diff --git a/playbooks/deploy-ace-step.yaml b/playbooks/deploy-ace-step.yaml
new file mode 100644
index 0000000..d6dd410
--- /dev/null
+++ b/playbooks/deploy-ace-step.yaml
@@ -0,0 +1,83 @@
+# Deploy ACE-Step 1.5 (Apache 2.0 music generation foundation model)
+# to irv-ml1.
+#
+# Builds the image locally from ace-step/ACE-Step via docker buildx
+# git URL context. ~10-15 min cold build (CUDA 12.6 runtime + torch +
+# transformers + spacy + audio deps). First /generate triggers the
+# model download (~5-10 GB) into the bind-mounted HF cache + warmup.
+#
+# Pre-req (user runs once):
+#   ssh -t irv-ml1 'sudo mkdir -p /worktank/ace-step/{checkpoints,outputs,logs,hf_cache} \
+#       /opt/docker/compose/ace-step && \
+#       sudo chown -R lkraven:lkraven /worktank/ace-step /opt/docker/compose/ace-step'
+#
+# Usage:
+#   scripts/elway irv-ml1 --playbook playbooks/deploy-ace-step.yaml
+#
+# Idempotent — every step is creates-/when-gated; rerun is safe.
+
+vars:
+  compose_dir: /opt/docker/compose/ace-step
+  worktank_root: /worktank/ace-step
+  host_port: "8210"
+
+steps:
+  # ── sanity checks (dirs were created by user-side sudo prep) ────────
+
+  - name: Verify /worktank/ace-step exists and is writable
+    shell: test -w {{ worktank_root }}
+    changed_when: "false"
+
+  - name: Verify compose dir exists and is writable
+    shell: test -w {{ compose_dir }}
+    changed_when: "false"
+
+  # ── deploy compose + env ────────────────────────────────────────────
+
+  - name: Upload compose.yaml
+    upload:
+      src: stacks/ace-step/compose.yaml
+      dest: "{{ compose_dir }}/compose.yaml"
+      mode: "0644"
+
+  - name: Upload Dockerfile (patched for cu126 torch resolution)
+    upload:
+      src: stacks/ace-step/Dockerfile
+      dest: "{{ compose_dir }}/Dockerfile"
+      mode: "0644"
+
+  - name: Seed .env from template (only if absent)
+    upload:
+      src: stacks/ace-step/.env.example
+      dest: "{{ compose_dir }}/.env"
+      mode: "0644"
+    when: "[ ! -f {{ compose_dir }}/.env ]"
+
+  # ── build + bring up ────────────────────────────────────────────────
+
+  - name: docker compose build (~10-15 min first time; cached after)
+    shell: |
+      set -o pipefail
+      cd {{ compose_dir }} && docker compose build 2>&1 \
+        | grep -vE '^#[0-9]+ |^ => |^=> |Collecting|Downloading|Requirement|Using cached|Installing collected|Successfully (installed|built)|━'
+
+  - name: docker compose up -d
+    shell: cd {{ compose_dir }} && docker compose up -d
+
+  - name: Wait for /health to respond (allow ~10 min for first model download + warmup)
+    shell: |
+      for i in $(seq 1 120); do
+        curl -sf -o /dev/null --max-time 3 http://localhost:{{ host_port }}/health && exit 0
+        sleep 5
+      done
+      exit 1
+    changed_when: "false"
+
+verify:
+  - name: /health returns 200
+    shell: curl -sf -o /dev/null http://localhost:{{ host_port }}/health
+    changed_when: "false"
+
+  - name: Container is running
+    shell: docker inspect ace-step --format '{{.State.Status}}' | grep -q running
+    changed_when: "false"
diff --git a/playbooks/deploy-stable-audio-open.yaml b/playbooks/deploy-stable-audio-open.yaml
new file mode 100644
index 0000000..d55315f
--- /dev/null
+++ b/playbooks/deploy-stable-audio-open.yaml
@@ -0,0 +1,126 @@
+# Deploy Stable Audio Open 1.0 (Stability AI diffusion SFX generator)
+# to irv-ml1.
+#
+# Builds a small custom image from server.py + Dockerfile (no upstream
+# Docker exists). ~5-10 min cold build (pytorch base + diffusers stack).
+# First start pulls the model (~6 GB) from HF into the bind-mounted
+# cache, then loads to VRAM (~30-60 s).
