How to Create a Speech Synthesis System with Python

Text-to-speech (TTS) is a fascinating feature that adds a human touch to your Python applications. The gTTS library simplifies the process of incorporating TTS capabilities into your scripts. In this article, we’ll explore a simple Python script that utilizes gTTS to make Python speak and understand the key components of the code.

Create a Speech Synthesis System with Python

Below is the step-by-step procedure to make Python speak by using os.system() in Python:

Step 1: Install Necessary Libraries

To proceed, you need to have the gTTS library installed. Open your terminal and run:

pip install gTTS

Step 2: Create a Python Script

Use your preferred code editor to create a new Python script (e.g., main.py). Below is the breakdown of our main.py file code:

Import Required Modules

In your Python script, import the necessary modules:

Python3

from gtts import gTTS
import os

Define the Speak Function

The speak function encapsulates the text-to-speech functionality. It takes a text input as a parameter and uses pyttsx3 to convert it into spoken words. Optional properties, such as the speech rate, can be set using engine.setProperty.

Python3

def text_to_speech(text):

    res = gTTS(text=text, lang='en')

    filename = "output.mp3"

    res.save(filename)

    os.system(f"start {filename}")

Use the Speak Function

Now, you can use the speak function to make Python speak.

Python3

if __name__ == "__main__":
    text = "Hello, I am GeeksforGeeks and I made a Speech Synthesis System With Python."
    text_to_speech(text)

Complete Code Implementation

Below is the complete code implementation of our Python main.py file.

main.py

Python3

from gtts import gTTS
import os

def text_to_speech(text):
    res = gTTS(text=text, lang='en')
    filename = "output.mp3"
    res.save(filename)
    os.system(f"start {filename}")

if __name__ == "__main__":
    text = "Hello, I am GeeksforGeeks and I made a Speech Synthesis System With Python."
    text_to_speech(text)

Step 3: Run the Script

Save your script and run it using:

python main.py

This will execute the speak function, and you should hear the specified text being spoken by the system’s default TTS engine.

Output:

You will listen an audio saying “Hello, I am GeeksforGeeks and I made a Speech Synthesis System With Python”.