Transform Your PDFs into Personalized Audiobooks using Python and GTTs: Practical Guide

4 min readJul 4, 2024

Introduction

Ever wished your books could read themselves to you while you juggle your daily chores? Imagine having your favorite novel or that never-ending work report narrate itself in your preferred accent, all while you’re making dinner or stuck in traffic. Sounds like magic, right? Well, buckle up because today, we’re diving into a nifty script that makes this dream a reality! Let’s sprinkle a little humor, as we unravel how to turn your PDFs into personalized audiobooks. After all, who needs an actual human narrator when you have technology on your side?

The Magic Script: Converting PDFs to Audio

Our innovative script not only extracts text from PDF files but also converts it into speech with a customizable accent. Yes, you heard that right — whether you fancy a Spanish accent from Spain, Mexico, or Colombia, this script has got you covered!

Get Kevin Meneses González’s stories in your inbox

Join Medium for free to get updates from this writer.

Remember me for faster sign in

Here’s a sneak peek at what our script offers:

Text to Speech with Accent Personalization: Choose your preferred accent using the tld parameter.
Robust Error Handling: Ensures a smooth conversion process with efficient error management.
User-Friendly: Simply provide the PDF file path and the save location for the MP3, and let the script do the rest!
Flexible and Customizable: Adjust the number of pages to convert and the narration language as per your needs.

How Does It Work?

Here’s the core of our script, designed to convert your PDFs into delightful audio files:

from gtts import gTTS
import PyPDF2
ef pdf_to_speech(pdf_path, audio_path, lang='es', num_pages_to_read=10, tld='com'):
    try:
        with open(pdf_path, 'rb') as file:
            reader = PyPDF2.PdfReader(file)
            num_pages = len(reader.pages)
            text = ""
            for page in range(min(num_pages, num_pages_to_read)):
                text += reader.pages[page].extract_text()
        tts = gTTS(text, lang=lang, tld=tld)
        tts.save(audio_path)
        print(f'Audio file saved at: {audio_path}')
    except FileNotFoundError:
        print(f'The file at {pdf_path} was not found.')
    except PyPDF2.errors.PdfReadError:
        print(f'There was an error reading the PDF file at {pdf_path}.')
    except Exception as e:
        print(f'An error occurred: {e}')
# Parameters
pdf_path = 'C:/Users/kevin/Downloads/LIBERTAD-INMOBILIARIA_Carlos-Galan_Actualizado-2024.pdf'
audio_path = 'C:/Users/kevin/Downloads/Libertad_Inmobiliaria_Cap1_2.mp3'
lang = 'es'
num_pages_to_read = 10
tld = 'com.mx'  # Example: for Mexican Spanish
pdf_to_speech(pdf_path, audio_path, lang, num_pages_to_read, tld)

Importing Libraries:
from gtts import gTTS: Imports the Google Text-to-Speech module for converting text to speech.
import PyPDF2: Imports the PyPDF2 module to read and extract text from PDF files.
Defining the Function pdf_to_speech:
Parameters:
pdf_path: Path to the PDF file to be converted.
audio_path: Path where the resulting MP3 file will be saved.
lang: Language for the text-to-speech conversion. Default is Spanish ('es').
num_pages_to_read: Number of pages to read from the PDF. Default is 10.
tld: Top-level domain for selecting the accent. Default is 'com'.
Error Handling with try/except:
FileNotFoundError: Catches errors if the specified PDF file is not found.
PyPDF2.errors.PdfReadError: Catches errors related to reading the PDF file.
General Exception: Catches any other exceptions and prints the error message.
Reading and Extracting Text from the PDF:
Opens the PDF file in read-binary mode.
Initializes the PDF reader.
Extracts text from the specified number of pages.
Converting Text to Speech:
Uses gTTS to convert the extracted text to speech, specifying the language and top-level domain for accent.
Saves the resulting audio file to the specified path.
Printing Confirmation:
Prints a message confirming that the audio file has been saved successfully

Case Studies: Real-World Applications

Multitasking Moms and Dads: Imagine a busy parent who wants to catch up on their reading while cooking dinner or doing laundry. This script can convert their favorite parenting book or latest novel into an audio format, making it easier to stay informed and entertained amidst daily tasks.
Commuters: Long commutes can be tedious. With this script, commuters can turn their daily ride into a productive session by listening to work documents or educational materials.
Students: Students can convert their study materials into audio files, making it easier to review notes and chapters on the go. This is especially helpful for auditory learners who grasp information better through listening.
Language Learners: Learning a new language? Convert language learning materials into audio files with your desired accent to improve pronunciation and comprehension skills.

Conclusion: Alternatives and Final Thoughts

While our script is a fantastic tool, there are several alternatives available for those who prefer a ready-made solution:

Amazon Polly: Offers a variety of lifelike voices and supports multiple languages and accents.
Google Cloud Text-to-Speech: Provides high-fidelity speech synthesis and customization options.
IBM Watson Text to Speech: Known for its advanced AI capabilities and wide range of voices.

Each of these services offers unique features, and while they might come at a cost, they provide excellent quality and reliability.

In summary, converting your PDFs to audio with a personalized accent is not just possible but also incredibly easy with our script. Whether you’re a multitasking parent, a daily commuter, or someone looking to enhance their language skills, this tool can make your life significantly easier. So, why not give it a try and add a touch of tech magic to your routine? And remember, with technology on your side, even your books can have an accent!

Full code here (Give me a star⭐)

https://github.com/Kevinelectronics/youtube/blob/main/pdf_to_audio.py

Follow me on Youtube
https://www.youtube.com/channel/UC8B7LR70zfRE1zbESFkyyzQ?sub_confirmation=1
Follow me on Linkedin
https://www.linkedin.com/in/kevin-meneses-897a28127/
Follow on Medium
https://medium.com/@kevinmenesesgonzalez/subscribe
Subscribe to Data Pulse Newsletter
https://www.linkedin.com/newsletters/datapulse-python-finance-7208914833608478720