from image import *
from language import *
from textToSpeach import *
from translation import *
import streamlit as st
import base64


# url = "https://i.imgur.com/qs0CxjE_d.webp?maxwidth=760&fidelity=grand"
# text = "How many cars are here?"

st.write('Part 1')

question = st.text_input('Posez votre question')
url = st.text_input('mettez le liens de votre image')
tts = st.checkbox('lire la réponse')
if url :
    st.image(url, width=250)


if st.button('générer'):
    question = frenchtoenglish(question)
    responseBase = image(url, question)
    st.write('response is :', responseBase)

    st.write('Part 2')
    enResponse = longText(responseBase, question)
    frResponse = englishtofrench(enResponse)
    st.write('en : ',enResponse)
    st.write('fr : ',frResponse)

    st.write('Part 3 : TTS')

    if tts:
        st.write('le TTS est en cours de chargement')
        st.audio(speaking(frResponse))
        def autoplay_audio(file_path: str):
            with open(file_path, "rb") as f:
                data = f.read()
                b64 = base64.b64encode(data).decode()
                md = f"""
                    <audio controls autoplay="true">
                    <source src="data:audio/mp3;base64,{b64}" type="audio/mp3">
                    </audio>
                    """
                st.markdown(
                    md,
                    unsafe_allow_html=True,
                )


        st.write("# Auto-playing Audio!")

        autoplay_audio("DoTTS_generation.wav")
    else:
        st.write('Pas de tts demander')