vh
e54df5f4f7
devnen/Chatterbox-TTS-Server doesn't expose /health — neither in code
nor OpenAPI. The deploy hung on the playbook's `Wait for /health to
respond` loop indefinitely (each curl -> 404, retry forever) even
though the container was up and the model loaded clean to CUDA at
22:52:21 (~42s after start).
/api/model-info returns `{"loaded":true,...}` only after the model
finishes loading, so it doubles as liveness + readiness. Updated:
* compose.yaml healthcheck — grep for `"loaded":true` from
/api/model-info.
* playbook wait step — same probe instead of /health.
* verify /health → verify /api/model-info reports loaded.
* verify /v1/audio/voices — switched from greping for `voice|alloy|echo`
literals to parsing JSON and asserting the actual response shape:
`{"status":"ok","voices":[...]}` (devnen's shape — note this is NOT
the OpenAI list-format vibevoice uses).
104 lines
4.1 KiB
YAML
104 lines
4.1 KiB
YAML
# Deploy Chatterbox Turbo (Resemble AI's low-latency English TTS w/
|
|
# voice cloning) via the devnen/Chatterbox-TTS-Server wrapper to
|
|
# irv-ml1.
|
|
#
|
|
# Builds the image locally from devnen's Dockerfile.gpu via docker
|
|
# buildx git URL context. ~8-10 min cold build (CUDA + torch +
|
|
# Chatterbox deps). First start pulls Chatterbox-Turbo weights (~6 GB)
|
|
# into the HF cache.
|
|
#
|
|
# Usage:
|
|
# scripts/elway irv-ml1 --playbook playbooks/deploy-chatterbox.yaml
|
|
#
|
|
# Idempotent — every step is creates-/when-gated; rerun is safe.
|
|
|
|
vars:
|
|
compose_dir: /opt/docker/compose/chatterbox
|
|
reference_dir: /worktank/chatterbox/reference_audio
|
|
cache_dir: /worktank/chatterbox/cache
|
|
host_port: "8196"
|
|
|
|
steps:
|
|
# ── host-side dirs ──────────────────────────────────────────────────
|
|
|
|
- name: Ensure /worktank/chatterbox root exists (one-time, sudo)
|
|
shell: mkdir -p /worktank/chatterbox
|
|
sudo: true
|
|
creates: /worktank/chatterbox
|
|
|
|
- name: Chown /worktank/chatterbox to lkraven
|
|
shell: chown lkraven:lkraven /worktank/chatterbox
|
|
sudo: true
|
|
when: '[ "$(stat -c %U /worktank/chatterbox)" != lkraven ]'
|
|
|
|
- name: Ensure reference-audio dir exists
|
|
shell: mkdir -p {{ reference_dir }}
|
|
creates: "{{ reference_dir }}"
|
|
|
|
- name: Ensure cache dir exists
|
|
shell: mkdir -p {{ cache_dir }}
|
|
creates: "{{ cache_dir }}"
|
|
|
|
- name: Ensure compose dir exists
|
|
shell: mkdir -p {{ compose_dir }}
|
|
creates: "{{ compose_dir }}"
|
|
|
|
# ── deploy compose files ────────────────────────────────────────────
|
|
|
|
- name: Upload compose.yaml
|
|
upload:
|
|
src: stacks/chatterbox/compose.yaml
|
|
dest: "{{ compose_dir }}/compose.yaml"
|
|
mode: "0644"
|
|
|
|
- name: Seed .env from template (only if absent)
|
|
upload:
|
|
src: stacks/chatterbox/.env.example
|
|
dest: "{{ compose_dir }}/.env"
|
|
mode: "0644"
|
|
when: "[ ! -f {{ compose_dir }}/.env ]"
|
|
|
|
# ── build + bring up ────────────────────────────────────────────────
|
|
|
|
- name: docker compose build (~8-10 min first time; cached after)
|
|
# See deploy-vibevoice.yaml for the rationale — same filter pattern.
|
|
shell: |
|
|
set -o pipefail
|
|
cd {{ compose_dir }} && docker compose build --progress=plain 2>&1 \
|
|
| grep -vE '^#[0-9]+ [0-9.]+ (Downloading|Collecting|Requirement|Using cached|Installing collected|Successfully (installed|built)|Saved /|━|Resolved|Prepared|Built)'
|
|
|
|
- name: docker compose up -d
|
|
shell: cd {{ compose_dir }} && docker compose up -d
|
|
|
|
- name: Wait for /api/model-info to report loaded:true (allow ~15 min for model download + warmup)
|
|
# The devnen wrapper has no /health endpoint. /api/model-info returns
|
|
# `{"loaded":true,...}` only after the model finishes loading, so it
|
|
# doubles as a liveness + ready probe.
|
|
shell: |
|
|
for i in $(seq 1 180); do
|
|
curl -sf --max-time 3 http://localhost:{{ host_port }}/api/model-info \
|
|
| grep -q '"loaded":true' && exit 0
|
|
sleep 5
|
|
done
|
|
exit 1
|
|
changed_when: "false"
|
|
|
|
verify:
|
|
- name: /api/model-info reports loaded:true
|
|
shell: curl -sf http://localhost:{{ host_port }}/api/model-info | grep -q '"loaded":true'
|
|
changed_when: "false"
|
|
|
|
- name: /v1/audio/voices returns the wrapper's status:ok + voices list
|
|
# Devnen's response shape is `{"status":"ok","voices":["Abigail.wav",...]}`
|
|
# — voices is an array of files in the predefined-voices dir. Assert
|
|
# both fields rather than greping for any one voice name (the seed
|
|
# set could change with upstream).
|
|
shell: |
|
|
curl -sf http://localhost:{{ host_port }}/v1/audio/voices \
|
|
| python3 -c "import json,sys; d=json.load(sys.stdin); assert d.get('status')=='ok' and isinstance(d.get('voices'), list)"
|
|
changed_when: "false"
|
|
|
|
- name: Container is running
|
|
shell: docker inspect chatterbox --format '{{.State.Status}}' | grep -q running
|
|
changed_when: "false"
|