Create app.py

app.py

@@ -0,0 +1,56 @@
+import gradio as gr
+import speech_recognition as sr
+import pyttsx3
+import tempfile
+
+# Initialize text-to-speech engine
+engine = pyttsx3.init()
+
+def transcribe_audio(audio_path):
+    # Initialize recognizer
+    recognizer = sr.Recognizer()
+    
+    # Use audio file to process audio
+    with sr.AudioFile(audio_path) as source:
+        audio_data = recognizer.record(source)
+    
+    # Transcribe audio to text
+    try:
+        text = recognizer.recognize_google(audio_data)
+        return text
+    except sr.UnknownValueError:
+        return "Sorry, I did not understand the audio."
+    except sr.RequestError:
+        return "Sorry, there was an error with the speech recognition service."
+
+def generate_audio_response(name):
+    # Generate personalized greeting
+    greeting = f"Hello {name}, welcome!"
+    
+    # Create a temporary file to save the speech
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp_file:
+        audio_path = temp_file.name
+        
+    # Save the greeting to an audio file
+    engine.save_to_file(greeting, audio_path)
+    engine.runAndWait()
+    
+    return audio_path
+
+def greet_user(audio):
+    # Transcribe the user's name from audio input
+    name = transcribe_audio(audio)
+    
+    # Generate and return the audio response
+    response_audio = generate_audio_response(name)
+    return response_audio
+
+# Define the Gradio Interface
+demo = gr.Interface(
+    fn=greet_user,
+    inputs=gr.inputs.Audio(source="microphone", type="filepath"),
+    outputs="audio"
+)
+
+# Launch the interface
+demo.launch()