8000 GitHub - kaloyaqn/voice · GitHub
[go: up one dir, main page]

Skip to content
kaloyaqnPublic

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

1 watching

Forks

Latest commit

 

History

13 Commits

Folders and files

Repository files navigation

How to install (currently)


pip install these:

  • pyttsx3
  • SpeechRecognition
  • wikipedia
  • win10toast (works for windows and windows only!!!)
  • gtts
  • playsound
  • wolframalpha
  • you will also need pyaudio and pyspeech

    note: if you have problem with pyaudio (most likely) install an older version

    ------BG------

    if you want your tts to speak in bulgarian do this:

    install TTS.Voices.MegaPack.exe from the installer select VE_Bulgarian_Daria_22kHz

    then run this code in a test.py file (i have included it in the gievn files)

    ####################################################

    import pyttsx3

    engine = pyttsx3.init()

    def speak(audio): engine.say(audio) engine.runAndWait()

    def getvoices(): voices = engine.getProperty('voices') print(voices[0].id)

    getvoices() ####################################################

    then debug test.py with ctrl + f5

    the termial should say something like: HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\YOURTTSVOICE

    after that change the voice id -- (print(voices[changeme].id) -- until you see somethng like this: HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices Tokens\VE_Bulgarian_Daria_22kHz

    remember the voice id and put it in my code

    Now you are ready!

    note: if you have a problem with the installation feel free to contact me!

    About

    No description, website, or topics provided.

    Resources

    Stars

    0 stars

    Watchers

    1 watching

    Forks

    Releases

    Packages

    Contributors

    Languages

    0