Update app.py

app.py

@@ -5,6 +5,7 @@ from sentence_transformers import SentenceTransformer, util
 import torch
 import json
 import urllib.parse
+import soundfile as sf
 
 # Fetch Hugging Face API Token securely from environment variables
 HF_API_TOKEN = os.getenv("HF_API_TOKEN")  # This fetches the token securely
@@ -60,19 +61,21 @@ def get_bot_response(query):
 # Gradio interface function
 def chatbot(audio, message, system_message, max_tokens, temperature, top_p):
     if audio is not None:
-        audio_data, sample_rate = audio
-        sf.write("temp.wav", audio_data, sample_rate)
-        # Transcribe the audio using Whisper
-        transcript = transcribe_audio("temp.wav")
-        message = transcript  # Use the transcript as the input message
+        sample_rate, audio_data = audio  # ✅ Correct order
+        sf.write("temp.wav", audio_data, sample_rate)  # Save audio
+        try:
+            transcript = transcribe_audio("temp.wav")
+            message = transcript  # Use transcribed text
+        except Exception as e:
+            return f"Audio transcription failed: {str(e)}", None
+
+    try:
+        response = get_bot_response(message)
+        audio_url = get_tts_audio_url(response)
+        return response, audio_url
+    except Exception as e:
+        return f"Error in generating response: {str(e)}", None
 
-    # Get the bot response using the text input or transcribed audio
-    response = get_bot_response(message)
-
-    # Generate the TTS audio URL
-    audio_url = get_tts_audio_url(response)
-
-    return response, audio_url
 
 # Define Gradio interface
 demo = gr.Interface(