Update app.py

app.py

@@ -52,13 +52,13 @@ def text_to_speech(text):
         # If input is already a path to synthesized speech, return it
         return text
 
-def speech_to_speech(input_audio_or_text):
-    if isinstance(input_audio_or_text, str):
-        # If input is audio file path, convert speech to text
-        transcription = speech_to_text(input_audio_or_text)
+def speech_to_speech(input_audio, text_input=None):
+    if text_input is None:
+        # If no text input is provided, convert the input audio to text
+        transcription = speech_to_text(input_audio)
     else:
-        # If input is text, use it directly
-        transcription = input_audio_or_text
+        # If text input is provided, use it directly
+        transcription = text_input
     # Synthesize text to speech and resample to 16kHz
     synthesized_speech_path = text_to_speech(transcription)
     return synthesized_speech_path