Skip to content
RepoQuarry

yovoice leemysw/yovoice

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.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

yovoice at a glance

Checked 15 Oct 2026

yovoice is a desktop app (first released September 2026) built on the audio.cpp engine, so it needs no Python. Its music mode makes full songs or instrumentals from a style and lyrics with ACE-Step 1.5, keeping each take as a version; it also does speech, voice cloning and a MIDI score editor. Songs need 12 GB+ VRAM or 16 GB+ Apple Silicon. Code is Apache-2.0; ACE-Step weights are MIT but some bundled speech models are non-commercial. No covers, section edits or Linux build. Lyrics help can use paid AI APIs or a local Ollama model.

Cite this pageRepoQuarry. “yovoice.” Checked 15 Oct 2026. https://repoquarry.dev/projects/yovoice

How much of Suno does it replace?

2 of 5 jobs. Songs and instrumentals from style and lyrics; no covers, section edits or stems from the model.

Partial: Full songs with vocals from a prompt or lyrics Partial replacement
Partial: Instrumental tracks (Instrumental mode) Partial replacement
No: Covers and restyles of an uploaded song (Cover) Not covered
No: Extending or regenerating part of a song (Extend Not covered
No: Splitting a song into vocal and instrument stems (Get Stems) Not covered

For 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), see other Suno alternatives. You may also need to build an interface, an API server and hosting yourself.

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction
QuestionAnswerSourceChecked
Runs on my machine? Confirmed: Yes, desktop app on your own GPU or CPU Runs entirely on your local GPU/CPU. github.com · yovoice#why-yovoice ↗ 1d ago
Code licence Confirmed: Apache-2.0 github.com · LICENSE ↗ 1d ago
Model weights licence Partial: ACE-Step 1.5 (music) is MIT; some bundled speech models (OmniVoice, Breeze TTS 2) are non-commercial OmniVoice (CC-BY-NC) and Breeze TTS 2 (BreezeBlue Research and Non-Commercial License) weights are restricted to non-commercial use. github.com · yovoice#supported-models ↗ 1d ago
Commercial use Partial: Yes for music with ACE-Step 1.5 (MIT); not with the non-commercial speech models weights are restricted to non-commercial use. github.com · yovoice#supported-models ↗ 1d ago
Paid services needed? Partial: None required; an optional AI service (paid APIs or local Ollama) can write lyrics and arrangements connect DeepSeek, Qwen, Kimi, OpenAI, Anthropic, Ollama or any compatible API github.com · yovoice#features ↗ 1d ago
Hardware Confirmed: Songs need 12 GB+ VRAM or 16 GB+ Apple Silicon; ACE-Step 1.5 Turbo is 10 GB (BF16) 12 GB+ VRAM / 16 GB+ Apple Silicon github.com · yovoice#hardware--vram-quick-guide ↗ 1d ago
Operating systems Partial: macOS 14+ (Apple Silicon) and Windows 10/11 x64; no Linux yovoice is an open-source, local-first audio and music creation studio for macOS and Windows. github.com · yovoice#installation ↗ 1d ago
Setup effort Confirmed: Easy; .dmg or Windows installer (CUDA runtimes bundled), models downloaded in the app Models are downloaded inside the app github.com · yovoice#installation ↗ 1d ago

Get the weekly top 5 and what’s new, every Monday

We’ll email you once a week. Unsubscribe any time. We never share your email.

Cookie preferences

Choose what we may store in your browser. You can change this any time from Cookie settings in the footer.

Essential

Security, and remembering this choice. rq-consent · 12 months

Always on