Create app.py

app.py

@@ -0,0 +1,31 @@
+from transformers import pipeline
+import gradio as gr
+
+# Load pre-trained models
+stt_model = pipeline("automatic-speech-recognition", model="openai/whisper-base")
+nlp_model = pipeline("text-generation", model="gpt2")
+tts_model = pipeline("text-to-speech", model="tts-coqui/coqui-tts-en")
+
+# Define a function to handle the workflow
+def conversation(audio):
+    # Step 1: Convert speech to text
+    text = stt_model(audio)["text"]
+    # Step 2: Generate a response
+    response = nlp_model(text, max_length=50)[0]["generated_text"]
+    # Step 3: Convert response text to speech
+    audio_response = tts_model(response)
+    return text, response, audio_response
+
+# Create Gradio Interface
+interface = gr.Interface(
+    fn=conversation,
+    inputs=gr.Audio(source="microphone", type="filepath"),
+    outputs=[
+        gr.Textbox(label="Transcription"),
+        gr.Textbox(label="AI Response"),
+        gr.Audio(label="Generated Speech")
+    ]
+)
+
+# Launch the app
+interface.launch()