app.py

import gradio as gr
from transformers import pipeline

asr = pipeline("automatic-speech-recognition", model="openai/whisper-small")
tts = pipeline("text-to-speech", model="espnet/kan-bayashi_ljspeech_vits")
chatbot = pipeline("text-generation", model="tiiuae/falcon-rw-1b")

def voice_bot(audio):
    text = asr(audio)["text"]
    reply = chatbot(text, max_length=50)[0]["generated_text"]
    speech = tts(reply)
    return reply, (speech["sampling_rate"], speech["audio"])

gr.Interface(
    fn=voice_bot,
    inputs=gr.Audio(source="microphone", type="filepath"),
    outputs=["text", "audio"],
    title="🎤 AI Voice Assistant"
).launch()