Open source. Open possibilities.

A tool to batch-render Serum 1 (.fxp) and Serum 2 (.SerumPreset) presets to audio files using DawDreamer as a headless engine.

FunTTS is a text-to-speech library with a unified interface that supports seamless switching between various open-source TTS engines, offering features like subtitle generation and multi-role dialogue.

A collection of self-contained, browser-based audio instruments and tools focused on generative sound design, resonance, and ambient synthesis using the Web Audio API.

A multi-platform MIDI chords and music theory application. It includes desktop (Python/PySide6), web (Cloudflare Worker), and mobile (Flutter) versions, offering harmonic detection, chord generation, and scale generation.

YuE2 is an open music generation model that unifies symbolic planning with audio synthesis: it turns lyrics and a style prompt into an editable melody-and-chord score, then renders a full song with vocals and accompaniment. It also supports zero-shot covers and agentic score editing.

A Python-based generator for .mod (ProTracker) files that creates algorithmic music using synthesized mathematical waveforms without external dependencies.

VoxCPM2 is a tokenizer-free text-to-speech system with a 2B diffusion autoregressive model supporting 30 languages, voice design from text descriptions, controllable voice cloning, and 48kHz audio output.

ChatTTS is an open-source text-to-speech model built for dialogue scenarios, supporting English and Chinese with multi-speaker output and fine-grained control over laughter, pauses and prosody.

A Linux guitar plugin and application featuring neural models (NAM/AIDA-X), dual model slots, cabinet IRs, and effects including slapback echo, spring/plate reverb, and tremolo. Designed for surf, rockabilly, and psychobilly genres with a Fender blackface style UI.

Sleepyland is an open-source sleep research platform and private browser-based sound machine. It provides evidence-backed guides on sleep topics and generates ambient noise locally without server uploads.

GPT-SoVITS is an open-source few-shot voice conversion and TTS system supporting zero-shot (5s) and few-shot (1min) voice cloning across Chinese, Japanese, Korean, Cantonese, and English. Includes WebUI tools for audio separation, ASR, and dataset preparation.

A rule-based classical piano music generator that creates complete pieces in the browser from a single seed.