AudioHacking ORG

AceForge is a local-first AI music workstation for Apple/OSX based on Ace-Step, DeMucs, XTTSv2

🎵 AceStep-cpp UI - 100% local and free Suno alternative powered by acestep-cpp and 0% python

LTX Desktop w/ Apple MPS Local Inference support :tada:

🔊 High-precision web player for multi-device audio playback and spatial audio. P2P Fork w/o Server-side components.,

Magenta JAM AU3 Plugin

Fork of the MRT2 AU3 Plugin

Unstable, Experimental LTX 2.3 GGUF inference in C++ (DO NOT USE IT YET)

ACE-Step Music Gen VST Plugin powered by acestep.cpp

Acestep 1.5 API emulator for AceStep-DAW (dev) 100% powered by acestep-cpp

ComfyUI Node FP8 Metal compute kernels for Apple Silicon MPS — fixing what PyTorch doesn't support yet

Portable C++17 implementation of ACE-Step 1.5 music generation using GGML. Text + lyrics in, stereo 48kHz WAV out.

LTX2 CLI + WS Server compatible with FastVideo API

ComfyUI Node for acestep.cpp

Run Claude Code with local AI on Apple Silicon. 122B model at 41 tok/s with Google TurboQuant. No cloud, no API fees.

Realtime Polez VST3/AU - Audio forensics and sanitization engine. Detects and removes watermarks, metadata, and statistical fingerprints from audio

CTFN Studio is a local Suno-like music generation studio for OSX/MPS powered by HeartMuLa/heartlib with reference audio style transfer

Portable C++17 implementation of mispeech/Dasheng-AudioGen a 2B-parameter flow-matching text-to-audio model using GGML

Pinokio 1-click launcher for acestep.cpp + acestep UI

Github Action running Ace-Step Generations

DAWProject > Logic Pro X converter

Experimental AU2 MCP Tools for Logic Pro X

Experimental AU/VST Plugin to control the SUNO API

Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.

No description.

RVC App for MacOSX MPS

Builders & Actions

WIP ACE-Step LoRA Trainer

Browser-native personal AI assistant. Zero infrastructure, the browser is the server.

A simple, high-quality voice conversion tool focused on ease of use and performance.

singing voice change based on whisper, and lora for singing voice clone

No description.

No description.

seven open source ai music models inside the DAW

No description.

DEMON: Diffusion Engine for Musical Orchestrated Noise

The Infinite Crate is a DAW plugin built on JUCE, React, and the Lyria RealTime live music model

AU Plugin Template for Magenta-Realtime framework

Magenta RealTime 2: An Open-Weights Live Music Model

The most powerful free AI-native digital audio workstation with an agent-centric design, assisting creators to explore and excel in music production.

No description.

Audio forensics and sanitization engine. Detects and removes watermarks, metadata, and statistical fingerprints from audio files.

OpenReel Video - Professional browser-based video editor. Open source CapCut alternative. 100% browser-based, no installation, no cloud uploads, no watermarks.

Bidirectional, stateful control of Logic Pro from AI assistants. 8 dispatcher tools + 7 resources across 5 native macOS channels.

Adaptive Test-time Learning and Autonomous Specialization

fastest runtime for apple silicon.

No description.

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, and Vision fine-tuning — natively on MLX. Unsloth-compatible API.

A 🍴 of a 🔊 Text-Prompted Generative Audio Model

Evolving a Coding agent using Copilot

🎵 The Ultimate Open Source Suno Alternative - Professional UI for ACE-Step 1.5 AI Music Generation. Free, local, unlimited. Stop paying for Suno!

Everything-Reactivity in ComfyUI (audio, MIDI, motion, proximity, and more). Animate and manipulate images, masks, videos, audio, and more. Native ACEStep extensions

A powerful tool that translates ComfyUI workflows into executable Python code.

The ultimate training toolkit for finetuning diffusion models (For Apple Silicon)

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

PyTorch Implementation of TCSinger 2(ACL 2025): Customizable Multilingual Zero-shot Singing Voice Synthesis

Optimized Retrieval-based Voice Conversion WebUI for Apple Silicon Macs (M1/M2/M3). Real-time, high-quality voice conversion with an easy web interface. All models included!

Singing Voice Conversion & Singing Voice Cloning for OSX

Bare-Metal Rust Audio AI Framework

No description.

so-vits-svc fork with realtime support, improved interface and more features.

No description.

TCSinger-App

PyTorch Implementation of TCSinger(EMNLP 2024): Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control

ComfyUI for Audio

A ComfyUI node pack that implements FreeLong (NeurIPS 2024) spectral blending for Wan 2.2 video generation

Candy Dungeon Music Forge (CDMF) is a local-first AI music workstation for Windows. It runs on your PC, uses your GPU, and keeps your prompts and audio on your hardware. CDMF is powered by ACE-Step (text → music diffusion) and includes a custom UI for generating tracks, managing a library, and training LoRAs.

Some music tools in ComfyUI

Advanced sampling nodes optimized for ACE-Step audio generation in ComfyUI.