app.py

import gradio as gr
import pandas as pd


import numpy as np

import time

def show_inputs(text, image, audio):
    return f"You said: {text}", image, audio

demo = gr.Interface(
    fn=show_inputs,
    inputs=[
        gr.Textbox(label="Your Text"),
        gr.Image(label="Upload Image"),
        gr.Audio(label="Upload Audio")
    ],
    outputs=["text", "image", "audio"]
)

demo.launch(share=True)