+#
+# Pre-req (user runs once):
+#   1. Visit https://huggingface.co/stabilityai/stable-audio-open-1.0
+#      and accept the Stability AI Community License (one click).
+#   2. Generate a read token at https://huggingface.co/settings/tokens.
+#   3. Put it in /opt/docker/compose/stable-audio-open/.env as
+#      SAO_HF_TOKEN=hf_xxx (the playbook seeds .env from .env.example
+#      with this field blank; the model gate fails closed without it).
+#   4. ssh -t irv-ml1 'sudo mkdir -p \
+#         /worktank/stable-audio-open/{hf_cache,outputs} \
+#         /opt/docker/compose/stable-audio-open && \
+#         sudo chown -R lkraven:lkraven \
+#         /worktank/stable-audio-open /opt/docker/compose/stable-audio-open'
+#
+# Usage:
+#   scripts/elway irv-ml1 --playbook playbooks/deploy-stable-audio-open.yaml
+#
+# Idempotent — every step is creates-/when-gated; rerun is safe.
+
+vars:
+  compose_dir: /opt/docker/compose/stable-audio-open
+  worktank_root: /worktank/stable-audio-open
+  host_port: "8211"
+
+steps:
+  # ── sanity checks (dirs were created by user-side sudo prep) ────────
+
+  - name: Verify /worktank/stable-audio-open exists and is writable
+    shell: test -w {{ worktank_root }}
+    changed_when: "false"
+
+  - name: Verify compose dir exists and is writable
+    shell: test -w {{ compose_dir }}
+    changed_when: "false"
+
+  # ── upload build context (compose + Dockerfile + server.py) ─────────
+
+  - name: Upload compose.yaml
+    upload:
+      src: stacks/stable-audio-open/compose.yaml
+      dest: "{{ compose_dir }}/compose.yaml"
+      mode: "0644"
+
+  - name: Upload Dockerfile
+    upload:
+      src: stacks/stable-audio-open/Dockerfile
+      dest: "{{ compose_dir }}/Dockerfile"
+      mode: "0644"
+
+  - name: Upload server.py
+    upload:
+      src: stacks/stable-audio-open/server.py
+      dest: "{{ compose_dir }}/server.py"
+      mode: "0644"
+
+  - name: Seed .env from template (only if absent — REMEMBER TO SET SAO_HF_TOKEN)
+    upload:
+      src: stacks/stable-audio-open/.env.example
+      dest: "{{ compose_dir }}/.env"
+      mode: "0644"
+    when: "[ ! -f {{ compose_dir }}/.env ]"
+
+  # Fail loud + early if the HF token is still empty — the model is
+  # gated and the container will crashloop on a 401 if we let it boot
+  # without one. Better to bail here than to wait for the healthcheck
+  # deadline to expire.
+  - name: Verify SAO_HF_TOKEN is set (model is gated, 401s without it)
+    shell: |
+      set -e
+      grep -q '^SAO_HF_TOKEN=hf_' {{ compose_dir }}/.env || {
+        echo "ERROR: SAO_HF_TOKEN is empty or invalid in {{ compose_dir }}/.env" >&2
+        echo "  1. Accept license at https://huggingface.co/stabilityai/stable-audio-open-1.0" >&2
+        echo "  2. Generate token at https://huggingface.co/settings/tokens" >&2
+        echo "  3. Put hf_xxx token into {{ compose_dir }}/.env" >&2
+        exit 1
+      }
+    changed_when: "false"
+
+  # ── build + bring up ────────────────────────────────────────────────
+
+  - name: docker compose build (~5-10 min first time; cached after)
+    shell: |
+      set -o pipefail
+      cd {{ compose_dir }} && docker compose build 2>&1 \
+        | grep -vE '^#[0-9]+ |^ => |^=> |Collecting|Downloading|Requirement|Using cached|Installing collected|Successfully (installed|built)|━'
+
+  - name: docker compose up -d
+    shell: cd {{ compose_dir }} && docker compose up -d
+
+  - name: Wait for /health to respond (allow ~10 min for first model download + load)
+    shell: |
+      for i in $(seq 1 120); do
+        curl -sf -o /dev/null --max-time 3 http://localhost:{{ host_port }}/health && exit 0
+        sleep 5
+      done
+      exit 1
+    changed_when: "false"
+
+verify:
+  - name: /health returns 200 and reports model loaded
+    shell: |
+      out=$(curl -sf --max-time 5 http://localhost:{{ host_port }}/health)
+      echo "$out" | grep -q '"loaded":true' || { echo "model not loaded: $out" >&2; exit 1; }
+    changed_when: "false"
+
+  - name: /v1/audio/sfx returns a real WAV (cheap 1s clip, 10 steps)
+    shell: |
+      out=$(mktemp --suffix=.wav)
+      curl -sf -X POST http://localhost:{{ host_port }}/v1/audio/sfx \
+        -H 'Content-Type: application/json' \
+        -d '{"prompt":"a single soft bell chime","duration":1,"steps":10}' \
+        -o "$out" --max-time 60
+      file -b "$out" | grep -q '^RIFF.*WAVE'
+      rm -f "$out"
+    changed_when: "false"
+
+  - name: Container is running
+    shell: docker inspect stable-audio-open --format '{{.State.Status}}' | grep -q running
+    changed_when: "false"
diff --git a/stacks/ace-step/.env.example b/stacks/ace-step/.env.example
new file mode 100644
index 0000000..e838291
--- /dev/null
+++ b/stacks/ace-step/.env.example
@@ -0,0 +1,47 @@
+# ACE-Step 1.5 stack tunables. Copy to `.env` on irv-ml1 before
+# deploying.
