AI Agent Skills

Multi-agent systems, memory, planning, reasoning loops

Production First and Production Ready End-to-End Speech Recognition Toolkit

A framework for efficient model inference with omni-modality models

Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/multiplatform CPU, AMD, NVIDIA GPU PyTorch support, handling, and auto-stitching

:movie_camera: Python and OpenCV-based scene cut/transition detection program & library.

Generate audiobooks from EPUBs, PDFs and text with synchronized captions.

On-device wake word detection powered by deep learning

PHP library allowing thumbnail, snapshot or PDF generation from a url or a html page. Wrapper for wkhtmltopdf/wkhtmltoimage

Effort free video editing!

OpenAI Whisper ASR Webservice API

A small speech recognizer

A nearly-live implementation of OpenAI's Whisper.

Converts text to speech in realtime

Advancing Open-source World Models

The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!

A unified inference and post-training framework for accelerated video generation.