vh
4549d241a7
Three TTS additions to round out coverage on irv-ml1, each filling a
distinct niche the existing slate doesn't own.
Final coverage matrix (all on irv-ml1):
Kokoro — low-latency English, fixed voice library, ~300ms TTFA
Chatterbox Turbo — low-latency English w/ voice cloning + paralinguistic tags
IndexTTS-2 — English voice cloning + emotion vector / text control
Qwen3-TTS-1.7B-Base — high-quality English voice cloning
CosyVoice 3 — multilingual (Chinese-leaning)
VibeVoice 1.5B — long-form / multi-speaker dialogue
stacks/kokoro:
- port 8193, GPU device 0 (3090)
- pulls ghcr.io/remsky/kokoro-fastapi-gpu:v0.2.4-master (no Dockerfile,
no first-run model download — models baked in)
- 60+ built-in voices, OpenAI-compat with stream=true over chunked HTTP
- Apache-2.0 weights + code, ~1 GB VRAM
stacks/vibevoice:
- port 8194, GPU device 1 (A6000 — for 7B headroom)
- builds groxaxo/VibeVoice-FastAPI1 (more current fork of ncoder-ai)
pinned to 7614c469a145
- default model microsoft/VibeVoice-1.5B (~7 GB bf16 VRAM); env var
swap to rsxdalv/VibeVoice-Large (7B) or FabioSarracino/VibeVoice-Large-Q8
- multi-speaker dialogue via /v1/vibevoice/generate with Speaker N: format
- long-form niche only — not low-latency
stacks/chatterbox:
- port 8196, GPU device 0 (3090)
- builds devnen/Chatterbox-TTS-Server (most active Turbo-supporting wrapper)
- default model ResembleAI/chatterbox-turbo (~2.5 GB fp16, ~75ms latency)
- paralinguistic tags inline ([laugh] [whisper] etc) — different shape
from IndexTTS-2's emotion vector; fills the speed+cloning niche
Kokoro/IndexTTS don't cover together
- mandatory PerTh watermark on outputs (Resemble policy)
Three matching playbooks under playbooks/deploy-{kokoro,vibevoice,
chatterbox}.yaml. All idempotent, creates-/when-gated.
Cold-deploy disk on /worktank/: ~7 GB Kokoro + ~19 GB VibeVoice 1.5B
+ ~12 GB Chatterbox = ~38 GB total. VRAM concurrent: ~10-11 GB across
both GPUs.
Skipped from the original four-stack proposal: VibeVoice Realtime
(overlaps Kokoro's niche; Kokoro wins on latency, license, and not
needing a build).
89 lines
3.1 KiB
YAML
89 lines
3.1 KiB
YAML
# Deploy VibeVoice 1.5B (long-form) to irv-ml1.
|
|
#
|
|
# Builds the image locally from groxaxo/VibeVoice-FastAPI1 via docker
|
|
# buildx git URL context. ~12 min cold build (CUDA 12.8 + torch 2.8 +
|
|
# flash-attn). First start downloads VibeVoice-1.5B (~7 GB) into the
|
|
# bind-mounted HF cache. Generous /healthz wait deadline accommodates
|
|
# both.
|
|
#
|
|
# Usage:
|
|
# scripts/elway irv-ml1 --playbook playbooks/deploy-vibevoice.yaml
|
|
#
|
|
# Idempotent — every step is creates-/when-gated; rerun is safe.
|
|
|
|
vars:
|
|
compose_dir: /opt/docker/compose/vibevoice
|
|
voices_dir: /worktank/vibevoice/voices
|
|
cache_dir: /worktank/vibevoice/cache
|
|
host_port: "8194"
|
|
|
|
steps:
|
|
# ── host-side dirs ──────────────────────────────────────────────────
|
|
|
|
- name: Ensure /worktank/vibevoice root exists (one-time, sudo)
|
|
shell: mkdir -p /worktank/vibevoice
|
|
sudo: true
|
|
creates: /worktank/vibevoice
|
|
|
|
- name: Chown /worktank/vibevoice to lkraven
|
|
shell: chown lkraven:lkraven /worktank/vibevoice
|
|
sudo: true
|
|
when: '[ "$(stat -c %U /worktank/vibevoice)" != lkraven ]'
|
|
|
|
- name: Ensure voices dir exists
|
|
shell: mkdir -p {{ voices_dir }}
|
|
creates: "{{ voices_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/vibevoice/compose.yaml
|
|
dest: "{{ compose_dir }}/compose.yaml"
|
|
mode: "0644"
|
|
|
|
- name: Seed .env from template (only if absent)
|
|
upload:
|
|
src: stacks/vibevoice/.env.example
|
|
dest: "{{ compose_dir }}/.env"
|
|
mode: "0644"
|
|
when: "[ ! -f {{ compose_dir }}/.env ]"
|
|
|
|
# ── build + bring up ────────────────────────────────────────────────
|
|
|
|
- name: docker compose build (~12 min first time; cached after)
|
|
shell: cd {{ compose_dir }} && docker compose build
|
|
|
|
- name: docker compose up -d
|
|
shell: cd {{ compose_dir }} && docker compose up -d
|
|
|
|
- name: Wait for /health to respond (allow ~20 min for model download + warmup)
|
|
shell: |
|
|
for i in $(seq 1 240); 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: /v1/audio/voices returns valid JSON
|
|
shell: curl -sf http://localhost:{{ host_port }}/v1/audio/voices | grep -q '"voices"\|"voice"\|alloy\|Carter'
|
|
changed_when: "false"
|
|
|
|
- name: Container is running
|
|
shell: docker inspect vibevoice --format '{{.State.Status}}' | grep -q running
|
|
changed_when: "false"
|