Using Google Cloud's API to Create Assistive Technology
Authentication
For this project I made use of Google Cloud's Text-to-Speech client libraries, which provide high-level language support for programmatic authentication. I used locally stored Application Default Credentials (ADC).
I did code a tkinter GUI for this project through which the user could select a pdf from their files, then listen to the generated mp3 in the same GUI. I don't believe this solution offered any advantages over simply outputting the mp3 file to the user's local files though.
Google's Text-to-Speech Technology
The offering from Google here is very impressive.
main.py
"""Synthesizes speech from the input string of text or ssml.
Make sure to be working in a virtual environment.
Note: ssml must be well-formed according to:
https://www.w3.org/TR/speech-synthesis/
"""
from google.cloud import texttospeech
from pypdf import PdfReader
# creating a pdf reader object
reader = PdfReader('sample.pdf')
# printing number of pages in pdf file
print(len(reader.pages))
text_string = ""
for i in range(len(reader.pages)):
page = reader.pages[i]
text = page.extract_text()
text_string += text
print(text_string)
# # creating a page object
# page = reader.pages[0]
#
# # extracting text from page
# text = page.extract_text()
# Instantiates a client
client = texttospeech.TextToSpeechClient()
# Set the text input to be synthesized
synthesis_input = texttospeech.SynthesisInput(text=text_string)
# Build the voice request, select the language code ("en-US") and the ssml
# voice gender ("neutral")
voice = texttospeech.VoiceSelectionParams(
language_code="en-US", ssml_gender=texttospeech.SsmlVoiceGender.NEUTRAL
)
# Select the type of audio file you want returned
audio_config = texttospeech.AudioConfig(
audio_encoding=texttospeech.AudioEncoding.MP3
)
# Perform the text-to-speech request on the text input with the selected
# voice parameters and audio file type
response = client.synthesize_speech(
input=synthesis_input, voice=voice, audio_config=audio_config
)
# The response's audio_content is binary.
with open("output.mp3", "wb") as out:
# Write the response to the output file.
out.write(response.audio_content)
print('Audio content written to file "output.mp3"')
