Update app.py

app.py

@@ -5,13 +5,14 @@ from gtts import gTTS
 from groq import Groq
 import tempfile
 
-# Load Whisper model for speech-to-text
-print("Loading Whisper model...")
+# Load Whisper model
 whisper_model = whisper.load_model("base")
 
 # Initialize Groq API
-print("Initializing Groq API...")
-client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+if not GROQ_API_KEY:
+    raise ValueError("GROQ_API_KEY environment variable not set.")
+client = Groq(api_key=GROQ_API_KEY)
 
 # Function to transcribe audio to text
 def transcribe_audio(audio_file):
@@ -36,4 +37,50 @@ def get_llm_response(user_input):
         return f"Error in LLM interaction: {e}"
 
 # Function to convert text to speech
-def text_to_sp
+def text_to_speech(text):
+    try:
+        tts = gTTS(text)
+        temp_file = tempfile.NamedTemporaryFile(suffix=".mp3", delete=False)
+        tts.save(temp_file.name)
+        return temp_file.name
+    except Exception as e:
+        return f"Error in text-to-speech conversion: {e}"
+
+# Main pipeline
+def chatbot_pipeline(audio_file):
+    # Transcribe audio
+    user_input = transcribe_audio(audio_file)
+    if "Error" in user_input:
+        return user_input, "No response", None
+
+    # Get response from LLM
+    response = get_llm_response(user_input)
+    if "Error" in response:
+        return user_input, response, None
+
+    # Convert response to audio
+    response_audio = text_to_speech(response)
+    if "Error" in response_audio:
+        return user_input, response, None
+
+    return user_input, response, response_audio
+
+# Gradio Interface
+interface = gr.Interface(
+    fn=chatbot_pipeline,
+    inputs=gr.Audio(source="microphone", type="filepath"),
+    outputs=[
+        gr.Textbox(label="Transcribed Text"),
+        gr.Textbox(label="Chatbot Response"),
+        gr.Audio(label="Response Audio"),
+    ],
+    title="Real-Time Voice-to-Voice Chatbot",
+    description=(
+        "This chatbot transcribes your voice input using Whisper, "
+        "processes it through Groq's API to generate a response, "
+        "and converts the response back to speech."
+    ),
+)
+
+if __name__ == "__main__":
+    interface.launch(server_name="0.0.0.0", server_port=7860)