Update app.py

app.py

@@ -1,51 +1,76 @@
-# Import libraries
-import whisper
+# Import necessary libraries
 import os
-from gtts import gTTS
-import gradio as gr
-from groq import Groq
 
-# Load Whisper model for transcription
+# Install required libraries
+try:
+    import whisper
+    import gtts
+    import gradio as gr
+    from groq import Groq
+except ImportError:
+    os.system("pip install git+https://github.com/openai/whisper.git gtts gradio groq")
+
+# Load Whisper model
 model = whisper.load_model("base")
 
-Groq_api_key = "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"
+# Fetch the API key from the environment variable
+Groq_api_key = os.getenv("GROQ_API_KEY")
+
+# Check if the API key is set
+if Groq_api_key is None:
+    raise ValueError("API key for Groq not found. Please set the 'GROQ_API_KEY' environment variable.")
+
+# Initialize the Groq client
 client = Groq(api_key=Groq_api_key)
 
-# Function to get the LLM response from Groq
-def get_llm_response(user_input):
+# Function to transcribe audio
+def transcribe_audio(audio_path):
+    result = model.transcribe(audio_path)
+    return result["text"]
+
+# Function to get response from Groq's API
+def get_groq_response(transcribed_text):
     chat_completion = client.chat.completions.create(
-        messages=[{"role": "user", "content": user_input}],
-        model="llama3-8b-8192",  # Replace with your desired model
+        messages=[
+            {
+                "role": "user",
+                "content": transcribed_text,
+            }
+        ],
+        model="llama3-8b-8192",
     )
     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"):
-    tts = gTTS(text)
-    tts.save(output_audio)
-    return output_audio
+# Function to convert text to speech
+def text_to_speech(text):
+    tts = gtts.gTTS(text=text, lang='en')
+    audio_path = "response.mp3"
+    tts.save(audio_path)
+    return audio_path
 
-# Main chatbot function to handle audio input and output
+# Gradio chatbot function
 def chatbot(audio):
-    # Step 1: Transcribe the audio using Whisper
-    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)
+    # Step 1: Transcribe the audio
+    transcribed_text = transcribe_audio(audio)
+    
+    # Step 2: Get LLM response from Groq API
+    response_text = get_groq_response(transcribed_text)
+    
+    # Step 3: Convert response text to speech
+    response_audio = text_to_speech(response_text)
     
-    return response_text, output_audio
+    # Return the response audio
+    return response_audio
 
-# Gradio interface for real-time interaction
+# Create a Gradio interface
 iface = gr.Interface(
     fn=chatbot,
-    inputs=gr.Audio(type="filepath"),  # Input from mic or file
-    outputs=[gr.Textbox(), gr.Audio(type="filepath")],  # Output: response text and audio
+    inputs=gr.Audio(source="microphone", type="filepath"),
+    outputs="audio",
+    title="Voice-to-Voice Chatbot",
+    description="Speak to the chatbot and listen to the response!",
     live=True
 )
 
-# Launch the Gradio app
+# Launch the interface
 iface.launch()