make_audiobook.py

#!/usr/bin/env python
"""
To use:
1. install/set-up the google cloud api and dependencies listed on https://github.com/GoogleCloudPlatform/python-docs-samples/tree/master/texttospeech/cloud-client
2. install pandoc and pypandoc 
3. create and download a service_account.json ("Service account key") from https://console.cloud.google.com/apis/credentials
4. run GOOGLE_APPLICATION_CREDENTIALS=service_account.json python make_audiobook.py book_name.epub
"""
import sys
import os.path
import pypandoc
from google.cloud import texttospeech

client = texttospeech.TextToSpeechClient()
voice = texttospeech.types.VoiceSelectionParams(
    language_code='en-US', name='en-US-Wavenet-E')
audio_config = texttospeech.types.AudioConfig(
    audio_encoding=texttospeech.enums.AudioEncoding.MP3)


def book_to_text(book_file):
    try:
        return pypandoc.convert_file(book_file, 'plain', extra_args=['--wrap=none'])
    except RuntimeError:
        print("Format not recognized. Treating as plain text...")
        with open(book_file) as book:
            return book.read()


def text_to_mp3(text, file_dest):
    lines = text.splitlines()
    with open(file_dest, 'wb') as out:
        for (i, text_chunk) in enumerate(lines):
            # skip empty lines
            if (len(text_chunk) > 0):
                input_text = texttospeech.types.SynthesisInput(text=text_chunk)
                response = client.synthesize_speech(input_text, voice, audio_config)
                # this is fine because mp3s can be concatenated naively and still work
                out.write(response.audio_content)
                # print progress
                ticks = min(48, round(i / len(lines) * 48))
                bar = "=" * ticks + "." * (48 - ticks)
                sys.stdout.write("\r" + "[" + bar + "]")
                sys.stdout.flush()
    print()

if __name__ == "__main__":
    books = sys.argv[1:]
    for book_file in books:
        print("Processing", book_file)
        text = book_to_text(book_file)
        mp3_file = os.path.join("/tmp/", os.path.splitext(os.path.basename(book_file))[0] + ".mp3")
        text_to_mp3(text, mp3_file)
        print("Generated mp3", mp3_file)