Pinned Repositories
Gem-System
An "MCP" that handles AI, Vision, Speech, Hearing and Creating Blendshapes and syncing for Unreal Engine.
JayGee_AI_WebApp
An app that uses AI. Supports Speech, Text, Images and Video. It also supports the added POST functions in Neurosync.
NeuroSync_Player
The NeuroSync Player allows for real-time streaming of facial blendshapes into Unreal Engine 5 using LiveLink - enabling facial animation from audio input.
NeuroSync_Local_API
NeuroSync Audio to face animation local inference helper code.
Unreal-Engine-5.6.1-VTuber-Face-ABP
chatterbox
SoTA open-source TTS
embeddinggemma
espeak-ng
eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
listen
A python script that listen to the microphone and then transcribe the speech and send it to Gemini.
NeuroSync_Real-Time_API
A collection of AI model endpoints you can run locally for a real-time audio2face system. Toy demonstration, not for production. Use this to learn!
JayGeeUnreal's Repositories
JayGeeUnreal/Gem-System
An "MCP" that handles AI, Vision, Speech, Hearing and Creating Blendshapes and syncing for Unreal Engine.
JayGeeUnreal/Unreal-Engine-5.6.1-VTuber-Face-ABP
JayGeeUnreal/listen
A python script that listen to the microphone and then transcribe the speech and send it to Gemini.
JayGeeUnreal/NeuroSync_Player
The NeuroSync Player allows for real-time streaming of facial blendshapes into Unreal Engine 5 using LiveLink - enabling facial animation from audio input.
JayGeeUnreal/StyleTTS2
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
JayGeeUnreal/VibeVoice
Frontier Open-Source Text-to-Speech
JayGeeUnreal/chatterbox
SoTA open-source TTS
JayGeeUnreal/espeak-ng
eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
JayGeeUnreal/embeddinggemma
JayGeeUnreal/VibeVoice-ComfyUI
A comprehensive ComfyUI integration for Microsoft's VibeVoice text-to-speech model, enabling high-quality single and multi-speaker voice synthesis directly within your ComfyUI workflows.
JayGeeUnreal/OLMoASR
An open-source implementation of Whisper
JayGeeUnreal/Python-3.12.10
JayGeeUnreal/JayGee_AI_WebApp
An app that uses AI. Supports Speech, Text, Images and Video. It also supports the added POST functions in Neurosync.
JayGeeUnreal/NeuroSync_Trainer_Lite
A multi GPU audio to face animation AI model trainer for your iPhone ARKit data.
JayGeeUnreal/NeuroSync_Real-Time_API
A collection of AI model endpoints you can run locally for a real-time audio2face system. Toy demonstration, not for production. Use this to learn!
JayGeeUnreal/NeuroSync_Local_API
NeuroSync Audio to face animation local inference helper code.