app.py

import gradio as gr
import os

def inference(text,audio):
  os.system('tts  --text '+text+' --model_name tts_models/multilingual/multi-dataset/your_tts  --speaker_wav '+audio+' --language_idx "en"')
  return "tts_output.wav"
  
gr.Interface(inference,["text",gr.Audio(type="filepath")],gr.Audio(type="filepath")).launch()