24 skills found
asanchezyali / Talking Avatar With AIThis project is a digital human that can talk and listen to you. It uses OpenAI's GPT to generate responses, OpenAI's Whisper to transcript the audio, Eleven Labs to generate voice and Rhubarb Lip Sync to generate the lip sync.
met4citizen / HeadTTSHeadTTS: Free neural text-to-speech (Kokoro) with timestamps and visemes for lip-sync. Runs in-browser (WebGPU/WASM) or on local Node.js WebSocket/REST server (CPU).
AntiAnti / MetahumVisemeCurvesPose Asset with visemes for Epic's MetaHuman face skeleton
Amoner / Lipsync EngineZero-dependency, renderer-agnostic streaming lip-sync engine for browser-based 2D animation. Real-time viseme detection via AudioWorklet + Web Audio API.
SCRN-VRC / Voice Recognition ShaderAudio detection with visemes in a fragment shader
jetfontanilla / Canvas Talking Head Modelcanvas-based talking head model using viseme data
ShyWolf42 / Copy To MMD VisemesCopies English shape keys to their Japanese counterparts for MMD animations.
YUCHEN005 / UniVPMCode for paper "Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition"
asanchezyali / AI AvatarZippy Talking Avatar uses Azure Cognitive Services and OpenAI API to generate text and speech. It is built with Next.js and Tailwind CSS. This avatar responds to user input by generating both text and speech, offering a dynamic and immersive user experience
team-pp-studio / VoiceTuberVTuber application which only requires your voice and microphone, no need for a webcam or other tracking nonsense.
aflr-archive / Viseme To VideoCreates video from TTS output and viseme images.
met4citizen / HeadAudioHeadAudio: An audio node/processor for real-time audio-driven viseme detection and lip-sync in browsers.
jetfontanilla / Azure Viseme JsonExample code on how to generate viseme json
Magicboomliu / Viseme ClassificationA pipeline from Dataset Gathering,Data annotations, Model training,Model Evaluation for viseme (visual sound phoneme) classification
KyuubiYoru / VisemesAtHomeNo description available
kaaori / AutoVisemeAssignerAuto Detect wasn't doing the job for me. Automatically assigns Visemes generated from CATs for VRChat.
simoncen / Lip Sync VisemeText to speech program that output the Viseme Id for displaying the corresponding SVG.
Adinyk03 / Lip Syncthe given text is converted to speech and this speech is then lip synced with the visemes, that are hardcoded into the code, according to the alphabets and the letters in the text.
amalhotra08 / Custom AvatarA talking head avatar using SadTalker and visemes for realistic lip-sync and expressive facial animations.
mmuppidi / PuppetBotPuppetBot is a cloud powered chatter robot (chatbot) written in python. PuppetBot uses AWS Lex as its chatbot engine. AWS Rekognition for face detection. AWS Polly for converting conversations into visemes, which are used as an input to control lip movements.