feat(omnivoice): new TTS stack — k2-fsa/OmniVoice on irv-ml1 3090

Zero-shot, massively-multilingual (600+ language) voice-cloning + voice-design
TTS (diffusion-LM, Apache-2.0). No official image, so a thin CUDA container
around the pip package running upstream's own Gradio demo (no FastAPI wrapper).
Pinned to GPU 0 (3090) — the A6000 is ComfyUI-exclusive — port 8199. Built +
verified live on irv-ml1 (Gradio 200, container healthy). Surface is the Gradio
UI + Gradio API, NOT OpenAI-compat /v1/audio/speech (wrap later if asset-engine
should consume it). deploy-omnivoice.yaml builds local + verifies.

stacks/omnivoice/Dockerfile

@@ -0,0 +1,54 @@
+# syntax=docker/dockerfile:1.6
+#
+# OmniVoice (k2-fsa/OmniVoice) — zero-shot, massively-multilingual (600+
+# languages) voice-cloning + voice-design TTS, diffusion-LM architecture,
+# Apache-2.0. Upstream ships a pip package + its own Gradio demo
+# (`omnivoice-demo`); there's no official image, so we build a thin CUDA
+# container around the pip package and run its Gradio server directly.
+# Unlike index-tts we DON'T need a FastAPI wrapper — OmniVoice serves itself.
+
+ARG CUDA_BASE=nvidia/cuda:12.8.0-cudnn-runtime-ubuntu22.04
+FROM ${CUDA_BASE}
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    PIP_ROOT_USER_ACTION=ignore \
+    PYTHONUNBUFFERED=1 \
+    PATH="/opt/venv/bin:${PATH}"
+
+RUN apt-get update \
+ && apt-get install -y --no-install-recommends \
+        python3.10 python3.10-venv python3-pip \
+        git ffmpeg libsndfile1 \
+        ca-certificates wget \
+ && rm -rf /var/lib/apt/lists/* \
+ && python3.10 -m venv /opt/venv
+
+# CUDA 12.8 torch wheels (per OmniVoice's documented install line).
+RUN pip install --no-cache-dir \
+        torch==2.8.0 torchaudio==2.8.0 \
+        --index-url https://download.pytorch.org/whl/cu128
+
+# OmniVoice from PyPI (+ huggingface_hub for the entrypoint weight pre-warm).
+# Optional reproducible pin via the OMNIVOICE_VERSION build arg (empty=latest).
+ARG OMNIVOICE_VERSION=
+RUN pip install --no-cache-dir "omnivoice${OMNIVOICE_VERSION:+==${OMNIVOICE_VERSION}}" huggingface_hub
+
+# Fail the build loudly if the console script name isn't what we expect,
+# rather than crash-loop at runtime. Logs the actual omni* entrypoints.
+RUN echo "omni console scripts:" && (ls /opt/venv/bin | grep -i omni || true) \
+ && command -v omnivoice-demo >/dev/null \
+    || { echo "ERROR: omnivoice-demo CLI not found after install"; exit 1; }
+
+WORKDIR /app
+COPY entrypoint.sh /usr/local/bin/entrypoint.sh
+RUN chmod +x /usr/local/bin/entrypoint.sh
+
+EXPOSE 8001
+
+# Gradio serves HTML at / — 200 once the UI is up (weights load lazily on
+# first synth; the entrypoint pre-warms them). Generous start period.
+HEALTHCHECK --interval=30s --timeout=10s --start-period=900s --retries=3 \
+    CMD wget -q -O /dev/null http://127.0.0.1:8001/ || exit 1
+
+ENTRYPOINT ["/usr/local/bin/entrypoint.sh"]
+CMD ["omnivoice-demo", "--ip", "0.0.0.0", "--port", "8001"]