I want to create a web-based real-time voice-to-text application using HTML and JS files. However, my HTML content is somewhat long and cannot correctly display the speech recognition box. Where should I set it so that I can correctly display all the html

from pathlib import Path
from typing import Optional

import streamlit as st
import streamlit.components.v1 as components

# Tell streamlit that there is a component called audio2text,
# and that the code to display that component is in the "frontend" folder
frontend_dir = (Path(__file__).parent / "frontend").absolute()
_component_func = components.declare_component(
	"audio2text", path=str(frontend_dir)
)

# Create the python function that will be called
def audio2text():
    """
    Add a descriptive docstring
    """
    _component_func()

def main():
    # st.set_page_config()
    st.write("## Offline real-time speech-to-text")
    audio2text()


if __name__ == "__main__":
    main()