Pyttsx3 voice tone and language configuration

Question

I am using the pyttsx3 module for text-to-speech in for an ai python assistant, but I am not able to choose a male/female option for voices. I read the documentation given on https://pypi.org/project/pyttsx3/ where it says use voices[0].id/voices[1].id for male and female voices respectively. However, that does not seem to work as there is no significant difference between the 2 voices.

this is my code:

    import pyttsx3
    engine = pyttsx3.init()

    voices = engine.getProperty('voices')
    engine.setProperty('voice', voices[0].id)

    engine.say("Hello World!")
    engine.runAndWait()

also is there any way to configure the language of the voice?

Answer 1

Actually, the documentation is not updated and correct for all operating systems.

First, check if there is a female voice among the available voices:

import pyttsx3

engine = pyttsx3.init()

voices = engine.getProperty("voices")

for voice in voices:
    print(voice)

<Voice id=afrikaans
          name=afrikaans
          languages=[b'\x05af']
          gender=male
          age=None>
<Voice id=aragonese
          name=aragonese
          languages=[b'\x05an']
          gender=male
          age=None>
<Voice id=bulgarian
          name=bulgarian
          languages=[b'\x05bg']
          gender=None
          age=None>
...

I couldn't find the female voice myself. If you are using Linux/espeak, it seems that there are no specific female voices. However, you can simulate them using +f1 to +f4 intonations. The following code loops through all available combinations to help you find a suitable sample:

import pyttsx3

engine = pyttsx3.init()

voices = engine.getProperty("voices")

for voice in voices:
    for intonation in ["+f1", "+f2", "+f3", "+f4"]:
        print(voice.id, intonation)
        engine.setProperty('voice', voice.id + intonation)

        engine.say("Hello World!")
        engine.runAndWait()

        input("Press enter to continue ...")