• New TikTok voices added: Wizard, Halloween, Madam Leota, Ghost Host, Pirate, Empathetic, Serious, Grandma, Grinch, Santa, Cupid
• Fix for audio cutting out when increasing rate/speed of Azure and Amazon Polly voices

• tiktok http 3 minute timeout
• tiktok http keepalive false
• new voice codes are also included

shows tiktok inner exception

• IBM Watson TTS voices are now available with Voice Wizard Pro
  • You can find voice samples here: https://cloud.ibm.com/docs/text-to-speech?topic=text-to-speech-voices
• New Spanish TikTok Voices added
• Any characters should now work with Word Replacements
• Upon Receiving a Startup or OnLoad Error more details will now be displayed. Make a Help post in the Discord if you are experiencing this error.
• Whisper model download indicator fixed
• Other bug fixes

• fixes TTS Queue breaking on invalid input from any TTS method

• fixes invalid text inputs getting stuck in queue
• fixes app crashing on voice wizard pro api internal error.

• possible fix for Configuration system failed to initialize
  • set app.config encoding to utf-16 instead of the default utf-8

Changelog

v1.4.1.5 (current)

• changed link for whisper model downloads

v1.4.1

• Soundpad support added, must be launched before TTS Voice Wizard to appear in media list.
• Youtube video tutorial link added to media integration tab
• Media Presets now save update interval and other toggles.
• Timers now use background threads (let me know if anything unexpected happens)
• Supporter Banner Removed
• Bug Fixes

v1.4.0

• Heavily Refactored
• Audio Backend changed heavily
  • Pitch and Rate can now be changed for all voices
• Buttons have been added to password text fields to view their contents
• Corrupted Config Error now takes you to the TTSVoiceWizard config.
• System tray icon changed to new logo
• There is now in indicator under the selection for windows media mode that displays if the output is considered paused.
• Spotify Media Mode will now only output the first artist to match Windows Media Modes output.

v1.3.8

• eleven labs shows API status code and message when it fails now.

• Soundpad support added, must be launched before TTS Voice Wizard to appear in media list.
• Youtube video tutorial link added to media integration tab
• Media Presets now save update interval and other toggles.
• Timers now use background threads (let me know if anything unexpected happens)
• Supporter Banner Removed
• Bug Fixes

• fixes incorrect path errors

• Heavily Refactored
• Audio Backend changed heavily
  • Pitch and Rate can now be changed for all voices
• Buttons have been added to password text fields to view their contents
• Corrupted Config Error now takes you to the TTSVoiceWizard config.
• System tray icon changed to new logo
• There is now in indicator under the selection for windows media mode that displays if the output is considered paused.
• Spotify Media Mode will now only output the first artist to match Windows Media Modes output.

• eleven labs shows API status code and message when it fails now.

Changelog

• media tab customization text presets
• Translated text file added to TextOut for usage with OBS
• change update interval of counters
• Azure volume with pro will now be adjusted client side rather than through ssml characters on the server side to preserve resources
  • Azure volume with pro will be twice as loud/soft on this version until full release (API needs to be updated)

• Updated Whisper Package to hopefully prevent crashing
• other minor fixes

Changelog

v1.3.6 (current)

• UI fixes which should help with weird interactions on some computers

v1.3.5

• VoiceWizardPro now has Speech to Text with DeepGram Recognition
  • this is currently in testing limits for each tier can be found on the VoiceWizardPro Wiki Page.

Settings Tab

Speech Provider > VoiceWizardPro

• Activate Speech to Text in VRChat with /avatar/parameters/DoSpeechToText
• Fixed input or output devices appearing as blanks if the remembered device is not connected upon launch (now selects default)
• azure voices now show a visual error in log when the json file could not be opened
• fixed non pro amazon polly not saving audio to wave file when setting was enabled
• fixed tracker variable autofill being out of date

• VoiceWizardPro now has Speech to Text with DeepGram Recognition
  • this is currently in testing limits for each tier can be found on the VoiceWizardPro Wiki Page. An announcement will be made in the discord when this feature is thoroughly tested.

Settings Tab

Speech Provider > VoiceWizardPro

• Activate Speech to Text in VRChat with /avatar/parameters/DoSpeechToText
• Fixed input or output devices appearing as blanks if the remembered device is not connected upon launch (now selects default)
• azure voices now show a visual error in log when the json file could not be opened
• fixed non pro amazon polly not saving audio to wave file when setting was enabled
• fixed tracker variable autofill being out of date

• fix for being unable to translate non pro voices with pro translation.
• fix for previous updates bug which caused some voices to not work properly with certain settings

• fix for being unable to translate non pro voices with pro translation.
• bug causing voices to produce no audio under certain conditions

Changelog

• Homepage Revamped
• fixed some amazon voices being unable to read their native language
• fixed translation with pro with No TTS selected
• Crashing from Windows Media fixed
• Other fixes

• modified Windows Media Controller package to prevent crashing from device not ready, the error is simply catch'ed and ignored.
• prevent double output upon switching song with windows media mode