🦍 The Cloud-Native Gateway for APIs & AI

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal is…

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…

Full stack web app which lets users upload & browse videos in order to analyze their content using an AI model based on the LLAMA LLM.

Mouseover Translate Any Language At Once - Chrome Extension: PDF Translator, EBOOK, EPUB, OCR, TTS, YOUTUBE DUAL SUBTITLES, GOOGLE DOCS, AI, VIEWER, GMAIL, WRITING, IMAGE, DUAL SUBS, MANGA, HOVER, …

CLI tool for automatic subtitling using whisper.

auto video translation-video translator can auto translate video hard subtitles, auto video translation and dubbing, remove any video text, auto remove video subtitles/text. 自动视频翻译配音，自动翻译视频字幕和回填样式，…

background voice detection program that listens for a wake word and activates transcription mode

If you're struggling with creating subtitles for your video, we're here to help you do it in no time.

Focus on prompting and generating

The best and simplest free open source website change detection, restock monitor and notification service. Restock Monitor, change detection. Designed for simplicity - Simply monitor which websites…

Zero: A simple and fast Python RPC framework

Open Source FAST Channel Engine library based on VOD2Live technology

A fullstack starter with Next.js, Tailwind, Shadcn UI, FastAPI, SQLAlchemy, Pydantic, Alembic, Asyncio, Postgres, Redis, Celery, RabbitMQ

(In development) Microservices full-stack single-page web app built with Typescript, React, Redux, Styled Components (for CSS-in-JS), Python, Django, Redis, and PostgreSQL. Separate servers for LIM…

Bayesian multi-object tracking

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Generate 3D objects conditioned on text or images

Characterize Anything: A Wondrous Chemical Reaction between vision models and AI Characters

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

A web-based document annotation tool, powered by GPT-4 🚀

A PyTorch implementation of text-to-3D models, e.g., DreamFusion and Magic3D, based on NerfAcc.

Web app for keeping track of buildings in danger of collapsing in the event of an earthquake

🎨 ArtPlayer.js is a modern and full featured HTML5 video player

Master thesis- Movie web portal with support for data classification and prediction using deep learning methods

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.