Simple VoiceVOX sinetizer just for fun
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
2023-03-25 23:58:24 +03:00
src Printer fixed 2023-03-25 23:16:05 +03:00
.gitignore Cache folder removed 2023-03-25 23:18:22 +03:00
config.ini Deleted default AudioDeviceName 2023-03-25 23:24:41 +03:00
main.py Cache folder removed 2023-03-25 23:18:22 +03:00
README.md Update README.md 2023-03-25 23:50:01 +03:00
requirements.txt Using git version of python-romkan 2023-03-25 23:58:24 +03:00

VoiceVOX-voice

Simple VoiceVOX sinetizer for fun (for Discord for example) on multiple languages

Architecture (Really cursed)

Your speech -> Text -> Translit -> Romanji -> Katokana -> VoiceVOX -> Audio Device

Installing

  • Install Python 3.10
  • Install VoiceVOX Server
  • Type pip install -r requirement.txt in your console in project folder

Configuration

  • Speed (Default = 1.75) - Speed of voice
  • Pitch (Default = 0.0) - Pitch of voice
  • Intonation (Default = 1.0) - Intonation of Voice
  • Volume (Default = 3.0) - Output volume
  • StartSilence (Default = 0.05) - Silence before words
  • Stereo (Default = True) - Stereo support
  • SamplingRate (Default = 48000) - Audio device sampling rate
  • RecognitionLanguage (Default = ru) - Language of your speech
  • VoiceNumber (Default = 1) - VoiceVOX voice number (characters)
  • AudioDeviceName (Example = CABLE Input (VB-Audio Virtual Cable), Windows WASAPI (VB-Audio Virtual Cable)) - Name of your audio device and API (Can be obtained from an error in the console on invalid input)