Re-implementation of the famed Audio Ghost in Python. For Audio Ghost, see https://github.com/gkhays/AudioGhost.

AudioGhostPy.md

Text to Speech in Python

A quick project to convert text files to speech.

Getting Started

A best practice in Python is to not "pollute" your entire workspace with Python modules. Instead, segregate them per project. Accordingly, set up and activate a virtual environment.

$ virtualenv .venv
$.venv/Scripts/activate.bat

Install the Google text to speech API.

pip install gTTS

Run the app.

python demo.py

When you are finished, exit the virtual environment.

deactivate

Next Steps

I started out with the Google text to speech API but the win32com.client sounds more like AudioGhost.

pip install pypiwin32

Code

import win32com.client

speaker = win32com.client.Dispatch("SAPI.SpVoice")

while 1:
    print("Enter the word you want to speak")
    s = input()
    speaker.Speak(s)

# Stop with CTRL + Z

References

• Using Google text to speech API
• Using win32com.client

demo.py

import win32com.client

speaker = win32com.client.Dispatch("SAPI.SpVoice")

while True:
    print("Enter word or phrase >>")
    s = input()
    if s.strip() == 'quit' or s.strip() == 'exit':
        break
    speaker.Speak(s)

# Enter quit or exit on a single line to stop.

gtts_data.txt

Hello earthling, I am glad you came to me. Let us talk. OK bye.

gtts_demo.py

from gtts import gTTS
import os

with open('data.txt', 'r') as datafile:
    text = datafile.read()

language = 'en'

engine = gTTS(text=text, lang=language, slow=False)
engine.save('data.mp3')
os.system("start data.mp3")