PDF to Audio Converter (with Text Chunking)

import pyttsx3
import PyPDF2
from pydub import AudioSegment
import re
import os
from contextlib import closing

def clean_text(text):
    text = re.sub(r'[^\x00-\x7F]+', ' ', text)
    text = re.sub(r'\s+', ' ', text)
    return text.strip()

def dynamic_chunk_text(text, delimiter='. ', max_chunk_length=1000):
    sentences = re.split(f'(?<={delimiter})', text)
    chunks = []
    current_chunk = ''

    for sentence in sentences:
        if len(current_chunk) + len(sentence) <= max_chunk_length:
            current_chunk += sentence
        else:
            if current_chunk:
                chunks.append(current_chunk)
            current_chunk = sentence
    if current_chunk:
        chunks.append(current_chunk)
    return chunks

def export_audio(combined_audio, filename, format='wav'):
    try:
        combined_audio.export(filename, format=format, bitrate="192k")
        print(f"Exported audio file: {filename}")
    except Exception as e:
        print(f"Failed to export audio file: {e}")

def pdf_to_audio_converter(pdf_path, audio_format='mp3'):
    speaker = pyttsx3.init()
    combined_audio = AudioSegment.empty()

    try:
        with open(pdf_path, 'rb') as pdf_file:
            pdfreader = PyPDF2.PdfReader(pdf_file)
            full_text = ''

            for page_num in range(len(pdfreader.pages)):
                text = pdfreader.pages[page_num].extract_text()
                full_text += clean_text(text) + ' '

        chunks = dynamic_chunk_text(full_text)

        for i, chunk in enumerate(chunks):
            with closing(speaker) as engine:
                audio_filename = f'temp_part_{i+1}.{audio_format}'
                engine.save_to_file(chunk, audio_filename)
                engine.runAndWait()
                combined_audio += AudioSegment.from_file(audio_filename, format=audio_format)
                os.remove(audio_filename)

        final_audio_filename = f"final_story.{audio_format}"
        export_audio(combined_audio, final_audio_filename, audio_format)

    except (PyPDF2.errors.PdfReadError, IOError) as e:
        print(f"Error reading PDF file: {e}")
    except Exception as e:
        print(f"An error occurred: {e}")

pdf_to_audio_converter('Brief answers.pdf', 'mp3')