https://github.com/pacistardust/hoscy
Companion for OSC and Communication
https://github.com/pacistardust/hoscy
osc speech-recognition tts voices vrc vrchat
Last synced: 11 months ago
JSON representation
Companion for OSC and Communication
- Host: GitHub
- URL: https://github.com/pacistardust/hoscy
- Owner: PaciStardust
- License: gpl-2.0
- Created: 2022-09-13T21:26:45.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2025-05-20T11:52:28.000Z (about 1 year ago)
- Last Synced: 2025-05-20T12:49:18.496Z (about 1 year ago)
- Topics: osc, speech-recognition, tts, voices, vrc, vrchat
- Language: C#
- Homepage:
- Size: 1.59 MB
- Stars: 38
- Watchers: 2
- Forks: 8
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# HOSCY
HOSCY is a free and Open-Source tool with many utilities for communication and OSC aimed at making communication and use of OSC easier
Need help setting this up? Check the **[Quickstart Guide](https://github.com/PaciStardust/HOSCY/wiki/Quickstart-Guide)**
If you wish to contribute or need support, join the **[Discord](https://discord.gg/pxwGHvfcxs)**
## Features
- **Speech Recognition**
- Windows Speech Recognition
- Locally running AI *(Thanks to [WHISPER](https://github.com/Const-me/Whisper) & [VOSK](https://alphacephei.com/vosk/))*
- Azure Cognitive Services
- Most external APIs *(Provided they use raw audio data)*
- **Utility for communicating**
- A manual textbox for input with preset support
- A customizable system for displaying Text on VRChats chatbox
- Integrated Text-to-Speech support
- **Translation** of whatever you say using an external API of your choice
- **OSC** ***(Open Sound Control)*** **Support** using [CoreOsc](https://github.com/PaciStardust/CoreOSC-UTF8)
- Configurable routing of incomming OSC data
- Sending out OSC data
- Creation of your own OSC command sequences
- Support for **[OSCQuery](https://github.com/vrchat-community/vrc-oscquery-lib)**
- Counters for any parameter and AFK detection
- **Media control** using Voice:
- Simple and non-intrusive "Now Playing" display
## Credits
- **[CoreOSC](https://github.com/PaciStardust/CoreOSC-UTF8)** by ValdemarOrn and Dalesjo for sending and receiving OSC Data
- **[OSCQuery](https://github.com/vrchat-community/vrc-oscquery-lib)** by VRChat for OSC-Service communication
- **[VOSK](https://alphacephei.com/vosk/)** by AlphaCephei for local AI speech recognition
- **[Azure Cognitive Services](https://azure.microsoft.com/en-us/services/cognitive-services/)** for API speech recognition
- **[Const-me](https://github.com/Const-me)** for creating a usable C# whisper wrapper
- **[AuroraNemoia](https://github.com/AuroraNemoia)** for branding *(Logo, Name)*
- **[Hyblocker](https://github.com/hyblocker)** for providing assistance when I got stuck
- **[Realmlist](https://linktr.ee/Realmlist)** for providing assistance and API keys for testing
- **[M.O.O.N](https://twitter.com/MOONVRCHAT)** for creating a youtube tutorial and sfx for muting and unmuting
- **[DrBlackRat](https://twitter.com/DrBlackRat)** for creating the Avatar 3.0 menu for VRChat use