+
+# ── build pin ────────────────────────────────────────────────────────
+# SHA of ace-step/ACE-Step to build from. Use the FULL 40-char SHA —
+# docker buildx git source resolver rejects short hashes. `main` works
+# at first deploy; pin to a real SHA before any production cutover so
+# upstream commits don't surprise you on next rebuild.
+ACE_STEP_SHA=main
+
+# Local image tag — bump when you change build context to force a
+# fresh layer build.
+ACE_STEP_TAG=v1
+
+# ── network ──────────────────────────────────────────────────────────
+# Host port (container listens on 8000 internally — infer-api.py
+# hardcodes uvicorn.run(host=0.0.0.0, port=8000)).
+# Reservations on irv-ml1: 8188 ComfyUI, 8190 CosyVoice, 8191 Qwen3-TTS,
+# 8192 IndexTTS-2, 8193 Kokoro, 8194 VibeVoice, 8195 Fish, 8196
+# Chatterbox, 8197 Voxtral, 8765 Parakeet ASR. 8210 starts the
+# audio-generation block (music + SFX) so future TTS adds can keep
+# going from 8198+.
+ACE_STEP_PORT=8210
+ACE_STEP_BIND=0.0.0.0
+
+# ── runtime / GPU ────────────────────────────────────────────────────
+# GPU pinning. "0" = RTX 3090 (24 GB), "1" = RTX A6000 (48 GB).
+# A6000 (1) recommended — Fish s2-pro lives there at ~17 GB, and
+# ACE-Step adds ~10-12 GB during inference, leaving comfortable
+# headroom on the 48 GB card. The 3090 is full with the TTS slate.
+ACE_STEP_GPU_DEVICES=1
+
+# ── persistent storage on the host ───────────────────────────────────
+# Model checkpoints — primary spot for any manually-staged checkpoints.
+# ACE-Step's auto-download lands in HF_HOME (cache dir below).
+ACE_STEP_CHECKPOINTS_DIR=/worktank/ace-step/checkpoints
+
+# Generated audio output — clients can pull from here via the
+# returned file path in the /generate response.
+ACE_STEP_OUTPUTS_DIR=/worktank/ace-step/outputs
+
+# Application logs.
+ACE_STEP_LOGS_DIR=/worktank/ace-step/logs
+
+# HF cache — first start pulls the ACE-Step checkpoint (~5-10 GB)
+# into this dir. Persistent across container recreates.
+ACE_STEP_CACHE_DIR=/worktank/ace-step/hf_cache
diff --git a/stacks/ace-step/Dockerfile b/stacks/ace-step/Dockerfile
new file mode 100644
index 0000000..250ffc0
--- /dev/null
+++ b/stacks/ace-step/Dockerfile
@@ -0,0 +1,66 @@
+# Custom Dockerfile for ACE-Step 1.5.
