[Python] synthesizer in windows sounds much better than in linux (python and pyttsx3)

I've made a simple text_to_speech function in python based on pyttsx3 library (in polish language).

import pyttsx3 as tts

engine = tts.init()
engine.setProperty('rate', 130)
engine.setProperty('voice', 'polish')

def text_to_speech(text):
engine.say(text)
engine.runAndWait()


When I run this on windows the voice is tolerable, but in linux sounds teribble (windows 10 and ubuntu 18.04, pyttsx==2.9 on both machines).

I've also made for loop to print all available voices:

voices = engine.getProperty('voices')

for voice in voices:
print("Voice:")
print("ID: %s" %voice.id)
print("Name: %s" %voice.name)
print("Age: %s" %voice.age)
print("Gender: %s" %voice.gender)
print("Languages Known: %s" %voice.languages)


Output in windows:

Voice: ID: HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_PL-PL_PAULINA_11.0 Name: Microsoft Paulina Desktop - Polish Age: None Gender: None Languages Known: [] Voice: ID: HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-US_ZIRA_11.0 Name: Microsoft Zira Desktop - English (United States) Age: None Gender: None Languages Known: []


Output in linux:

Voice:
ID: english-us
Name: english-us
Age: None
Gender: male
Languages Known: \[b'\\x02en-us'\]

Voice:
ID: polish
Name: polish
Age: None
Gender: male
Languages Known: \[b'\\x05pl'\]

Voice:
ID: brazil
Name: brazil
Age: None
Gender: male
Languages Known: \[b'\\x05pt-br'\]


and a lot of other languages
(...)


Is there a way to install other polish voices on linux version of pyttsx3 (or maybe other library)?

Continue reading...