JavaScript/TypeScript-native, low-boilerplate, object-capability RPC system

An interactive HTML pretty-printer for machine learning research in IPython notebooks.

🍦 Never use print() to debug again.

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.

Make your pi images smaller!

MCP generator for OpenAPIs 🫳🎤💥

A Conversational Speech Generation Model

A little fail-safe filesystem designed for microcontrollers

SuperCollider's scsynth audio engine as a web audioworklet

New version of CDP software

Cartridge for the Commodore 64 that packs a punch

An invertible and differentiable implementation of the Constant-Q Transform (CQT).

Virtual Lyra 8 in VST3, VST2, AUi, LV2 (Camomile) and Standalone (Pure Data) format.

Node based GUI for The Composers Desktop Project

MCP sever for controlling Elektron devices using LLMs

Unified automatic quality assessment for speech, music, and sound.

A library implementing the EBU R128 loudness standard.

A high-performance inference engine for AI models

code based for rectified flow

W&B Server is the self hosted version of Weights & Biases

Release for Improved Denoising Diffusion Probabilistic Models

A simple C++ library for reading and writing audio files.

The financial transactions database designed for mission critical safety and performance.

Sound As Pure Form - a Forth-like language for audio synthesis using lazy lists and APL-like auto-mapping.

A reimplementation of Stable Diffusion 3.5 in pure PyTorch

source for the pikocore drum machine

Safe rust abstractions over libpd.

Flexible LoRA Implementation to use with stable-audio-tools

A text to audio pipeline using Riffusion (a finetuned stablediffusion model) and using RAVE a audio to audio AutoEncoder.

music generation with masked transformers!