ace-step/ACE-Step-1.5 BEST FIT ★ 14k active 5d ago
Open-weight music model that writes and renders full songs with vocals locally, with covers, repainting, stem extraction and LoRA training.
Replaces Full songs with vocals from a prompt or lyrics + Instrumental tracks (Instrumental mode) + Covers and restyles of an uploaded song (Cover) + Extending or regenerating part of a song (Extend + Splitting a song into vocal and instrument stems (Get Stems) (partly)
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · MIT
- Paid services
- Confirmed: None required
- Hardware
- Confirmed: GPU, ~4GB+
- Setup
- Confirmed: Easy
timoncool/ACE-Step-Studio BEST FIT ★ 412 active today
Windows desktop studio for ACE-Step 1.5 that makes full songs with vocals offline, with covers, repaints, stems, LoRA training and karaoke.
Replaces Full songs with vocals from a prompt or lyrics + Instrumental tracks (Instrumental mode) + Covers and restyles of an uploaded song (Cover) + Extending or regenerating part of a song (Extend + Splitting a song into vocal and instrument stems (Get Stems) (partly)
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · MIT
- Paid services
- Partial: Optional only
- Hardware
- Confirmed: GPU, ~4GB+
- Setup
- Confirmed: Easy
fspecii/ace-step-ui BEST FIT ★ 5.1k active 3mo ago
Suno-style web interface for a local ACE-Step 1.5 install, with a song library, covers, repaint, stem extraction and an audio editor.
Replaces Full songs with vocals from a prompt or lyrics + Instrumental tracks (Instrumental mode) + Covers and restyles of an uploaded song (Cover) + Extending or regenerating part of a song (Extend + Splitting a song into vocal and instrument stems (Get Stems) (partly)
- Runs locally
- Confirmed: Yes
- Commercial use
- Unknown: Unknown
- Paid services
- Confirmed: None required
- Hardware
- Confirmed: GPU, ~4GB+
- Setup
- Confirmed: Medium
ServeurpersoCom/acestep.cpp BEST FIT ★ 437 active 2d ago
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.
Replaces Full songs with vocals from a prompt or lyrics + Covers and restyles of an uploaded song (Cover) + Extending or regenerating part of a song (Extend (partly) Not: instrumental tracks (Instrumental mode), splitting a song into vocal and instrument stems (Get Stems)
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · MIT
- Paid services
- Confirmed: None required
- Hardware
- Partial: CPU works
- Setup
- Confirmed: Hard
facebookresearch/audiocraft BEST FIT ★ 24k active 7mo ago
Meta's research library for MusicGen, a text-to-music model for short instrumental clips, optionally guided by a hummed or played melody.
Replaces Instrumental tracks (Instrumental mode) (partly) Not: full songs with vocals from a prompt or lyrics, covers and restyles of an uploaded song (Cover), extending or regenerating part of a song (Extend, splitting a song into vocal and instrument stems (Get Stems)
- Runs locally
- Confirmed: Yes
- Commercial use
- No: No · MIT code, CC-BY-NC-4.0 weights
- Paid services
- Confirmed: None required
- Hardware
- Confirmed: GPU needed
- Setup
- Confirmed: Medium
Comfy-Org/ComfyUI BEST FIT #1 TRENDING ★ 138k active today
Node-graph app for running open image, video, 3D and audio models locally, with inpainting, outpainting, upscaling and a local API.
Replaces Full songs with vocals from a prompt or lyrics (partly) Not: instrumental tracks (Instrumental mode), covers and restyles of an uploaded song (Cover), extending or regenerating part of a song (Extend, splitting a song into vocal and instrument stems (Get Stems)
- Runs locally
- Confirmed: Yes
- Commercial use
- Partial: Conditions · GPL-3.0
- Paid services
- Partial: Optional only
- Hardware
- Confirmed: GPU, ~4GB+
- Setup
- Confirmed: Easy
ASLP-lab/DiffRhythm BEST FIT ★ 2.3k active 10mo ago
Diffusion model that generates full-length songs (up to 4m45s) from timed lyrics and a text or audio style reference.
Replaces Full songs with vocals from a prompt or lyrics + Instrumental tracks (Instrumental mode) + Extending or regenerating part of a song (Extend (partly) Not: covers and restyles of an uploaded song (Cover), splitting a song into vocal and instrument stems (Get Stems)
- Runs locally
- Confirmed: Yes
- Commercial use
- Partial: Conditions · Apache-2.0
- Paid services
- Confirmed: None required
- Hardware
- Confirmed: GPU, ~8GB+
- Setup
- Confirmed: Medium
HeartMuLa/heartlib BEST FIT ★ 3.8k active 8d ago
Apache-2.0 music language model (3B) that generates songs with vocals from lyrics and style tags, plus a codec and lyrics transcriber.
Replaces Full songs with vocals from a prompt or lyrics (partly) Not: instrumental tracks (Instrumental mode), covers and restyles of an uploaded song (Cover), extending or regenerating part of a song (Extend, splitting a song into vocal and instrument stems (Get Stems)
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · Apache-2.0
- Paid services
- Confirmed: None required
- Hardware
- Unknown: Unknown
- Setup
- Confirmed: Medium
scragnog/HOT-Step-CPP BEST FIT ★ 175 active today
Portable local music studio running ACE-Step 1.5, MiniMax-Music3 and YuE2 in one C++ engine, with covers, repaint, stems and adapter training.
