Core AI is Apple's on-device ML runtime in iOS 27 / macOS 27 and the successor to Core ML: PyTorch models are exported with Apple's coreai-torch (LLMs: coreai.llm.export) into .aimodel bundles that run on the GPU or the Neural Engine, e.g. Qwen3-8B 4-bit decodes at 94 tok/s on an M4 Max GPU, MLX 90 under the same protocol (apple-silicon-llm-bench, macOS 27 beta, 2026-06).

Stable Audio Open Small — Core AI (on-device music generation)

The model zoo's first MUSIC / AUDIO generation model for Apple Core AI. Type a prompt, get ~11s of 44.1 kHz stereo audio — generated entirely on-device on Apple Silicon. A community port of stabilityai/stable-audio-open-small (Stability AI + Arm) to Core AI.

A latent diffusion text-to-audio model: a T5 text encoder conditions a DiT (diffusion transformer) that denoises a latent over 8 rectified-flow steps, then an Oobleck VAE decodes the latent to a waveform. Distilled (ARC) for few-step generation, so it's fast.

Stable Audio Open Small on iPhone 17 Pro — the zoo's coreai-audio app, 12 s of audio in ~1 s.

Use it

⚡ One line — this model is the default behind the kit's task op (import CoreAIOps; no session, no model plumbing, downloads on first use):

let audio = try await CoreAI.compose(prompt)

Every op, one shape — Cookbook.

▶️ Run it (source) — the Music runner (GUI + CLI, one app for every text-to-music model in the catalog):

git clone https://github.com/john-rocky/coreai-kit
open coreai-kit/Examples/Music/Music.xcodeproj
# → Run, then pick "Stable Audio Open Small" in the model picker

# agents / headless (macOS):
cd coreai-kit/Examples/Music
swift run music-cli --model stable-audio-open-small --prompt "128 BPM tech house drum loop" --output loop.wav

💻 Build with it — complete; the glue is kit API, copy-paste runs:

import CoreAIKit

let musician = try await KitMusician(catalog: "stable-audio-open-small")
let audio = try await musician.generate(prompt)
// audio.samples: 44.1 kHz stereo (planar L/R) — play it or write a WAV

The take-home is Examples/Music/Sources/QuickStart.swift — this exact code as one typed function, no UI; the CLI is an argument shell over it, and the GUI drives the same KitMusician(catalog:) and plays the result. Length? generate(_:seconds:) up to the model's ~11 s window. The WAV container is your app's territory (the runner ships a 30-line writer with planar-stereo support).

Integration checklist

• SPM: https://github.com/john-rocky/coreai-kit → product CoreAIKit
• Info.plist: none needed
• Entitlements: none needed (macOS)
• First run downloads the model — 1.1 GB (Mac) — then it loads from the local cache (Application Support; progress via the downloadProgress callback)
• Measure in Release — Debug is ~3× slower on per-token host work

What's in the bundle (macos/)

Three Core AI .aimodel bundles + a tiny host sampler loop:

Host loop (StableAudioRunner): tokenize (T5, t5_tokenizer/) → conditioner → start from Gaussian noise → 8-step rectified-flow euler x = x + (t_next − t)·v over the fixed schedule [1.0, .9944, .9845, .9579, .8909, .7455, .5125, .2739] → 0 → VAE decode → 44.1 kHz stereo wav. No KV cache, no CFG (cfg_scale 1.0 — the model is ARC-distilled).

Performance (M4 Max, GPU)

Numerics: each bundle engine-gated vs the reference at cos ≥ 0.9999; full pipeline reproduces the reference audio exactly.

Roadmap

• iPhone (h18p) build — bundles AOT-compile; device RTF pending
• int8 (further size cut)
• a music-generation tab in the zoo app

Credits & license

A community Core AI conversion — all credit to Stability AI (and Arm) for Stable Audio Open Small; T5 text encoder by Google. This bundle is governed by the Stability AI Community License (free for non-commercial use and for commercial use under $1M annual revenue; review the license before use). No retraining — conversion only.

Part of the Core AI model zoo.

---

More models in this format: Core AI Model Zoo — 75 models, each with the recipe that produced it.

Want a different model on-device? Open a request — free, open weights only; the export and its measured numbers get published publicly.