vh
e0d1c44137
The 2026-09-06 headscale cutover retired irv-ml1's wg0 tunnel IP 10.100.79.3 (now 10.6.110.50). Repointed all LIVE canonical refs to the DNS NAME so the next move can't re-break them: homepage.href/siteMonitor labels across 25 stack composes, load-bearing env defaults (asset-engine INFERENCE_HOST, open-webui AUDIO_TTS_OPENAI_API_BASE_URL, skaldsong SKALDSONG_TTS_BASE_URL, zonos-gateway ZONOS_URL, dia), homepage services.yaml manual cards (Voice Design Studio, IRV-ML1), and servers/irv-ml1/ssh-target. Updated the stale 'WG tunnel' comment to the mesh reality. Left as-is: README curl-examples and .env.example comments (docs), and historical mentions in CLAUDE.md/persistent-memory. NOTE: applying the label repoints to the RUNNING irv-ml1 containers needs a recreate per service (labels read at creation); deployed .env values are separate from these canonical defaults.
75 lines
3.6 KiB
YAML
75 lines
3.6 KiB
YAML
# Chatterbox Turbo (Resemble AI's 350M-param low-latency English TTS
|
|
# with zero-shot voice cloning) served via devnen/Chatterbox-TTS-Server
|
|
# — the most actively-maintained OpenAI-compat wrapper that supports
|
|
# the Turbo checkpoint.
|
|
#
|
|
# Why this stack exists alongside the other TTS:
|
|
# * Low-latency English with VOICE CLONING (Kokoro is fast but
|
|
# fixed-voice; this fills the speed-AND-cloning slot).
|
|
# * Native paralinguistic tags inline in text:
|
|
# [laugh] [cough] [sigh] [gasp] [whisper] [breath]
|
|
# Different shape from IndexTTS-2's emotion vector — cleaner for
|
|
# "say it like this" markup directly in the prompt.
|
|
# * MIT weights + code; ~2.5 GB VRAM at fp16; ~75 ms latency.
|
|
# * Mandatory PerTh watermark on outputs (Resemble policy, can't
|
|
# be disabled). Non-issue for internal use.
|
|
#
|
|
# Image is built locally from the upstream Dockerfile via docker
|
|
# buildx git-context (no source vendored on the host).
|
|
#
|
|
# All tunables live in .env — edit that, not this file.
|
|
|
|
services:
|
|
chatterbox:
|
|
image: local/chatterbox:${CHATTERBOX_TAG}
|
|
build:
|
|
context: https://github.com/devnen/Chatterbox-TTS-Server.git#${CHATTERBOX_SHA}
|
|
# Upstream moved Dockerfiles from docker/ to repo root and renamed
|
|
# them by CUDA version (Dockerfile.cu128, .cpu, .rocm). The old
|
|
# `docker/Dockerfile.gpu` is gone. cu128 is the GPU build for
|
|
# CUDA 12.8 — fits irv-ml1's 595.58.03 driver (CUDA 13.2 capable,
|
|
# backward-compatible to 12.8 toolkit-built images).
|
|
dockerfile: Dockerfile.cu128
|
|
container_name: chatterbox
|
|
restart: unless-stopped
|
|
runtime: nvidia
|
|
ports:
|
|
- "${CHATTERBOX_BIND:-0.0.0.0}:${CHATTERBOX_PORT}:8004"
|
|
environment:
|
|
- NVIDIA_VISIBLE_DEVICES=${CHATTERBOX_GPU_DEVICES:-0}
|
|
# Switch to ResembleAI/chatterbox-turbo (default) or the base
|
|
# ResembleAI/chatterbox / ResembleAI/chatterbox-multilingual
|
|
# via the wrapper's config hot-swap.
|
|
- CHATTERBOX_MODEL_REPO=${CHATTERBOX_MODEL_REPO:-ResembleAI/chatterbox-turbo}
|
|
- HF_HOME=/app/hf_cache
|
|
volumes:
|
|
- ${CHATTERBOX_REFERENCE_DIR}:/app/reference_audio
|
|
- ${CHATTERBOX_CACHE_DIR}:/app/hf_cache
|
|
# Optional: mount config.yaml as a host file for hot-edit. Default
|
|
# is to use the in-image config + env var overrides.
|
|
# - ${CHATTERBOX_CONFIG}:/app/config.yaml:ro
|
|
healthcheck:
|
|
# The devnen wrapper does NOT expose /health (no such route — use
|
|
# /docs or /openapi.json to enumerate). /api/model-info returns
|
|
# `{"loaded":true,...}` only after the model finishes loading,
|
|
# so it doubles as a liveness + ready probe.
|
|
#
|
|
# Use python urllib instead of curl: devnen's image is built
|
|
# from a python:3.10 base and doesn't ship curl. Bind 127.0.0.1
|
|
# explicitly — `localhost` on this image resolves to both ::1
|
|
# and 127.0.0.1, and uvicorn binds IPv4 only (busybox doesn't
|
|
# always retry on the v4 entry).
|
|
test: ["CMD-SHELL", "python3 -c \"import urllib.request,sys; b=urllib.request.urlopen('http://127.0.0.1:8004/api/model-info', timeout=5).read(); sys.exit(0 if b'\\\"loaded\\\":true' in b else 1)\""]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
# First boot pulls Chatterbox-Turbo (~6 GB total HF assets) and
|
|
# warms torch.compile — give it a generous deadline.
|
|
start_period: 600s
|
|
labels:
|
|
- homepage.group=AI - Speech (TTS)
|
|
- homepage.name=Chatterbox Turbo
|
|
- homepage.icon=mdi-account-music-outline
|
|
- homepage.description=Low-latency English TTS w/ voice cloning + paralinguistics (irv-ml1)
|
|
- homepage.href=http://irv-ml1.nh3.internal:${CHATTERBOX_PORT}
|