TTS Voice Wizard Documentation

website·Indexed 31 days ago

https://ttsvoicewizard.com/docs/intro

Documentation for TTS Voice Wizard, a tool for text-to-speech and speech-to-text integration. Features include support for Amazon Polly, Google Cloud, ElevenLabs, IBM Watson, and Whisper, as well as VRChat listener integration, OSC support, translation services, and custom voice cloning.

Tokens
16.6K
Snippets
38
Records
181
Agent score
60%

What's inside TTS Voice Wizard

  1. Overview of TTS Voice Wizard features

    TTS Voice Wizard is an open-source application providing accessibility and communication tools for VRChat, VTubers, and streamers. Key capabilities include:

    • Speech-to-Text & Text-to-Speech: Convert spoken words to text and back to speech using various recognition and synthesis methods.
    • VRChat Integration: Send speech as OSC messages to be displayed via VRChat's Chatbox or avatar components like KillFrenzyAvatarText and Frosty's Billboard.
    • Translation: Translate speech into over 70 supported languages.
    • Voice Customization: Access to 100+ different voices.
    • External Data Display: Display current Spotify/browser songs, tracker/controller battery life (via XSOverlay), and heart rate (via Pulsoid or HRtoVRChat_OSC).
    • Avatar Control: Use voice commands to control VRChat avatar parameters.
    • Interactive Counters: Display customizable counters triggered by VRChat contact receivers.
  2. Use OpenAI Whisper for high quality speech recognition

    TTS Voice Wizard leverages OpenAI's Whisper speech recognition technology to provide accurate and reliable speech-to-text conversion.
  3. Deepgram continuous usage and silence trimming updates

    Deepgram integration now supports continuous usage and features improved silence trimming for better audio processing.
  4. Use Deepgram for continuous audio and improved silence trimming

    Deepgram is now supported for continuous use, and the silence trimming functionality has been improved for better audio processing.
  5. Use DeepGram Speech Recognition in VoiceWizardPro

    DeepGram Speech Recognition is now available as a feature within VoiceWizardPro, providing speech-to-text (STT) capabilities.
  6. Translate speech into multiple languages

    TTS Voice Wizard supports speech translation into over 70 different languages, enabling communication with users globally.