app.py

import gradio as gr
import os
import shlex

os.system('chmod 777 encoder')
os.system('chmod 777 synthesizer')
os.system('chmod 777 vocoder')
os.system('wget https://github.com/blue-fish/Real-Time-Voice-Cloning/releases/download/v1.0/pretrained.zip')
os.system('unzip pretrained.zip')

def inference(audio, text):
    os.system("python demo_cli.py --audio_path "+audio.name+" --text "+shlex.quote(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()