+#
+# Mirrors upstream's Dockerfile structure, but fixes a CUDA-version
+# mismatch that crashloops the upstream image as of April 2026:
+#   * upstream's requirements.txt lists `torch torchvision torchaudio`
+#     with no version pins;
+#   * upstream's pip install uses `--extra-index-url cu126`, which is
+#     a FALLBACK only — pypi default wins for resolution;
+#   * pypi-default torch is now cu13, so torch installs cu13 + the
+#     cu126 fallback only kicks in for torchvision/torchaudio →
+#     `RuntimeError: Detected that PyTorch and torchvision were compiled
+#     with different CUDA major versions`.
+#
+# Fix: install torch/torchvision/torchaudio FIRST from the cu126 index
+# (forced via --index-url, not --extra-index-url). Then `pip install
+# -r requirements.txt` sees they're already satisfied and leaves them
+# alone.
+#
+# Also: command is `python3 infer-api.py` (REST), not `gui.py` (Gradio)
+# — see compose.yaml command override; CMD here is the same default
+# so the image works standalone too.
+FROM nvidia/cuda:12.6.0-runtime-ubuntu22.04 AS base
+
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    HF_HUB_ENABLE_HF_TRANSFER=1 \
+    DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        python3.10 \
+        python3-pip \
+        python3-venv \
+        python3-dev \
+        build-essential \
+        git \
+        curl \
+        ca-certificates \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/* \
+    && ln -sf /usr/bin/python3 /usr/bin/python
+
+RUN python -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+WORKDIR /app
+
+# Clone upstream. Bake the SHA into a layer-cache key so a different
+# SHA invalidates everything below.
+ARG ACE_STEP_REF=main
+RUN git clone https://github.com/ace-step/ACE-Step.git . \
+    && git checkout ${ACE_STEP_REF} \
+    && echo "ace-step ref: $(git rev-parse HEAD)"
+
+# Pre-install torch/torchvision/torchaudio from the cu126 index — this
+# satisfies the unpinned entries in requirements.txt so the next pip
+# install doesn't re-resolve them from pypi default (cu13).
+RUN pip install --no-cache-dir --upgrade pip \
+    && pip install --no-cache-dir \
+        torch torchvision torchaudio \
+        --index-url https://download.pytorch.org/whl/cu126 \
+    && pip install --no-cache-dir hf_transfer peft \
+    && pip install --no-cache-dir -r requirements.txt \
+    && pip install --no-cache-dir .
+
+EXPOSE 8000
+CMD ["python3", "infer-api.py"]
diff --git a/stacks/ace-step/README.md b/stacks/ace-step/README.md
new file mode 100644
index 0000000..1770b68
--- /dev/null
+++ b/stacks/ace-step/README.md
@@ -0,0 +1,53 @@
+# ace-step
+
+ACE-Step 1.5 — Apache 2.0 open-source music generation foundation
+model. Hybrid diffusion + LLM. Generates lyric-aware multi-minute
+songs (vocals + instrumentation).
+
+| | |
+|---|---|
+| host | `irv-ml1` |
+| port | `8210` |
+| GPU | A6000 (`device_ids: ["1"]`) |
+| VRAM | ~10-12 GB during inference |
+| upstream | https://github.com/ace-step/ACE-Step |
+| license | Apache 2.0 |
+
+## API surface
+
+`infer-api.py` (FastAPI) exposes:
+
+- `GET /health` — liveness, returns 200 once the process is up
+  (model is lazy-loaded on first /generate).
+- `POST /generate` — body: `ACEStepInput` Pydantic model with
+  ~27 params (prompt, lyrics, audio_duration, guidance_scale, etc.).
+  Returns `{status, output_path, message}`.
+
+The container does NOT expose the Gradio UI — we override the upstream
+default `python3 acestep/gui.py` with `python3 infer-api.py`. If you
+want the Gradio UI for ad-hoc experimentation, run a one-off:
+
+```bash
+ssh irv-ml1 'docker exec -it ace-step python3 acestep/gui.py --server_name 0.0.0.0 --port 7865'
+```
+
+…and port-forward 7865 to your laptop.
+
+## Deploy
+
+```bash
+scripts/elway irv-ml1 --playbook playbooks/deploy-ace-step.yaml
+```
+
+Idempotent. Cold build is ~10-15 min (CUDA + torch + transformers +
+spacy + audio deps). First `/generate` triggers the model download
+(~5-10 GB) and warmup (~30-60 s).
