vh
c5ab99e74f
Wrapper only enumerates one voice directory (settings.voices_dir, default /app/api/src/voices/v1_0 — inside the container's writable layer, not bind-mounted). Override via VOICES_DIR=/app/user_voices (host bind mount) and add a command shim that cp -r's built-ins from the in-image v1_0 into user_voices on every start. Built-ins re-seed fresh from the image (so upgrades that add voices propagate); custom .pt files in user_voices are preserved (cp -r is additive). Also adds scripts/blend_kokoro_voice.py + a playbook around it that mirrors the wrapper's request-time voice="a(w)+b(w)" math but writes the result as a named .pt to user_voices, making it discoverable via GET /v1/audio/voices and persistent across recreate. Defaults to athena = af_bella(2)+af_aoede(1) normalized.
69 lines
3.3 KiB
YAML
69 lines
3.3 KiB
YAML
# Kokoro-82M served via remsky/Kokoro-FastAPI — the de-facto OpenAI-
|
|
# compatible wrapper for hexgrad's Kokoro-82M TTS.
|
|
#
|
|
# Why this stack exists alongside the other TTS:
|
|
# * Lowest-latency English in the fleet — ~300 ms TTFA on GPU,
|
|
# RTF 35-100x on a 4060 Ti class card.
|
|
# * Native streaming via OpenAI-compat `stream=true` over HTTP
|
|
# chunked transfer (Kokoro's KPipeline is a per-phrase generator).
|
|
# * Apache-2.0 weights + code; ~1 GB VRAM at fp16.
|
|
# * 60+ built-in voices (no cloning — for that use IndexTTS-2 or
|
|
# Chatterbox Turbo). Voices combinable via "voice(weight)+..." syntax.
|
|
#
|
|
# Image is a published GHCR build; no Dockerfile to maintain. Models
|
|
# baked into the image, no first-run download. Deploy is a pull + up.
|
|
#
|
|
# All tunables live in .env — edit that, not this file.
|
|
|
|
services:
|
|
kokoro:
|
|
image: ghcr.io/remsky/kokoro-fastapi-${KOKORO_VARIANT:-cpu}:${KOKORO_TAG}
|
|
container_name: kokoro
|
|
restart: unless-stopped
|
|
# Only request GPU runtime when running the GPU variant. Toggling
|
|
# `runtime: nvidia` from a YAML knob isn't possible directly; we
|
|
# accomplish it by routing nvidia-only fields through the
|
|
# NVIDIA_VISIBLE_DEVICES env var instead. The cpu variant ignores
|
|
# that env var harmlessly; the gpu variant honors it.
|
|
ports:
|
|
- "${KOKORO_BIND:-0.0.0.0}:${KOKORO_PORT}:8880"
|
|
# Persistent custom voices: the wrapper only enumerates one voice
|
|
# directory (controlled by VOICES_DIR; default in-image is
|
|
# /app/api/src/voices/v1_0 which is NOT bind-mounted). We point it
|
|
# at /app/user_voices (which IS host-bind-mounted) and seed the
|
|
# built-ins into it on every container start. Custom voices written
|
|
# by scripts/blend_kokoro_voice.py land directly on the host bind
|
|
# mount and survive `up --force-recreate` and image upgrade.
|
|
# `cp -r` (no `-n`): always refresh built-ins from the image so
|
|
# upgrades that add/change built-in voicepacks propagate.
|
|
# Custom-named .pt files in user_voices that don't exist in v1_0
|
|
# are NOT touched (cp -r only copies entries from src).
|
|
command: ["/bin/bash", "-c", "cp -r /app/api/src/voices/v1_0/. /app/user_voices/ && exec ./entrypoint.sh"]
|
|
environment:
|
|
- NVIDIA_VISIBLE_DEVICES=${KOKORO_GPU_DEVICES:-}
|
|
- USE_GPU=${KOKORO_USE_GPU:-false}
|
|
- API_LOG_LEVEL=${KOKORO_LOG_LEVEL:-INFO}
|
|
- VOICES_DIR=/app/user_voices
|
|
volumes:
|
|
# Host-bind-mounted voice directory. Hosts both the image's
|
|
# built-ins (re-seeded on each container start by the command
|
|
# shim above) and any custom voices created via the blend
|
|
# script. Must be chowned to uid 1001 (appuser inside the
|
|
# container) on the host so the shim's cp can write — handled
|
|
# by playbooks/deploy-kokoro.yaml.
|
|
- ${KOKORO_USER_VOICES_DIR}:/app/user_voices
|
|
healthcheck:
|
|
# The image is python-based with curl available. /v1/audio/voices
|
|
# is a no-arg GET that exercises the full API path.
|
|
test: ["CMD-SHELL", "curl -fsS -o /dev/null http://localhost:8880/v1/audio/voices || exit 1"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 90s
|
|
labels:
|
|
- homepage.group=AI Systems
|
|
- homepage.name=Kokoro
|
|
- homepage.icon=mdi-microphone-message
|
|
- homepage.description=Low-latency English TTS w/ streaming (irv-ml1)
|
|
- homepage.href=http://10.100.79.3:${KOKORO_PORT}
|