app.py

import gradio as gr
import os

def inference(audio, text):
    os.system('python demo_cli.py -audio '+audio.name+' --text '+text.strip())
    return 'demo_output_1.wav'

iface = gr.Interface(inference, inputs=[gr.inputs.Audio(type="file"),"text"], outputs=gr.outputs.Audio(type="file"))

iface.launch()