+
+## Tunables
+
+See `.env.example` — copy to `.env` on the host (lives at
+`/opt/docker/compose/ace-step/.env`, gitignored). Common knobs:
+
+- `ACE_STEP_SHA` — pin upstream commit
+- `ACE_STEP_GPU_DEVICES` — GPU index
+- `ACE_STEP_*_DIR` — bind-mount paths under `/worktank/ace-step/`
diff --git a/stacks/ace-step/compose.yaml b/stacks/ace-step/compose.yaml
new file mode 100644
index 0000000..8de4475
--- /dev/null
+++ b/stacks/ace-step/compose.yaml
@@ -0,0 +1,70 @@
+# ACE-Step 1.5 — open-source music generation foundation model
+# (April 2026). Hybrid diffusion + LLM architecture, Apache 2.0.
+# ~50-80 s for a 4-minute song on A6000; under 4 GB VRAM at idle,
+# ~10-12 GB during inference. Beats YuE / DiffRhythm on the
+# speed/coherence trade.
+#
+# We launch upstream's REST API (`infer-api.py`) instead of the
+# default `gui.py` (Gradio). The REST surface is what we'll point
+# clients + automation at; Gradio is dev-time eye candy.
+#
+# Image is built locally from upstream's repo via docker buildx git
+# context, same pattern as fish-s2.
+#
+# All tunables live in .env — edit that, not this file.
+
+services:
+  ace-step:
+    image: local/ace-step:${ACE_STEP_TAG}
+    build:
+      # Build from local Dockerfile (not upstream's git context) — we
+      # ship a patched Dockerfile that fixes upstream's torch/cu126
+      # resolution bug. Playbook uploads Dockerfile alongside this
+      # compose.yaml.
+      context: .
+      dockerfile: Dockerfile
+      args:
+        ACE_STEP_REF: ${ACE_STEP_SHA}
+    container_name: ace-step
+    restart: unless-stopped
+    runtime: nvidia
+    ports:
+      # Container default for infer-api.py is 8000 (hardcoded
+      # uvicorn.run(host=0.0.0.0, port=8000) — no flags). Map host
+      # ACE_STEP_PORT to it.
+      - "${ACE_STEP_BIND:-0.0.0.0}:${ACE_STEP_PORT}:8000"
+    environment:
+      - NVIDIA_VISIBLE_DEVICES=${ACE_STEP_GPU_DEVICES:-1}
+      # ACE_OUTPUT_DIR is read by acestep at generation time — keep
+      # in sync with the bind mount below.
+      - ACE_OUTPUT_DIR=/app/outputs
+      # HF_HOME points the HuggingFace cache at the bind mount so the
+      # ~5-10 GB checkpoint download survives container recreates.
+      - HF_HOME=/app/hf_cache
+    volumes:
+      - ${ACE_STEP_CHECKPOINTS_DIR}:/app/checkpoints
+      - ${ACE_STEP_OUTPUTS_DIR}:/app/outputs
+      - ${ACE_STEP_LOGS_DIR}:/app/logs
+      - ${ACE_STEP_CACHE_DIR}:/app/hf_cache
+    # Override upstream's default `python3 acestep/gui.py` with the
+    # REST API entry point. infer-api.py self-binds 0.0.0.0:8000 and
+    # exposes POST /generate + GET /health.
+    command: ["python3", "infer-api.py"]
+    healthcheck:
+      # /health is the cheapest signal infer-api.py exposes — returns
+      # 200 as soon as the FastAPI app is up. The pipeline lazy-loads
+      # on first /generate, so /health says "process alive" not
+      # "model warm". Good enough for a liveness signal; first
+      # /generate has the ~30-60 s warmup baked in.
+      test: ["CMD-SHELL", "python3 -c \"import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5).status==200 else 1)\""]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      # First boot pulls ACE-Step checkpoint (~5-10 GB) into HF cache.
+      start_period: 600s
+    labels:
+      - homepage.group=AI Systems
+      - homepage.name=ACE-Step
+      - homepage.icon=mdi-music-note-eighth
+      - homepage.description=Open-source music generation — 4-min song in ~60s, lyrics + style prompts (irv-ml1)
+      - homepage.href=http://10.100.79.3:${ACE_STEP_PORT}
diff --git a/stacks/stable-audio-open/.env.example b/stacks/stable-audio-open/.env.example
new file mode 100644
index 0000000..5052fe5
--- /dev/null
+++ b/stacks/stable-audio-open/.env.example
@@ -0,0 +1,48 @@
+# Stable Audio Open 1.0 stack tunables. Copy to `.env` on irv-ml1
+# before deploying.
