vh
984b72757f
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.
49 lines
1.9 KiB
YAML
49 lines
1.9 KiB
YAML
# OmniVoice (k2-fsa/OmniVoice) — zero-shot, massively-multilingual (600+
|
|
# language) voice-cloning + voice-design TTS, diffusion-LM, Apache-2.0.
|
|
# Served via upstream's own Gradio demo. NOTE: this exposes the Gradio UI
|
|
# + Gradio API, NOT an OpenAI-compatible /v1/audio/speech endpoint — wrap
|
|
# it later (à la stacks/index-tts/app.py) if asset-engine integration is
|
|
# wanted. For now it's a "stand it up and try it" UI.
|
|
#
|
|
# Build: local image from the Dockerfile in this dir. Weights download
|
|
# from HF (k2-fsa/OmniVoice) on first boot into ${OMNIVOICE_CACHE_DIR}.
|
|
#
|
|
# Pinned to the 3090 (device 0) on irv-ml1 — the A6000 (device 1) is
|
|
# ComfyUI-exclusive after the 2026-06-18 VRAM consolidation. OmniVoice
|
|
# runs in well under 5 GB; the 3090 had ~18 GB free.
|
|
#
|
|
# All tunables live in .env — edit that, not this file.
|
|
|
|
services:
|
|
omnivoice:
|
|
image: local/omnivoice:${OMNIVOICE_TAG:-latest}
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile
|
|
args:
|
|
OMNIVOICE_VERSION: ${OMNIVOICE_VERSION:-}
|
|
container_name: omnivoice
|
|
restart: unless-stopped
|
|
runtime: nvidia
|
|
ports:
|
|
- "${OMNIVOICE_BIND:-0.0.0.0}:${OMNIVOICE_PORT}:8001"
|
|
environment:
|
|
- NVIDIA_VISIBLE_DEVICES=${OMNIVOICE_GPU_DEVICES:-0}
|
|
- HF_HOME=/app/hf_cache
|
|
volumes:
|
|
- ${OMNIVOICE_CACHE_DIR}:/app/hf_cache
|
|
- ${OMNIVOICE_VOICES_DIR}:/app/voices
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "wget -q -O /dev/null http://localhost:8001/ || exit 1"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
# First boot: weight pre-warm download (entrypoint) + CUDA warmup.
|
|
start_period: 900s
|
|
labels:
|
|
- homepage.group=AI Systems
|
|
- homepage.name=OmniVoice
|
|
- homepage.icon=mdi-account-voice
|
|
- homepage.description=Zero-shot multilingual voice-cloning TTS (irv-ml1, 3090)
|
|
- homepage.href=http://10.100.79.3:${OMNIVOICE_PORT}
|