update

app.py

@@ -43,16 +43,16 @@ def translate_speech(audio):
     synthesised_speech = tts(translated_text_str)
     print(f"Synthesised speech: {synthesised_speech}")  # Print the synthesised speech to see what it contains
 
-    # Check if the synthesised speech contains the expected key
-    if 'key' in synthesised_speech:  # Replace 'key' with the actual key
-        synthesised_speech_data = synthesised_speech['key']  # Replace 'key' with the actual key
+    # Check if the synthesised speech contains 'audio'
+    if 'audio' in synthesised_speech:
+        synthesised_speech_data = synthesised_speech['audio']
     else:
-        print("The synthesised speech does not contain 'key'")  # Replace 'key' with the actual key
+        print("The synthesised speech does not contain 'audio'")
         return
 
     # Define the max_range variable
     max_range = 32767  # You can adjust this value based on your requirements
-    synthesised_speech = (synthesised_speech_data.numpy() * max_range).astype(np.int16)
+    synthesised_speech = (synthesised_speech_data * max_range).astype(np.int16)
 
     return 16000, synthesised_speech