Convai Technologies Inc.'s repositories
Convai-UnrealEngine-SDK
This Unreal Engine plugin integrates Convai API for conversational AI and environment perception and action-taking by the AI in Unreal Engine.
ThreeJs-World-Tutorial
This repository contains a React Three Fiber 3D world with ConvAI NPCs. The 3D world is rendered using Three.js and React Three Fiber. The NPCs are created using Convai.
ov_extension
Omniverse extension for Convai Character API
Convai-Web-SDK
Integrate lifelike digital beings into your web applications with real-time conversations, actions, and facial expressions. Supports a variety of voices, languages, and emotions.
Convai-Modding
Source Code for all Convai Mods
Convai_Documentation
Contains iPython notebooks and other files solely used for documentation of our services.
Convai_Discord_Integration
This repository contains the required code to facilitate integration of Convai chat apis with Discord bot for smooth integration
Reallusion-HD-Demo-Sharing
HDRP project for recording Convai Actions tutorial video
app
Web metaverse client
Conv-AI.github.io
For serving static content.
coqa-bert-baselines
BERT baselines for extractive question answering on coqa (https://stanfordnlp.github.io/coqa/)
DeepLearningExamples
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
Convai-Documentation
The official documentation repository for our users.
FastSpeech2
An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
STTS2-AuxiliaryASR
Joint CTC-S2S Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)
STTS2-PitchExtractor
Deep Neural Pitch Extractor for Voice Conversion and TTS Training
STTS2-PL-BERT
Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions
StyleTTS2
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models