TTS Voice Wizard

TTS Voice Wizard is a free, open source Windows application that converts speech to text and text back to speech, built for VRChat players, VTubers and streamers. It uses OpenAI's Whisper for speech recognition and offers more than 100 voices with customization options, and it can translate speech into over 70 languages. Beyond voice features, it is built around VRChat integration. Spoken text can be sent as OSC messages to display on an avatar through a chatbox or avatar text systems, and voice commands can control avatar parameters. Other features include customizable interactive counters for contact receiver touches, display of the current Spotify track, tracker and controller battery levels through XSOverlay, and heart rate display through Pulsoid or HRtoVRChat_OSC. The vendor positions these as accessibility features, and the app also works outside VRChat. Documentation is available on the site, with help through a Discord server. The app is free to download. An optional VoiceWizardPro subscription through Patreon or Ko fi unlocks premium voices from cloud services including Microsoft Azure, Amazon Polly, Google Cloud and IBM Watson, extended translation, and speech recognition through Deepgram's Nova 2 model. The site does not publish a price for that subscription.