HeadTTS: 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 (WebGPU/CPU).
-
Updated
Oct 24, 2026 - JavaScript
HeadTTS: 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 (WebGPU/CPU).
HeadAudio: An audio node/processor for real-time audio-driven viseme detection and lip-sync in browsers.
Expressive face and body for TalkingHead avatars, decided by a classifier that reads the transcript.
A Streamlit app leveraging OpenAI's GPT-3.5 Turbo for trend discovery and video script generation, integrated with D-ID and HeyGen for video production. A one-stop solution for modern content creators.
LAM Gaussian-Splat Avatars for AI voice agents. Realistic avatars for interview/support/sales agents.
2021 Line Webtoon Year-in-Review Project :: Animation Production
[CVPR 2026] IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face Generation
Always-on embodied AI terminal for the home. A Raspberry Pi that sees you, knows who you are, and answers out loud through a lip-synced 3D avatar. Fully self-hosted, no cloud.
Avatar 3D conversacional en espanol con voz clonada, corriendo en local en 6 GB de VRAM: faster-whisper + LLM con fallback + XTTS-v2 + RAG (LanceDB) + lipsync espanol propio
Backend implementation of Conflicta, an AI-Powered Conflict Resolution Training Platform. Project submission to ScienceHack 2025, Munich.
Patchbay — a local voice instrument. Talk to your own models on your own hardware.
Markdown slides to HTML, PDF and narrated video
To associate your repository with the talkinghead topic, visit your repo's landing page and select "manage topics."