+
+# ── image ────────────────────────────────────────────────────────────
+# Local image tag — bump when you change Dockerfile or server.py to
+# force a fresh build.
+SAO_TAG=v1
+
+# Which Stable Audio model to load. As of 2026-04 the only released
+# checkpoint is 1.0; future revisions can swap here without touching
+# compose.yaml or server.py.
+SAO_MODEL=stabilityai/stable-audio-open-1.0
+
+# ── network ──────────────────────────────────────────────────────────
+# Host port (container listens on 8000 internally).
+# Reservations on irv-ml1: 8188 ComfyUI, 8190 CosyVoice, 8191 Qwen3-TTS,
+# 8192 IndexTTS-2, 8193 Kokoro, 8194 VibeVoice, 8195 Fish, 8196
+# Chatterbox, 8197 Voxtral, 8210 ACE-Step (music), 8765 Parakeet ASR.
+SAO_PORT=8211
+SAO_BIND=0.0.0.0
+
+# ── runtime / GPU ────────────────────────────────────────────────────
+# GPU pinning. "0" = RTX 3090 (24 GB), "1" = RTX A6000 (48 GB).
+# A6000 (1) recommended — Fish s2-pro lives there at ~17 GB; SAO adds
+# ~6 GB practical (model fp16 + small VAE working set), and ACE-Step
+# adds another ~12 GB during inference. Total ~35 GB / 48 GB still
+# leaves headroom. The 3090 is full with the TTS slate.
+SAO_GPU_DEVICES=1
+
+# ── HuggingFace auth ─────────────────────────────────────────────────
+# HF token — REQUIRED. Stable Audio Open is gated; you must:
+#   1. Visit https://huggingface.co/stabilityai/stable-audio-open-1.0
+#      and accept the Stability AI Community License (one click).
+#   2. Generate a read token at
+#      https://huggingface.co/settings/tokens.
+#   3. Paste it here.
+# Without this, the first model download 401s and the container
+# crashloops.
+SAO_HF_TOKEN=
+
+# ── persistent storage on the host ───────────────────────────────────
+# HF cache — first start pulls the model (~6 GB) into this dir.
+# Persistent across container recreates so we don't re-pull.
+SAO_CACHE_DIR=/worktank/stable-audio-open/hf_cache
+
+# Generated audio output — clients can pull from here for any flow
+# that wants a file path instead of a streamed WAV body.
+SAO_OUTPUTS_DIR=/worktank/stable-audio-open/outputs
diff --git a/stacks/stable-audio-open/Dockerfile b/stacks/stable-audio-open/Dockerfile
new file mode 100644
index 0000000..22ae6e8
--- /dev/null
+++ b/stacks/stable-audio-open/Dockerfile
@@ -0,0 +1,43 @@
+# Stable Audio Open 1.0 inference image.
+# pytorch/pytorch base ships torch + cuda + cudnn already linked, so
+# we only layer the diffusers stack + a libsndfile for soundfile + the
+# fastapi shim. Smaller and faster to build than starting from
+# nvidia/cuda and pip-installing torch ourselves.
+FROM pytorch/pytorch:2.5.1-cuda12.4-cudnn9-runtime AS base
+
+ENV PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PIP_NO_CACHE_DIR=1 \
+    PIP_DISABLE_PIP_VERSION_CHECK=1 \
+    HF_HOME=/app/hf_cache
+
+# libsndfile1 is the C lib soundfile binds to. Without it the pip
+# install of soundfile succeeds but `import soundfile` fails at
+# runtime with OSError: cannot find libsndfile.
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        libsndfile1 \
+    && rm -rf /var/lib/apt/lists/*
+
+# protobuf + sentencepiece are pulled in by the T5 text encoder
+# (Stable Audio Open uses google/t5-base-cb under the hood).
+# accelerate gates the .to(device) fast path for diffusers.
+# torchsde is required by CosineDPMSolverMultistepScheduler — diffusers
+# doesn't pull it as a hard dep; without it, pipeline init fails with
+# "CosineDPMSolverMultistepScheduler requires the torchsde library".
