Create app.py

app.py

@@ -0,0 +1,84 @@
+# Install required libraries
+!pip install gradio torch gtts openai-whisper
+
+import os
+import torch
+import whisper
+from gtts import gTTS
+import gradio as gr
+from groq import Groq  # Assuming Groq is installed and accessible
+
+# Load the Whisper model
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = whisper.load_model("base", device=device)
+
+# Set your Groq API key
+os.environ["GROQ_API_KEY"] = "your_groq_api_key_here"
+client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
+
+# Function to transcribe audio using Whisper
+def transcribe(audio_path):
+    try:
+        result = model.transcribe(audio_path)
+        return result["text"]
+    except Exception as e:
+        return f"Error during transcription: {e}"
+
+# Function to get response from Groq's LLM
+def get_llm_response(text):
+    try:
+        chat_completion = client.chat.completions.create(
+            messages=[{"role": "user", "content": text}],
+            model="llama-3.3-70b-versatile",
+        )
+        return chat_completion.choices[0].message.content
+    except Exception as e:
+        return f"Error during LLM response generation: {e}"
+
+# Function to convert text to speech
+def text_to_speech(text):
+    try:
+        tts = gTTS(text, lang="en")
+        audio_path = "response.mp3"
+        tts.save(audio_path)
+        return audio_path
+    except Exception as e:
+        return f"Error during text-to-speech conversion: {e}"
+
+# Combined function for processing audio input and generating audio output
+def process_audio(audio_path):
+    transcription = transcribe(audio_path)
+    if "Error" in transcription:
+        return transcription, None, None
+    
+    llm_response = get_llm_response(transcription)
+    if "Error" in llm_response:
+        return transcription, llm_response, None
+    
+    audio_response = text_to_speech(llm_response)
+    if "Error" in audio_response:
+        return transcription, llm_response, audio_response
+
+    return transcription, llm_response, audio_response
+
+# Build the Gradio interface
+with gr.Blocks() as app:
+    gr.Markdown("## Real-Time Voice-to-Voice Chatbot")
+    with gr.Row():
+        with gr.Column():
+            audio_input = gr.Audio(type="filepath", label="Speak", interactive=True)
+        with gr.Column():
+            transcription_output = gr.Textbox(label="Transcription (Text)", lines=2)
+            response_output = gr.Textbox(label="Response (LLM Text)", lines=2)
+            audio_output = gr.Audio(label="Response (Audio)")
+    submit_button = gr.Button("Submit")
+
+    # Connect the input and output components
+    submit_button.click(
+        process_audio,
+        inputs=[audio_input],
+        outputs=[transcription_output, response_output, audio_output],
+    )
+
+# Launch the app
+app.launch()