# Quadlet unit: frank-tts (rootless, boot-persistent).
#
# Install path on dankclaw: ~/.config/containers/systemd/frank-tts.container
# Unit name: frank-tts.service (container name: frank-tts)
#
# WHAT IT IS. The fleet's one OpenAI-compatible speech endpoint: consumers
# (omp, OpenWebUI, open-notebook) POST /v1/audio/speech with voice=<name> and
# get audio in that cloned voice. A voice is a directory under
# /home/dank/voices holding reference.wav; the shim refuses any name without
# one (400 + the list that does exist) rather than narrating in a fallback
# voice nobody chose. The engine behind it is a separate decision —
# TTS_BACKEND in scripts/frank-tts.env picks between forwarding to an
# OpenAI-shaped upstream on host :8880 and running a local CLI binary per
# request.
#
# IMAGE. Built locally from dankclaw/voiceservice/Containerfile by
# deploy-remote.sh (build_compose_image), like loki/alloy: python 3.12-alpine
# pinned by digest + ffmpeg, app.py copied in, running as uid 10000.
# Pull=never and the localhost/ prefix are required — this host's quadlet
# path cannot resolve a locally built tag from local storage otherwise.
#
# NETWORK. Bridge (dankclaw_default), NOT host: nothing here needs a shared
# loopback namespace, and the comfyui/loki/authentik units are bridge too.
# Consequences both ways: consumers reach it on the published 7772, and the
# shim reaches the host-side TTS engine through host.containers.internal
# (never the LAN IP — a bridge netns cannot route to the host's own address
# for every bind shape, and the fleet's law is the gateway name). NOTE for
# whoever starts the :8880 engine: host.containers.internal reaches the host
# network namespace, so the engine must bind an address that namespace
# accepts; a 127.0.0.1-only bind is not it (the 2026-09-17 signal-relay hop
# needed the host LAN bind for the same reason).
#
# VOICES. /home/dank/voices is host state, never repo state, and is mounted
# READ-ONLY: this endpoint has no business writing voice packs. Because the
# container runs as uid 10000, the packs must be world-readable (644 files,
# 755 directories), which is how the pack builder writes them.
#
# NO GPU. The shim is a façade: audio conversion via ffmpeg on the CPU and,
# for the CLI backend, whatever CPU threads LLAMA_TTS_THREADS allows, at nice
# 19. No /dev/kfd, no /dev/dri, no keep-groups — unlike comfyui, whose unit
# carries them deliberately.
[Unit]
Description=frank-tts (cloned-voice OpenAI-compatible TTS facade)
After=network-online.target
Wants=network-online.target

[Container]
ContainerName=frank-tts
Image=localhost/franksdank/frank-tts:latest
Pull=never
Network=dankclaw_default
PublishPort=7772:7772
EnvironmentFile=/home/dank/serverAppConfigs/scripts/frank-tts.env
Volume=/home/dank/voices:/voices:ro
# The probe is a probe, not a voice test: /health answers 200 with the backend
# and the resolved voice list, so a mounted-but-empty /voices still reads
# healthy while a dead app does not. busybox wget ships in the alpine base;
# keep the command argument-only — the podman 5.x generator splits HealthCmd
# on spaces (see the comfyui unit for the quoting trap).
HealthCmd=wget --spider -q http://127.0.0.1:7772/health
HealthInterval=30s
HealthTimeout=10s
HealthRetries=3
HealthStartPeriod=30s

[Service]
Restart=always
RestartSec=10

[Install]
WantedBy=default.target