stacks/index-tts: own FastAPI wrapper for IndexTTS-2 + deploy playbook

Adds a third TTS to the irv-ml1 fleet. IndexTTS-2 is Bilibili's
emotion-controllable zero-shot TTS (paper 2506.21619). Distinguishing
capability vs the existing two: timbre and emotion are disentangled —
clone a voice's timbre from one reference and the emotion from a
different reference, OR set emotion via 8-vector, OR derive it from a
text description. Neither CosyVoice 3 nor Qwen3-TTS-1.7B-Base does
this cleanly in English.

Wrapper is owned end-to-end (~150 lines in app.py) — the only existing
FastAPI fork (csllpr/index-tts-fastapi) targets v1 and is a dormant
single-commit repo. Upstream IndexTTS-2 ships only a Gradio webui.

Layout follows the qwen3-tts pattern:
  stacks/index-tts/
    Dockerfile           — CUDA 12.8 base, IndexTTS pinned to a SHA
    app.py               — FastAPI: POST /v1/audio/speech + /v1/voices
    entrypoint.sh        — one-time HF snapshot_download of the weights
    compose.yaml         — env-driven, GPU pinning support, bind mounts
    .env.example         — port 8192, fp16, paths
    README.md            — API examples + comparison vs the other TTS
  playbooks/deploy-index-tts.yaml  — elway playbook for irv-ml1

Voice and emotion libraries are flat host dirs of WAVs, bind-mounted.
Drop a new <name>.wav and /v1/voices picks it up immediately.

License caveat: IndexTTS-2 weights ship under a custom Bilibili
license (free at our scale, not OSI-open). README documents it.

playbooks/deploy-index-tts.yaml

@@ -0,0 +1,117 @@
+# Deploy IndexTTS-2 (https://github.com/index-tts/index-tts) to irv-ml1
+# behind our own FastAPI wrapper (stacks/index-tts/app.py).
+#
+# Builds the image locally from the Dockerfile in stacks/index-tts/
+# (which clones the upstream IndexTTS-2 repo at a pinned SHA inside
+# the build), stages app.py + entrypoint.sh + compose + .env under
+# /opt/docker/compose/index-tts/, brings it up, waits for /healthz,
+# and verifies the API surface.
+#
+# First run is slow: ~5-10 min for the docker build (CUDA torch + the
+# IndexTTS pinned-deps tail) plus ~5-7 GB model download from HF on
+# first container start (entrypoint.sh handles that). The healthz wait
+# below allows up to 15 min total.
+#
+# Usage:
+#   scripts/elway irv-ml1 --playbook playbooks/deploy-index-tts.yaml
+#
+# Idempotent — every step is creates-/when-gated; rerun is safe.
+
+vars:
+  compose_dir: /opt/docker/compose/index-tts
+  cache_dir: /worktank/index-tts/cache
+  voices_dir: /worktank/index-tts/voices
+  emotions_dir: /worktank/index-tts/emotions
+  host_port: "8192"
+
+steps:
+  # ── host-side dirs ──────────────────────────────────────────────────
+
+  - name: Ensure /worktank/index-tts root exists (one-time, sudo)
+    shell: mkdir -p /worktank/index-tts
+    sudo: true
+    creates: /worktank/index-tts
+
+  - name: Chown /worktank/index-tts to lkraven
+    shell: chown lkraven:lkraven /worktank/index-tts
+    sudo: true
+    when: '[ "$(stat -c %U /worktank/index-tts)" != lkraven ]'
+
+  - name: Ensure cache dir exists
+    shell: mkdir -p {{ cache_dir }}
+    creates: "{{ cache_dir }}"
+
+  - name: Ensure voices dir exists
+    shell: mkdir -p {{ voices_dir }}
+    creates: "{{ voices_dir }}"
+
+  - name: Ensure emotions dir exists
+    shell: mkdir -p {{ emotions_dir }}
+    creates: "{{ emotions_dir }}"
+
+  - name: Ensure compose dir exists
+    shell: mkdir -p {{ compose_dir }}
+    creates: "{{ compose_dir }}"
+
+  # ── deploy build context (compose, env, dockerfile, app, entrypoint) ──
+
+  - name: Upload compose.yaml
+    upload:
+      src: stacks/index-tts/compose.yaml
+      dest: "{{ compose_dir }}/compose.yaml"
+      mode: "0644"
+
+  - name: Upload Dockerfile
+    upload:
+      src: stacks/index-tts/Dockerfile
+      dest: "{{ compose_dir }}/Dockerfile"
+      mode: "0644"
+
+  - name: Upload app.py
+    upload:
+      src: stacks/index-tts/app.py
+      dest: "{{ compose_dir }}/app.py"
+      mode: "0644"
+
+  - name: Upload entrypoint.sh
+    upload:
+      src: stacks/index-tts/entrypoint.sh
+      dest: "{{ compose_dir }}/entrypoint.sh"
+      mode: "0755"
+
+  - name: Seed .env from template (only if absent)
+    upload:
+      src: stacks/index-tts/.env.example
+      dest: "{{ compose_dir }}/.env"
+      mode: "0644"
+    when: "[ ! -f {{ compose_dir }}/.env ]"
+
+  # ── build + bring up ────────────────────────────────────────────────
+
+  - name: docker compose build (~5-10 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 /healthz to respond (allow ~15 min for model download)
+    shell: |
+      for i in $(seq 1 180); do
+        curl -sf -o /dev/null --max-time 3 http://localhost:{{ host_port }}/healthz && exit 0
+        sleep 5
+      done
+      exit 1
+    changed_when: "false"
+
+verify:
+  - name: /healthz returns 200
+    shell: curl -sf -o /dev/null http://localhost:{{ host_port }}/healthz
+    changed_when: "false"
+
+  - name: /v1/voices returns a JSON object with 'voices' and 'emotions' keys
+    shell: curl -sf http://localhost:{{ host_port }}/v1/voices | grep -q '"voices"'
+    changed_when: "false"
+
+  - name: Container is running
+    shell: docker inspect index-tts --format '{{.State.Status}}' | grep -q running
+    changed_when: "false"