yue2

An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.

Local AI song generator with an editable score — YuE2 on your GPU: full songs with vocals, sheet music, covers, exact replay. Native Windows app, no Python, installer with auto-update.

YuE2 music generation and an editable piano roll for ComfyUI

Free, open-source local AI music studio: ACE-Step 1.5 and YuE2-3B text-to-music, stem separation, an AI arranger that adds parts to your track, a multitrack DAW, MIDI transcription and LoRA training.

Turn dials. Summon bangers! NOW WITH MORE C++! Local AI music generation powered by GGML

a bunch of open source ai music models inside the DAW

Ruach Studio: The Ultimate YuE2 Studio for local AI music generation. YuE2 Songs Creator, AI Writer, Refiner (30+ nodes, Piano Roll, DAW), Cover Artist, MiniMax H3 Videographer, LoRA Trainer, Librarian. SUNO AI alternative.

A web interface (and more) for YuE2: cover a recording or write a song from a prompt, edit the score, extract the stems, create your own LoRA, import them, export them, share them with fellow yeufonic users. Installs via Docker containers on Linux or Windows. or directly via an installer for Windows and MacOS.

OpenSuno-YuE2: local music generation studio for the YuE2 model on Apple Silicon and Windows/NVIDIA, with automatic model downloads.

AI music prompt nodes for ComfyUI — 73 style presets plus song analysis for MiniMax Music 3 and YuE2. Runs on CPU.

Generate songs from a musical style and lyrics in ComfyUI using YuE2. Optional score viewing and editing, separate generation stages, and stereo 48 kHz audio output. Experimental.

YUE2 // GROOVE — an unofficial web UI for YuE2 song generation (Apple Silicon first; Linux/CUDA via YuE2)

macOS app + installer to run YuE2-3B music generation, covers and transcription locally on Apple Silicon (MLX), with fixes for 24 GB Macs

Kwesi — a local-first desktop app for generating and training music with open-source AI models. No cloud, no accounts. Bundles MusicGen, MuseCoco, ACE-Step 1.5, RAVE, Museformer, and YuE2 behind one dynamic UI. Electron + React + Python sidecar servers.

Free, open-source AI music studio on your Android phone: full songs with vocals, Write with AI, stem splitting, mixer, recording and drum pads. No cloud, no subscription.

YUE2 // GROOVE is the latest music studio on open-source Yue2. Generate high-quality songs from style & lyrics (editable score), cover with SheetSage2/MERT2, refine edits, and manage a reusable library — with real creative control.

A web interface (and more) for YuE2: cover a recording or write a song from a prompt, edit the score, extract the stems, create your own LoRA, import them, export them, share them with fellow YUE2gen-studio users. Installs via Docker containers on Linux or Windows. or directly via a Windows installer.

伶风 Lingfeng — Windows songwriting and jianpu editor with dual melodies, ABC and MusicXML exchange, and YuE2-ready ABC export.

16 native YuE2 music concept sliders with routed particles, ComfyUI support, and a Hugging Face demo.

Re-sing a song in your singer's voice with YuE2: the song's own lead sheet, section-tagged lyrics and a tempo-matched voice prefix, over a newly generated arrangement.