timoncool/YuE2-Studio

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.

What it solves

YuE2 Studio provides a complete, offline desktop environment for generating full-length songs using the YuE2 open-source music model. It solves the complexity of running advanced generative music models by offering a single, self-contained Windows executable that handles everything from score generation and vocal performance to audio processing and MIDI editing without requiring Python or complex manual setups.

How it works

It acts as a graphical interface for yue2.cpp, a native C++/CUDA implementation of the YuE2 model. The studio allows users to input lyrics and style descriptions to generate a musical score (in ABC notation), which the model then performs. Users can edit the generated score directly, re-render performances with different settings, or use the built-in MIDI editor to refine compositions. The application also includes an MCP (Model Context Protocol) server, allowing AI agents to control the studio's functions programmatically.

Who it’s for

This tool is designed for music creators, AI enthusiasts, and developers who want to run high-quality generative music models locally on Windows. It is particularly useful for those who want granular control over the composition process—such as editing notes or chords—rather than just generating audio from a single prompt.

Highlights

  • Full-stack music creation: Generates songs from lyrics and style, with the ability to edit the underlying score and re-render performances.
  • Native performance: Runs offline on NVIDIA GPUs (6GB+ VRAM) with experimental support for AMD/Intel via Vulkan.
  • Extensive editing tools: Includes a multi-track MIDI editor, audio stem separation (via HT-Demucs), and audio processing chains (VST3 support, mastering).
  • Agent-ready: Features an integrated MCP server, enabling AI agents to manage song creation, training, and file operations.
  • Advanced training: Includes a built-in LoRA trainer to fine-tune the model on specific artist styles or datasets.
  • User-friendly interface: Offers a portable Windows experience with features like a Winamp-style skin mode, visualizers, and automatic updates.

Related

  • Project
    timoncool/ACE-Step-Studio

    A desktop studio for ACE-Step 1.5 that enables local generation of full songs with vocals, featuring integrated LoRA training, stem separation, and MIDI tools.

  • Project
    multimodal-art-projection/YuE

    YuE2 is an open‑source music‑generation system that turns lyrics + style prompts into an editable symbolic score and then into high‑fidelity audio. It offers three modes (full plan, melody‑only, direct), supports zero‑shot covers via SheetSage2 transcription, and achieves state‑of‑the‑art benchmark scores. The Python pipeline, agent skill, and web demo make it easy to create, edit, or cover songs, all under an Apache 2.0 code license and CC‑BY‑NC model license.

  • Project
    debpalash/VoiceStudio

    VoiceStudio is an open‑source desktop app (Electron) for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation in hundreds of languages. It runs locally on macOS, Windows or Linux, supports GPU acceleration, offers a model manager, and exposes a local API/MCP for integration with AI agents.

  • Project
    AkshitIreddy/AI-Powered-Video-Tutorial-Generator

    AI‑Powered Video Tutorial Generator is a Windows‑only desktop app that turns a question or topic into a fully editable video lesson. It handles research, script writing, storyboard creation, narration, illustration, presenter animation and final export, using either local diffusion models (ComfyUI/SDXL) or cloud LLM/image providers. The open‑source stack combines a React/Tauri UI, a Rust core, and a Python pipeline, and it ships with bundled runtimes (Python, Node, Chromium, FFmpeg).

  • Project
    ace-step/ACE-Step-1.5

    ACE‑Step 1.5 is an open‑source music‑generation foundation model that combines a language‑model planner with a Diffusion‑Transformer audio decoder. It can create full songs (10 s‑10 min) in under 10 seconds on a RTX 3090, runs with <4 GB VRAM for base models, and supports LoRA fine‑tuning from a handful of tracks. The repo provides Gradio and REST interfaces, launch scripts for all major OSes, multiple model sizes (including a 4 B XL version), and extensive control over lyrics, style, tempo, and instrumentation.