# Open-source alternatives for AI music

> Open models and apps that generate songs, vocals and instrumentals, instead of paying for an AI music subscription.

## Paid products
- [Open-source alternatives to Suno](https://repoquarry.dev/alternatives/suno.md): Hosted AI music service that turns a text prompt or your own lyrics into full songs with vocals, with instrumental mode, covers of uploaded audio, extending and replacing song sections, and stem downloads. Runs only in the cloud on credits. Pricing: See pricing page.

## Top ranked projects
1. [ComfyUI](https://repoquarry.dev/projects/comfyui.md): Node-graph app for running open image, video, 3D and audio models locally, with inpainting, outpainting, upscaling and a local API. Commercial use: Partial.
2. [Ultimate Vocal Remover](https://repoquarry.dev/projects/ultimate-vocal-remover.md): Desktop app that splits songs into vocals and instrumental or other stems using MDX-Net, VR, Demucs and MDX23C models. Commercial use: Confirmed.
3. [ACE-Step 1.5](https://repoquarry.dev/projects/ace-step-1-5.md): Open-weight music model that writes and renders full songs with vocals locally, with covers, repainting, stem extraction and LoRA training. Commercial use: Confirmed.
4. [YuE2](https://repoquarry.dev/projects/yue.md): Open song model that writes an editable melody-and-chord score from lyrics and style, then sings it as a full song with accompaniment. Commercial use: Partial.
5. [yovoice](https://repoquarry.dev/projects/yovoice.md): Local desktop audio studio for macOS and Windows that makes songs and instrumentals with ACE-Step 1.5, alongside text-to-speech and voice cloning. Commercial use: Partial.
6. [Magenta RealTime 2](https://repoquarry.dev/projects/magenta-realtime.md): Google's open-weights live music model that streams instrumental music in real time from text prompts on Apple Silicon Macs. Commercial use: Confirmed.
7. [YuE2 Studio](https://repoquarry.dev/projects/yue2-studio.md): Windows desktop app for YuE2 that writes an editable score and sings it as a full song offline from 6 GB of VRAM, with covers and stems. Commercial use: Partial.
8. [acestep.cpp](https://repoquarry.dev/projects/acestep-cpp.md): C++/GGML port of ACE-Step 1.5 with a local web UI and API; runs quantised song models on CPU, CUDA, Metal or Vulkan without Python. Commercial use: Confirmed.
9. [ACE-Step Studio](https://repoquarry.dev/projects/ace-step-studio.md): Windows desktop studio for ACE-Step 1.5 that makes full songs with vocals offline, with covers, repaints, stems, LoRA training and karaoke. Commercial use: Confirmed.
10. [Stable Audio Open (stable-audio-tools)](https://repoquarry.dev/projects/stable-audio-tools.md): Stability AI's training and inference code for Stable Audio Open, which makes short instrumental music and sound clips from text. Commercial use: Partial.
11. [HeartMuLa](https://repoquarry.dev/projects/heartmula.md): Apache-2.0 music language model (3B) that generates songs with vocals from lyrics and style tags, plus a codec and lyrics transcriber. Commercial use: Confirmed.
12. [HOT-Step CPP](https://repoquarry.dev/projects/hot-step-cpp.md): Portable local music studio running ACE-Step 1.5, MiniMax-Music3 and YuE2 in one C++ engine, with covers, repaint, stems and adapter training. Commercial use: Partial.
13. [Audio Separator](https://repoquarry.dev/projects/python-audio-separator.md): Command-line tool and Python package that splits audio into vocals, instrumental and other stems using UVR, Demucs and RoFormer models. Commercial use: Unknown.
14. [AudioCraft (MusicGen)](https://repoquarry.dev/projects/audiocraft.md): Meta's research library for MusicGen, a text-to-music model for short instrumental clips, optionally guided by a hummed or played melody. Commercial use: No.
15. [ACE-Step UI](https://repoquarry.dev/projects/ace-step-ui.md): Suno-style web interface for a local ACE-Step 1.5 install, with a song library, covers, repaint, stem extraction and an audio editor. Commercial use: Unknown.
---
Source: RepoQuarry (https://repoquarry.dev/categories/ai-music). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.