+RUN pip install \
+        "diffusers>=0.27.0" \
+        "transformers>=4.40.0" \
+        accelerate \
+        protobuf \
+        sentencepiece \
+        soundfile \
+        torchsde \
+        fastapi \
+        "uvicorn[standard]" \
+        pydantic
+
+WORKDIR /app
+COPY server.py /app/server.py
+
+EXPOSE 8000
+CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "8000"]
diff --git a/stacks/stable-audio-open/README.md b/stacks/stable-audio-open/README.md
new file mode 100644
index 0000000..5c963a5
--- /dev/null
+++ b/stacks/stable-audio-open/README.md
@@ -0,0 +1,55 @@
+# stable-audio-open
+
+Stability AI's Stable Audio Open 1.0 — text-to-audio latent diffusion.
+Strong on SFX, foley, ambience, short loops. Not a music model — it
+does not generate intelligible vocals or structured songs (use
+`ace-step` for that).
+
+| | |
+|---|---|
+| host | `irv-ml1` |
+| port | `8211` |
+| GPU | A6000 (`device_ids: ["1"]`) |
+| VRAM | ~6 GB in fp16 |
+| max clip | 47 s at 44.1 kHz |
+| upstream | https://github.com/Stability-AI/stable-audio-tools |
+| model | `stabilityai/stable-audio-open-1.0` (gated) |
+| license | Stability AI Community (non-commercial / personal / research) |
+
+## API surface
+
+`server.py` (custom FastAPI shim) exposes:
+
+- `GET /health` — returns 200 once the model is loaded.
+- `POST /v1/audio/sfx` — returns a `audio/wav` blob.
+
+```jsonc
+{
+  "prompt": "a vintage typewriter clacking in a quiet room",
+  "negative_prompt": "Low quality.",   // optional, default "Low quality."
+  "duration": 10.0,                     // seconds, 0.5 – 47
+  "steps": 100,                         // 10 – 300, more = better quality
+  "seed": 42,                           // optional
+  "cfg_scale": 7.0                      // 0 – 20
+}
+```
+
+Why a custom shim: there's no upstream Docker image and no upstream
+HTTP server for Stable Audio Open. Diffusers exposes
+`StableAudioPipeline` cleanly — the shim is ~70 lines.
+
+## Deploy
+
+```bash
+scripts/elway irv-ml1 --playbook playbooks/deploy-stable-audio-open.yaml
+```
+
+Pre-deploy: visit https://huggingface.co/stabilityai/stable-audio-open-1.0
+once and accept the Community License (HF token alone is not enough —
+the gate is per-model). Then put the token in `SAO_HF_TOKEN` in `.env`
+on the host.
+
+## Tunables
+
+See `.env.example` — copy to `.env` on the host (lives at
+`/opt/docker/compose/stable-audio-open/.env`, gitignored).
diff --git a/stacks/stable-audio-open/compose.yaml b/stacks/stable-audio-open/compose.yaml
new file mode 100644
index 0000000..c64179f
--- /dev/null
+++ b/stacks/stable-audio-open/compose.yaml
@@ -0,0 +1,61 @@
+# Stable Audio Open 1.0 — Stability AI's open-weight latent-diffusion
+# SFX/ambience generator. 1.21B params, ~4-6 GB VRAM in fp16, up to
+# 47 s clips at 44.1 kHz. Strong on text-aligned sound effects, foley,
+# field-recording-style ambience. NOT a music model — it does not
+# generate intelligible vocals or structured songs (use ACE-Step for
+# that).
+#
+# LICENSE: Stability AI Community License. Personal / research use is
+# free; commercial use requires a separate license from Stability
+# (https://stability.ai/license). Same posture we already accepted
+# for Voxtral.
+#
+# No upstream Docker image — we ship a custom Dockerfile + a small
+# FastAPI shim (server.py) that wraps diffusers' StableAudioPipeline
+# and exposes POST /v1/audio/sfx.
+#
+# All tunables live in .env — edit that, not this file.
+
+services:
+  stable-audio-open:
+    image: local/stable-audio-open:${SAO_TAG}
+    build:
+      # Build context is the compose dir on the host — the playbook
+      # uploads server.py + Dockerfile alongside this compose.yaml.
+      context: .
+      dockerfile: Dockerfile
+    container_name: stable-audio-open
+    restart: unless-stopped
+    runtime: nvidia
+    ports:
+      - "${SAO_BIND:-0.0.0.0}:${SAO_PORT}:8000"
+    environment:
+      - NVIDIA_VISIBLE_DEVICES=${SAO_GPU_DEVICES:-1}
+      - SAO_MODEL=${SAO_MODEL:-stabilityai/stable-audio-open-1.0}
+      - HF_HOME=/app/hf_cache
+      # Model is gated on HuggingFace (you must accept the Stability
+      # Community License once on the model page before the token can
+      # download it). Set SAO_HF_TOKEN in .env. Without this, the
+      # first model download 401s and the container crashloops.
