This project provides real-time speech-to-text (STT) and text-to-speech (TTS) captioning for streaming and virtual reality platforms like OBS, VRChat, Twitch, and Discord. It targets streamers, content creators, and VR users seeking enhanced accessibility and interactive features for their audiences.

How It Works

The application integrates with multiple STT and TTS services, including Microsoft Azure, Speechly, Deepgram, and WebSpeechAPI. It offers extensive customization for OBS captions, supporting custom fonts (via Google Fonts), animations, sound effects, particle effects, and CSS styling. For VRChat, it can utilize avatar text and chatbox features, while Twitch integration allows for custom emotes.

Quick Start & Requirements

• Install: Download the latest release from the project's releases page or Discord.
• OBS Setup: Copy the provided link and create a browser source in OBS, adjusting the window size. Alternatively, use the "Set Up OBS" option, which requires the obs-websocket plugin.
• Dependencies: Browser with WebSpeechAPI support (Chrome, Edge) for certain STT/TTS features.

Highlighted Details

• Supports over 1000 Google Fonts for OBS captions.
• Enables the use of 7TV/FFZ/BTTV emotes in Twitch captions.
• Allows STT output to be posted to chat or used as a source for TTS.
• Features a scene management system for saving and switching caption designs.

Maintenance & Community

The project maintains an active Discord server for support, feature requests, bug reports, and release notifications.

Licensing & Compatibility

The license is not explicitly stated in the README. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project is still under active development, with planned features like STT support for Vosk and OpenAI Whisper, and TTS for VoiceVox. The lack of explicit licensing information may pose a barrier to commercial adoption.