Update app.py

app.py

@@ -2,11 +2,28 @@ import gradio as gr
 from groq import Groq
 import os
 import time
+import speech_recognition as sr
+from gtts import gTTS
 
 api_key = os.getenv('GROQ_API_KEY')
 # Initialize Groq client
 client = Groq(api_key=api_key)
 
+# Function to convert audio to text
+def audio_to_text(audio_file):
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(audio_file) as source:
+        audio_data = recognizer.record(source)
+        text = recognizer.recognize_google(audio_data)
+    return text
+
+# Function to convert text to audio
+def text_to_audio(text):
+    tts = gTTS(text)
+    audio_file = "output_audio.mp3"
+    tts.save(audio_file)
+    return audio_file
+
 # Function to generate responses with error handling
 def generate_response(user_input, chat_history: list):
     try:
@@ -26,7 +43,6 @@ def generate_response(user_input, chat_history: list):
         # Call Groq API to get a response from LLaMA
         chat_completion = client.chat.completions.create(
             messages=messages,
-            #model="llama3-8b-8192"
             model='llama-3.1-70b-versatile'
         )
         
@@ -47,34 +63,27 @@ def gradio_interface():
         # Create input textbox and button for clearing chat
         gr.Markdown("## LoserHero - A Mental Health Chatbot")
         chatbot = gr.Chatbot(type="messages")
+        audio_input = gr.Audio(source="microphone", type="filepath", label="Speak your message")
         msg = gr.Textbox(placeholder="Type your message here...")
+        text_output = gr.Textbox(label="Response (Text)")
+        audio_output = gr.Audio(label="Response (Audio)")
         clear = gr.Button("Clear")
 
-        # User message submission function
-        def user(user_message, history: list):
-            # Add user message to the history
-            history.append({"role": "user", "content": user_message})
-            return "", history  # Reset message input and return updated history
-
-        # Bot response function with simulated typing effect
-        def bot(history: list):
-            # Ensure that history is not empty
-            if len(history) > 0:
-                user_input = history[-1]["content"]  # Get the last user message
-                response, updated_history = generate_response(user_input, history)  # Get bot's response
-
-                history = updated_history  # Update the history with the new response
-                history.append({"role": "assistant", "content": ""})  # Add placeholder for assistant
-
-                # Simulate typing effect for the bot's response
-                for character in response:
-                    history[-1]['content'] += character
-                    time.sleep(0.02)  # Typing delay
-                    yield history  # Yield updated history as the bot types
+        def process_input(user_message, audio_file, history: list):
+            if audio_file:
+                user_message = audio_to_text(audio_file)
+            if user_message:
+                history.append({"role": "user", "content": user_message})
+                response, updated_history = generate_response(user_message, history)
+                history = updated_history
+                history.append({"role": "assistant", "content": response})
+                response_audio = text_to_audio(response)
+                return "", None, response, response_audio, history
+            return "", None, "Please provide a valid input.", None, history
 
-        # Set up interaction flow:
-        msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(bot, chatbot, chatbot)
-        clear.click(lambda: [], None, chatbot, queue=False)  # Clear chat history when clicked
+        msg.submit(process_input, [msg, audio_input, chatbot], [msg, audio_input, text_output, audio_output, chatbot])
+        audio_input.change(process_input, [msg, audio_input, chatbot], [msg, audio_input, text_output, audio_output, chatbot])
+        clear.click(lambda: ("", None, "", None, []), None, [msg, audio_input, text_output, audio_output, chatbot])
 
     demo.launch()