Update app.py

app.py

@@ -1,3 +1,4 @@
+
 # Import libraries
 import whisper
 import os
@@ -5,78 +6,50 @@ from gtts import gTTS
 import gradio as gr
 from groq import Groq
 
-pip install torch 
-pip install --upgrade gradio
-
-
-
 # Load Whisper model for transcription
 model = whisper.load_model("base")
 
 # Set up Groq API client (ensure GROQ_API_KEY is set in your environment)
-GROQ_API_KEY = "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"
+#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
+GROQ_API_KEY = "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"
 client = Groq(api_key=GROQ_API_KEY)  
 
+
 # Function to get the LLM response from Groq
 def get_llm_response(user_input):
-    try:
-        chat_completion = client.chat.completions.create(
-            messages=[{"role": "user", "content": user_input}],
-            model="llama3-8b-8192"  # Replace with your desired model
-        )
-        return chat_completion.choices[0].message.content
-    except Exception as e:
-        return f"Error: {e}"
+    chat_completion = client.chat.completions.create(
+        messages=[{"role": "user", "content": user_input}],
+        model="llama3-8b-8192",  # Replace with your desired model
+    )
+    return chat_completion.choices[0].message.content
 
 # Function to convert text to speech using gTTS
 def text_to_speech(text, output_audio="output_audio.mp3"):
-    try:
-        tts = gTTS(text)
-        tts.save(output_audio)
-        return output_audio
-    except Exception as e:
-        return f"Error generating audio: {e}"
+    tts = gTTS(text)
+    tts.save(output_audio)
+    return output_audio
 
 # Main chatbot function to handle audio input and output
 def chatbot(audio):
     # Step 1: Transcribe the audio using Whisper
-    try:
-        result = model.transcribe(audio)
-        user_text = result["text"]
-    except Exception as e:
-        return f"Error in transcription: {e}", None
+    result = model.transcribe(audio)
+    user_text = result["text"]
 
     # Step 2: Get LLM response from Groq
     response_text = get_llm_response(user_text)
 
     # Step 3: Convert the response text to speech
     output_audio = text_to_speech(response_text)
-
+    
     return response_text, output_audio
 
-# Gradio interface for dual input (microphone and file upload)
-with gr.Blocks() as demo:
-    gr.Markdown("# Voice-to-Voice Chatbot")
-    
-    # Input section
-    with gr.Row():
-        microphone_input = gr.Audio(source="microphone", type="filepath", label="Speak into the microphone")
-        file_upload_input = gr.Audio(source="upload", type="filepath", label="Upload an audio file")
-    
-    # Output section
-    chatbot_response_text = gr.Textbox(label="Chatbot Response")
-    chatbot_response_audio = gr.Audio(type="filepath", label="Response Audio")
-    
-    # Buttons to process each input
-    mic_button = gr.Button("Process Microphone Input")
-    file_button = gr.Button("Process Uploaded Audio")
-    
-    # Actions for buttons
-    mic_button.click(chatbot, inputs=microphone_input, outputs=[chatbot_response_text, chatbot_response_audio])
-    file_button.click(chatbot, inputs=file_upload_input, outputs=[chatbot_response_text, chatbot_response_audio])
+# Gradio interface for real-time interaction
+iface = gr.Interface(
+    fn=chatbot,
+    inputs=gr.Audio("microphone", type="filepath"),  # Input from mic
+    outputs=[gr.Textbox(), gr.Audio(type="filepath")],  # Output: response text and audio
+    live=True
+)
 
 # Launch the Gradio app
-demo.launch()
-
-
-
+iface.launch()