How to Convert Text to Speech in Python with 5 Powerful TTS Libraries

This article introduces five Python libraries for text‑to‑speech conversion and demonstrates how to install, configure, and generate audio files with each.

1. gTTS

gTTS converts any text into an MP3 audio file.

pip install gtts

from gtts import gTTS

Configure the client: tts = gTTS(text=text, lang='zh-tw') Save the audio:

tts.save("output.mp3")

2. Baidu AIP

Use Baidu's speech synthesis service by creating an account on the Baidu Open Platform.

# Install Baidu AIP
pip install baidu-aip

from aip import AipSpeech

APP_ID = 'your_app_id'
API_KEY = 'your_api_key'
SECRET_KEY = 'your_secret_key'
client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)

res = client.synthesis(text, 'zh', 1, {
    'spd': 5,
    'pit': 5,
    'vol': 5,
    'per': 0
})
with open('output.mp3', 'wb') as f:
    f.write(res)

3. pyttsx3

pyttsx3 is an offline TTS engine that allows voice property adjustments.

pip install pyttsx3

import pyttsx3

engine = pyttsx3.init()

engine.say('Hello World')
engine.runAndWait()

Adjust volume:

vol = engine.getProperty('volume')
engine.setProperty('volume', vol + 0.5)

Start a loop for continuous playback:

engine.startLoop()

4. pywin32

pywin32 provides access to Windows COM interfaces, enabling speech synthesis via SAPI.

pip install pywin32

import win32com.client

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

Note: Chinese language support is limited.

5. speech

The speech library, built on top of pywin32, is convenient for voice‑controlled scripts.

pip install speech

import speech
speech.say('hello')

These five libraries cover a range of use cases from simple online TTS to offline, customizable speech synthesis. Choose the one that best fits your project requirements.