Create app.py

app.py

@@ -0,0 +1,18 @@
+import gradio as gr 
+from transformers import pipeline
+
+
+speech_to_text = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")
+text_generation = pipeline("text-generation", model="NousResearch/Hermes-2-Pro-Llama-3-8B")
+text_to_speech = pipeline("text-to-speech", model="kakao-enterprise/vits-ljs")
+
+def alexa(audio):
+    text = speech_to_text(audio)["text"]
+    generate = text_generation(text, max_length=60)[0]["generated_text"]
+    speech = text_to_speech(generate, lang="en", num_of_speakers = 2)["speech"]
+    return speech
+
+gr.Interface.from_pipeline(
+    fn = alexa,
+    inputs = [gr.inputs.Audio(source="microphone", type="filepath")],
+    outputs = [gr.outputs.Audio()], live=True).launch()