app.py

import gradio as gr
from gtts import gTTS
import io
import os
import time
from gtts.lang import _main_langs

AUDIO_DIR = 'audio_files'
MAX_FILE_AGE = 24 * 60 * 60  # maximum age of audio files in seconds (24 hours)

def text_to_speech(text, lang, tld):
    # map the language name to its corresponding code
    lang_codes = {lang_name: lang_code for lang_code, lang_name in _main_langs().items()}
    lang_code = lang_codes[lang]

    # create the text-to-speech audio
    tts = gTTS(text, lang=lang_code, tld=tld)
    fp = io.BytesIO()
    tts.write_to_fp(fp)
    fp.seek(0)

    # create the audio directory if it does not exist
    os.makedirs(AUDIO_DIR, exist_ok=True)

    # generate a unique file name for the audio file
    file_name = str(time.time()) + '.wav'
    file_path = os.path.join(AUDIO_DIR, file_name)

    # save the audio stream to a file
    with open(file_path, 'wb') as f:
        f.write(fp.read())

    # delete old audio files
    delete_old_audio_files()

    # return the file path
    return file_path, f.name

def delete_old_audio_files():
    # delete audio files older than MAX_FILE_AGE
    now = time.time()
    for file_name in os.listdir(AUDIO_DIR):
        file_path = os.path.join(AUDIO_DIR, file_name)
        if now - os.path.getmtime(file_path) > MAX_FILE_AGE:
            os.remove(file_path)

# list of supported TLDs
tlds = [
    "com",
    "ad",
    "ae",
    "com.af",
    "com.ag",
    "com.ai",
    "com.ar",
    "as",
    "at",
    "com.au",
    "az",
    "ba",
    "com.bd",
    "be",
    "bf",
    "bg",
    "bj",
    "br",
    "bs",
    "bt",
    "co.bw",
    "by",
    "com.bz",
    "ca",
    "cd",
    "ch",
    "ci",
    "co.ck",
    "cl",
    "cm",
    "cn",
    "com.co",
    "co.cr",
    "cv",
    "dj",
    "dm",
    "com.do",
    "dz",
    "com.ec",
    "ee",
    "com.eg",
    "es",
    "et",
    "fi",
    "com.fj",
    "fm",
    "fr",
    "ga",
    "ge",
    "gg",
    "com.gh",
    "com.gi",
    "gl",
    "gm",
    "gr",
    "com.gt",
    "gy",
    "com.hk",
    "hn",
    "ht",
    "hr",
    "hu",
    "co.id",
    "ie",
    "co.il",
    "im",
    "co.in",
    "iq",
    "is",
    "it",
    "iw",
    "je",
    "com.je",
    "jo",
    "co.jp",
    "co.ke",
    "com.kh",
    "ki",
    "kg",
    "co.kr",
    "com.kw",
    "kz",
    "la",
    "com.lb",
    "li",
    "lk",
    "co.ls",
    "lt",
    "lu",
    "lv",
    "com.ly",
    "com.ma",
    "md",
    "me",
    "mg",
    "mk",
    "ml",
    "mm",
    "mn",
    "ms",
    "com.mt",
    "mu",
    "mv",
    "mw",
    "com.mx",
    "com.my",
    "co.mz",
    "na",
    "ng",
    "ni",
    "ne",
    "nl",
    "no",
    "com.np",
    "nr",
    "nu",
    "co.nz",
    "com.om",
    "pa",
    "pe",
    "pg",
    "ph",
    "pk",
    "pl",
    "pn",
    "com.pr",
    "ps",
    "pt",
    "com.py",
    "com.qa",
    "ro",
    "ru",
    "rw",
    "com.sa",
    "com.sb",
    "sc",
    "se",
    "com.sg",
    "sh",
    "si",
    "sk",
    "com.sl",
    "sn",
    "so",
    "sm",
    "sr",
    "st",
    "com.sv",
    "td",
    "tg",
    "co.th",
    "com.tj",
    "tl",
    "tm",
    "tn",
    "to",
    "com.tr",
    "tt",
    "com.tw",
    "co.tz",
    "com.ua",
    "co.ug",
    "co.uk",
    "com,uy",
    "co.uz",
    "com.vc",
    "co.ve",
    "vg",
    "co.vi",
    "com.vn",
    "vu",
    "ws",
    "rs",
    "co.za",
    "co.zm",
    "co.zw",
    "cat",
]

# create the Gradio interface
iface = gr.Interface(fn=text_to_speech, 
                     inputs=[gr.inputs.Textbox(lines=10, label="Enter your text here:"),
                             gr.inputs.Dropdown(choices=list(_main_langs().values()), label="Select language:"),
                             gr.inputs.Dropdown(choices=[tld for tld in tlds], label="Select TLD:", default="com")], 
                     outputs=[gr.Audio(label="Audio"), gr.File(label="Audio File")],
                     allow_flagging="never")

iface.launch(enable_queue=True)