NVIDIA NeMo Speech is an Apache-2.0 PyTorch framework for building, customizing and deploying speech AI models, covering automatic speech recognition, text-to-speech and speech LLMs, with pre-trained checkpoints and Docker/uv install paths.
Open source. Open possibilities.
Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONValis is a virtual analog synthesis system that lets users build circuits using RDF/Turtle syntax, with UI views for controls, circuit diagrams, and code. It supports LLM-driven design via MCP and runs as a standalone app or DAW plugin.
MPCTK is a Python toolkit for creating, editing, and generating Akai MPC Sample (.xpj) projects. It supports sample injection, pad layout generation (chromatic/scale-based), transposition, and preserves project structure. Validated on physical hardware.
Olla Nest is a self-hosted, admin-controlled AI workspace that integrates local Ollama models and cloud providers with an automatic request router.
An open-source wavetable synthesizer built on the ESP32-S3, designed to explore high-quality embedded audio synthesis using affordable hardware.
MuJoCo is a general-purpose physics engine designed for fast and accurate simulation of articulated structures interacting with their environment.
thinksynth is a modular software synthesizer and algorithmic composition engine that builds sounds and music using a graph of DSP nodes.
fabu is a collaborative music creation program featuring a piano roll, custom instruments, and real-time multiplayer capabilities for up to 100 users.
An 8-voice analog synthesizer with digital control, featuring a modulation matrix and digital recall for over 100 presets.
Fonoster is an open-source programmable telecommunications stack designed as an alternative to Twilio, allowing businesses to connect telephony services with the internet via a cloud-based utility.
A cross-platform plugin for the Elektron SidStation that allows individual control of its three MOS6581 SID voices from a DAW using the ASID protocol.
Python bindings for the Dexed DX7 synthesizer, providing tools for patch editing, sysex management, and ML-ready preset representations.
fizzle converts WAV/SFZ files into Casio FZ sampler disk images. Supports CLI and browser editor for creating, editing, and managing floppy disk images for FZ-1/10M/20M samplers.