Convert Text to Speech in Python

Last Updated : 23 Feb, 2026

Text-to-Speech (TTS) means converting written text into spoken audio. In Python, one of the simplest libraries for this task is gTTS (Google Text-to-Speech).

Features of gTTS

  • Converts text into speech easily
  • Supports multiple languages
  • Saves output in MP3 format
  • Allows normal or slow speech speed
  • Simple and beginner-friendly API

Installation

To install the gTTS library, open the terminal or command prompt and run:

pip install gTTS

Syntax

The basic syntax for gTTS is:

from gtts import gTTS
myobj = gTTS(text="Your text here", lang="en", slow=False)
myobj.save("output.mp3")

Parameters:

  • text: The text you want to convert to speech.
  • lang: Language code (e.g., 'en' for English).
  • slow: True for slow speech, False for normal speed.
  • save(): Saves the audio file as MP3.

Example: This program converts text into speech, saves it as an MP3 file, and plays it using your system's default audio player.

Python 
from gtts import gTTS
import os

mytext = 'Welcome to GeeksforGeeks Joe!'
language = 'en'

myobj = gTTS(text=mytext, lang=language, slow=False)
myobj.save("welcome.mp3")
os.system("start welcome.mp3")

Output

Explanation:

  • myobj = gTTS(text=mytext, lang=language, slow=False): Creates a gTTS object using the given text and language, with normal speech speed.
  • os.system("start welcome.mp3"): Plays the generated audio file using the system’s default media player.
Comment
Article Tags:
Python

Explore