Replaces Full songs with vocals from a prompt or lyrics + Covers and restyles of an uploaded song (Cover) + Extending or regenerating part of a song (Extend + Splitting a song into vocal and instrument stems (Get Stems) (partly) Not: instrumental tracks (Instrumental mode)
- Runs locally
- Confirmed: Yes
- Commercial use
- Partial: Conditions · MIT
- Paid services
- Partial: Optional only
- Hardware
- Confirmed: CPU works
- Setup
- Confirmed: Easy
magenta/magenta-realtime BEST FIT ★ 1.8k active 2w ago
Google's open-weights live music model that streams instrumental music in real time from text prompts on Apple Silicon Macs.
Replaces Instrumental tracks (Instrumental mode) (partly) Not: full songs with vocals from a prompt or lyrics, covers and restyles of an uploaded song (Cover), extending or regenerating part of a song (Extend, splitting a song into vocal and instrument stems (Get Stems)
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · Apache-2.0 code, CC-BY-4.0 weights
- Paid services
- Confirmed: None required
- Hardware
- Confirmed: GPU needed
- Setup
- Confirmed: Easy
nomadkaraoke/python-audio-separator BEST FIT ★ 1.4k active 2w ago
Command-line tool and Python package that splits audio into vocals, instrumental and other stems using UVR, Demucs and RoFormer models.
Replaces Splitting a song into vocal and instrument stems (Get Stems) Not: full songs with vocals from a prompt or lyrics, instrumental tracks (Instrumental mode), covers and restyles of an uploaded song (Cover), extending or regenerating part of a song (Extend
- Runs locally
- Confirmed: Yes
- Commercial use
- Unknown: Unknown
- Paid services
- Confirmed: None required
- Hardware
- Confirmed: CPU works
- Setup
- Confirmed: Easy
Stability-AI/stable-audio-tools BEST FIT ★ 3.9k active 6d ago
Stability AI's training and inference code for Stable Audio Open, which makes short instrumental music and sound clips from text.
Replaces Instrumental tracks (Instrumental mode) (partly) Not: full songs with vocals from a prompt or lyrics, covers and restyles of an uploaded song (Cover), extending or regenerating part of a song (Extend, splitting a song into vocal and instrument stems (Get Stems)
- Runs locally
- Confirmed: Yes
- Commercial use
- Partial: Conditions · MIT
- Paid services
- Confirmed: None required
- Hardware
- Unknown: Unknown
- Setup
- Confirmed: Medium
Anjok07/ultimatevocalremovergui BEST FIT ★ 27k active 9d ago
Desktop app that splits songs into vocals and instrumental or other stems using MDX-Net, VR, Demucs and MDX23C models.
Replaces Splitting a song into vocal and instrument stems (Get Stems) Not: full songs with vocals from a prompt or lyrics, instrumental tracks (Instrumental mode), covers and restyles of an uploaded song (Cover), extending or regenerating part of a song (Extend
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · MIT
- Paid services
- Confirmed: None required
- Hardware
- Confirmed: GPU, ~6GB+
- Setup
- Confirmed: Easy
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.
Replaces Full songs with vocals from a prompt or lyrics + Instrumental tracks (Instrumental mode) (partly) Not: covers and restyles of an uploaded song (Cover), extending or regenerating part of a song (Extend, splitting a song into vocal and instrument stems (Get Stems)
- Runs locally
- Confirmed: Yes
- Commercial use
- Partial: Conditions · Apache-2.0
- Paid services
- Partial: Optional only
- Hardware
- Confirmed: GPU, ~12GB+
- Setup
- Confirmed: Easy
multimodal-art-projection/YuE BEST FIT ★ 12k active 10d ago
Open song model that writes an editable melody-and-chord score from lyrics and style, then sings it as a full song with accompaniment.
Replaces Full songs with vocals from a prompt or lyrics + Instrumental tracks (Instrumental mode) + Covers and restyles of an uploaded song (Cover) (partly) Not: extending or regenerating part of a song (Extend, splitting a song into vocal and instrument stems (Get Stems)
- Runs locally
- Confirmed: Yes
- Commercial use
- Partial: Conditions · Apache-2.0 code, CC-BY-NC-4.0 weights
- Paid services
- Confirmed: None required
- Hardware
- Confirmed: GPU, ~24GB+
- Setup
- Confirmed: Medium
timoncool/YuE2-Studio BEST FIT ★ 731 active today
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.
Replaces Full songs with vocals from a prompt or lyrics + Covers and restyles of an uploaded song (Cover) + Splitting a song into vocal and instrument stems (Get Stems) (partly) Not: instrumental tracks (Instrumental mode), extending or regenerating part of a song (Extend
- Runs locally
- Confirmed: Yes
- Commercial use
- Partial: Conditions · MIT code, CC-BY-NC-4.0 weights
- Paid services
- Partial: Optional only
- Hardware
- Confirmed: GPU, ~6GB+
- Setup
- Confirmed: Easy
No project meets all of your requirements. The list below shows what you'd need to relax.