testing audio

app.py

@@ -35,7 +35,7 @@ def process_speech(audio):
         "English",# target language
         api_name="/run",
     )
-    # out = out[1] # get the text
+    out = out[1] # get the text
     try :
         return f"{out}"
     except Exception as e :
@@ -226,6 +226,7 @@ def process_and_query(text, image, audio):
 
         if audio is not None:
             text = process_speech(audio)
+            return f"{text}"
 
         # Now, use the text (either provided by the user or obtained from OpenAI) to query Vectara
         vectara_response_json = query_vectara(text)