iArt.ai
AI motion graphics software — the After Effects alternative anyone can use. Create animations and explainer videos from a text prompt in minutes.
Karaoke versions of the songs that don't have one. Free and open source.
MediaRust · TypeScriptGitHub @whithrOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
A karaoke machine for any song you have: AI vocal removal, word-timed lyrics, a full-screen player and party mode. Free, open source, runs on your computer.
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
karaoke for the songs nobody made a karaoke version of.
drop in a song you have. baritoad turns the singer down, times the lyrics word
by word, and puts them on your tv. friends pick songs from their phones. free,
open source, and it all runs on your computer.
windows 10 or 11, 64-bit ·
mac with apple silicon (m1 or newer), macos 13.4 or later ·
linux laterRead the full README ↗karaoke for the songs nobody made a karaoke version of.
drop in a song you have. baritoad turns the singer down, times the lyrics word by word, and puts them on your tv. friends pick songs from their phones. free, open source, and it all runs on your computer.
windows 10 or 11, 64-bit · mac with apple silicon (m1 or newer), macos 13.4 or later · linux later
the installers aren't signed yet. windows may warn you: more info → run anyway. on a mac, open baritoad once, then system settings → privacy & security → open anyway. the first start downloads about 2 GB of models. they run locally, on your computer.
it's not studio karaoke. sometimes you'll still hear a little of the original singer.
taking the vocals out is the slow part. a graphics card makes it a lot faster, but the cpu works too. one 3:15 song, start to finish:
| time | |
|---|---|
| gpu (rtx 2080 super) | 17 s |
| cpu only (i7-9700k) | 1 min 54 s |
that's with pasted lyrics. a song without lyrics takes longer, because baritoad transcribes it first. the gpu path uses directml, so it isn't tied to one brand of card, but we've only tried nvidia. if your card doesn't pass baritoad's quick check, it uses the cpu instead.
on a mac it uses the cpu for now. a 3:37 song with its lyrics found online took 2 min 39 s on an m1 pro.
no account, no telemetry, nothing uploaded. it only goes online for the models, lyrics lookups and links you ask for, and party mode (what the relay sees).
cd apps/desktop
pnpm install
pnpm fetch-tools
pnpm tauri dev
more in apps/desktop/README.md · contributing
GPL-3.0-or-later. model and dependency licenses are in MODEL_LICENSES.md and docs/DEPENDENCIES.md. the demucs separation weights are, per their author, for research use.
Additional permission under GNU GPL version 3 section 7: if you modify this program, or any covered work, by linking or combining it with Microsoft DirectML or NVIDIA CUDA, cuDNN or TensorRT (or a modified version of those libraries), containing parts covered by the terms of those libraries' licenses, the licensors of this program grant you additional permission to convey the resulting work.