+      - HF_TOKEN=${SAO_HF_TOKEN}
+    volumes:
+      - ${SAO_CACHE_DIR}:/app/hf_cache
+      - ${SAO_OUTPUTS_DIR}:/app/outputs
+    healthcheck:
+      # /health is set by server.py — returns 200 once FastAPI is up
+      # AND the pipeline finished loading (lifespan blocks startup
+      # until the model is in VRAM).
+      test: ["CMD-SHELL", "python -c \"import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5).status==200 else 1)\""]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      # First boot pulls the model (~6 GB) into HF cache + loads to
+      # VRAM. Cold start ~3-5 min on a fast pipe; subsequent starts
+      # are ~30 s.
+      start_period: 600s
+    labels:
+      - homepage.group=AI Systems
+      - homepage.name=Stable Audio Open
+      - homepage.icon=mdi-waveform
+      - homepage.description=Diffusion SFX/ambience generator — up to 47s at 44.1 kHz (irv-ml1)
+      - homepage.href=http://10.100.79.3:${SAO_PORT}
diff --git a/stacks/stable-audio-open/server.py b/stacks/stable-audio-open/server.py
new file mode 100644
index 0000000..3c24955
--- /dev/null
+++ b/stacks/stable-audio-open/server.py
@@ -0,0 +1,80 @@
+# FastAPI shim around diffusers' StableAudioPipeline.
+# Single endpoint POST /v1/audio/sfx returns a WAV blob.
+# Model is loaded once on startup and held in process memory.
+import io
+import os
+import time
+from contextlib import asynccontextmanager
+from typing import Optional
+
+import soundfile as sf
+import torch
+from diffusers import StableAudioPipeline
+from fastapi import FastAPI, HTTPException, Response
+from pydantic import BaseModel, Field
+
+MODEL_ID = os.environ.get("SAO_MODEL", "stabilityai/stable-audio-open-1.0")
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+DTYPE = torch.float16 if DEVICE == "cuda" else torch.float32
+
+state: dict = {}
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    print(f"[sao] loading {MODEL_ID} on {DEVICE} ({DTYPE})", flush=True)
+    t0 = time.time()
+    pipe = StableAudioPipeline.from_pretrained(MODEL_ID, torch_dtype=DTYPE)
+    pipe = pipe.to(DEVICE)
+    state["pipe"] = pipe
+    print(f"[sao] loaded in {time.time() - t0:.1f}s", flush=True)
+    yield
+    state.clear()
+
+
+app = FastAPI(lifespan=lifespan)
+
+
+class SfxRequest(BaseModel):
+    prompt: str = Field(..., min_length=1)
+    negative_prompt: Optional[str] = "Low quality."
+    duration: float = Field(10.0, gt=0.5, le=47.0)
+    steps: int = Field(100, ge=10, le=300)
+    seed: Optional[int] = None
+    cfg_scale: float = Field(7.0, gt=0.0, le=20.0)
+
+
+@app.get("/health")
+def health():
+    return {
+        "status": "ok",
+        "model": MODEL_ID,
+        "device": DEVICE,
+        "loaded": "pipe" in state,
+    }
+
+
+@app.post("/v1/audio/sfx")
+def sfx(req: SfxRequest):
+    pipe = state.get("pipe")
+    if pipe is None:
+        raise HTTPException(503, "model not loaded yet")
+
+    generator = None
+    if req.seed is not None:
+        generator = torch.Generator(DEVICE).manual_seed(req.seed)
+
+    audio = pipe(
+        req.prompt,
+        negative_prompt=req.negative_prompt,
+        num_inference_steps=req.steps,
+        audio_end_in_s=req.duration,
+        num_waveforms_per_prompt=1,
+        generator=generator,
+    ).audios
+
+    waveform = audio[0].T.float().cpu().numpy()
+    buf = io.BytesIO()
+    sf.write(buf, waveform, pipe.vae.sampling_rate, format="WAV")
+    buf.seek(0)
+    return Response(content=buf.read(), media_type="audio/wav")