🧄 aioli
Your at-home AI studio: clone voices, compose songs, draw images,
generate video and produce podcasts. All on your machine. No cloud.
🎙️ Voice • 🎵 Music • 🖼️ Image • 🎬 Video • 🎧 Master • 📻 Podcast
What it does (with real examples)
| Plugin | Produces | Example |
|---|---|---|
🎙️ voice |
Cloned or synthetic voice as WAV (native Spanish with chatterbox, free CPU drafts with piper) | aioli voice generate "Hola mundo" --profile vega --engine chatterbox -o hola.wav |
🎵 music |
Full song (vocals + instruments) from a style and your lyrics — it sings in Spanish | aioli music generate --preset reggae-consciente --backend yue2 -l my-lyrics.txt -o track.mp3 |
🖼️ image |
Image from text, editing, inpainting or character reference (~9 s with FLUX-klein-4b) | aioli image generate "a robot garlic" -m z_image_turbo |
🎬 video |
MP4 clip with synced audio from text or image | aioli video generate "a robot garlic dancing" --frames 81 -o ajo.mp4 |
🎧 master |
Audio finishing with ffmpeg: mix, ducking, denoise, -16 LUFS |
aioli master loudnorm mix.wav -o final.wav |
📻 podcast |
MP3 episode + show notes from a script (voices + music bed + pauses) | aioli podcast episode script.md -o ./ep1 |
19 songs, their cover art and several clips were made this way, locally, with these commands. No accounts, no subscription.
How it works
aioli setupinspects your machine and tells you what fits your GPU.aioli models downloadfetches verified weights (sha256, resumable) into~/.local/share/aioli(or whereverAIOLI_MODELS_DIRpoints).- You generate locally: not a byte leaves your machine. No accounts, no subscription. Only licensed weights (Flux, LTX) ask for a free HuggingFace account to accept their license once.
Install
curl -fsSL https://aioli.es/install.sh | sh # installs uv+ffmpeg if missing → doctor → setup → status
# …or truly by hand (needs `uv`, Python ≥3.12 and `ffmpeg`):
uv tool install aioli-cli # extras: aioli-cli[voice-piper,music-storage]
aioli setup # tells you what fits your GPU, downloads weights
aioli doctor # preflight: CUDA, ffmpeg, models, VRAM
For top-tier image and video (Flux, LTX), accept their license on
huggingface.co and export HF_TOKEN (read-only token) before setup.
🔒 Paranoid (good): the installer lives in the repo's
install.sh. It only uses the network forastral.sh(uv), GitHub and HuggingFace. The only elevated step is installingffmpegif missing — it asks first (or skips with--no-ffmpeg). Re-running is safe: it upgrades in place and preserves your extras and--withengines.
Requirements
| What | Minimum | Recommended |
|---|---|---|
| OS | Ubuntu 22.04+ | Ubuntu 24.04 |
| GPU | none (CPU voice with piper) | NVIDIA 12–16 GB VRAM |
| Disk | 15 GB (one plugin) | 100 GB (full set ≈ 60 GB) |
| Account | — | free HuggingFace (for Flux and LTX, licensed) |
aioli setup detects your machine (tier patata/modesta/capaz/bicha —
yes, potato to beast) and only downloads what fits. Weights are sha256
verified and resume if your connection drops.
Usage
# image: text → PNG (editing, inpainting and reference available)
aioli image generate "a lighthouse in the fog" -m z_image_turbo
# music: style + your lyrics → full song
aioli music generate "cheerful rumba" --backend yue2
aioli music generate --preset reggae-consciente -l my-lyrics.txt -o track.mp3
# voice: create profile, add a sample with its transcript, generate
aioli voice profiles create vega --language es
aioli voice profiles add-sample vega ref.wav -t "exact audio transcript"
aioli voice generate "Hola mundo" --profile vega --engine chatterbox -o hola.wav
# video: text or image → clip with audio
aioli video generate "a robot garlic dancing" --frames 81 -o ajo.mp4
# podcast: script with [VOICES], [MUSIC:] and [PAUSE:] → episode + notes
aioli podcast episode script.md -o ./ep1
# master: finish any audio (mix, ducking, -16 LUFS…)
aioli master loudnorm mix.wav -o final.wav
aioli <plugin> --help details every command; aioli doctor diagnoses
failures. Note: the CLI itself speaks Spanish — the models don't mind.
License
MIT. Third-party weights carry their own license (some non-commercial or
requiring acceptance on HuggingFace); aioli models warns you.
1 maintainer
Release files for aioli-cli 0.1.39
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| aioli_cli-0.1.39.tar.gz | 229.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| aioli_cli-0.1.39-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 515.7 kB
Release files / aioli_cli-0.1.39.tar.gz
| Download URL | aioli_cli-0.1.39.tar.gz |
|---|---|
| Size | 229.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
627e2d0c7164560775c880d1bc75f5195dfd7eb0b84223bc7c602cdb1829e8e3
|
|
BLAKE2b-256 checksum How to use checksums |
03b48e7795b80ef380875c0e3fb7833a6fdb3b285a2e4a53291d2345c0217916
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 21, 2026.
Transparency logRelease files / aioli_cli-0.1.39-py3-none-any.whl
| Download URL | aioli_cli-0.1.39-py3-none-any.whl |
|---|---|
| Size | 285.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c9b0d5e55627fd34cede85e78ad163ae0576fb5e2124cb40d9e64357a8b2648f
|
|
BLAKE2b-256 checksum How to use checksums |
169229880e044dc38a27f187512fdcab23b6387214468c1a3134486e6eb1c180
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 21, 2026.
Transparency log
