item, str):
-                    # Check if the item is a URL pointing to an audio file
-                    if item.endswith('.mp3'):
-                        if not audio_file_path:  # Store only the first audio file path
-                            audio_file_path = item
+                    if item.endswith('.mp3') and not audio_file_path:
+                        audio_file_path = item
                     else:
-                        # Concatenate the translated text
                         translated_text += item + " "
+    except Exception as e:
+        return None, f"Error processing result: {str(e)}"
 
-        return audio_file_path, translated_text.strip()
+    if not audio_file_path:
+        return None, "No audio file path found in the result."
+
+    return audio_file_path, translated_text.strip()
 
-    except Exception as e:
-        return None, 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