Real time interactive streaming digital human
Repositories
hacksider repositories
The media player for language learning, with dual subtitles, AI-generated subtitles, realtime-OCR, translation, word lookup, and more!
A high-quality rapid TTS voice cloning model that reaches speeds of 150x realtime.
A research prototype of a human-centered web agent
MAGI-1: Autoregressive Video Generation at Scale
Master Folder
Free, open-source no-code web data extraction platform. Build custom robots to automate data scraping [In Beta]
Unofficial One-click Version of LivePortrait, with Webcam Support
MoCha: End-to-End Video Character Replacement without Structural Guidance
MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS.
A small web app for watching movies and shows easily
Sample code for MS Learn module "Deploy and run a containerized web application with App Service"
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
AI generated UI components
A community-supported supercharged version of paperless: scan, index and archive all your physical documents
PersonaLive! : Expressive Portrait Image Animation for Live Streaming