Upstar existe aussi en français.

Voir cette page en français
TI

timoncool/ACE-Step-Studio

Portable AI music generator — full songs with vocals, covers, music videos. One-click install, 100% offline, NVIDIA GPU.

TypeScriptMIT license Last commit 18 hours ago timoncool.github.io/ACE-Step-Studio(opens in new tab)

Updated 24 min ago

Growth

Last 24 hours
+1
stars
Last 7 days
+25
stars
Last 30 days
+92
stars
Total stars
429
Forks
61

Top 3 in Machine learning this week

  1. 1 kanaworksai-hue/audio-studio-mcp +405 stars this week
  2. 2 Tencent-Hunyuan/Prism +294 stars this week
  3. 3 rohitg00/ai-engineering-from-scratch +2.9k stars this week

This repo: #52 of 129 this week, #93 of 328 this month.

Also this week: #109 in Local LLMs, #284 in Windows, #724 in TypeScript

See all 129 Machine learning repos

Star history

250300350400450Aug 5Aug 19Sep 2Sep 16Sep 30Oct 14

Total stars at the end of each week, from GitHub’s daily star counts.

+25 stars this week, against ~10 in a usual week

Health signals

HealthyChecked Oct 21, 2026
Commit activity
Commits in 13 of the last 13 weeks 419 commits on the default branch in 90 days
Maintainers
1 commit author in 90 days Top author: 100% of the last 68 commits
Issue responsiveness
Median first response: 6 hours 21 of 21 issues opened in 90 days are closed
Pull requests
20 merged, 0 closed, 0 open Of 20 pull requests opened in 90 days
Releases
Last release: today 15 releases in the last 12 months
Project hygiene
License, CI and security policy
OpenSSF Scorecard
Not scanned Unknown, not counted against the project

Signals are computed automatically from public GitHub data. They are not an endorsement or a security audit. How health is computed

README

README.md

ACE-Step Studio

Suno at home: full songs with vocals from ACE-Step 1.5 on your own GPU. One executable — no Python, no Node.js, no launcher.

English · Русский · 中文 · 日本語 · 한국어

ACE-Step Studio is a desktop studio for ACE-Step 1.5, the open music model that writes and sings full songs. Describe a sound and write lyrics — or give it a one-line idea — and it plans the song with its language model and renders it with vocals on your own graphics card. Covers, remixes, repaints, a LoRA catalogue, your own LoRA trained on your songs, stems, MIDI, karaoke and video clips, all in one window. Windows…

Read the full README on GitHub(opens in new tab)