# Kyutai TTS — 1.6B / 2B-class streaming TTS from Kyutai (the Moshi /
# Mimi team), trained on 2.5M hours. 220 ms latency in solo setup; up
# to 32 simultaneous streams under 350 ms on an L40-class GPU.
#
# Served via the NillPointer/Kyutai-TTS-Server community wrapper —
# Kyutai's official deployment is Rust + websockets only, which doesn't
# fit our OpenAI-compat fleet. The community wrapper bridges Kyutai's
# native streaming to the OpenAI /v1/audio/speech contract.
#
# Why this stack alongside the existing TTS:
#   * Kyutai's claim is the lowest streaming latency in this size
#     class (220 ms on a single GPU). Worth bench-comparing against
#     Chatterbox (~1.2 s) and Fish S2-Pro (~150 ms claimed).
#   * Trained on 2.5M hours — a different scaling regime from the
#     others (CosyVoice 5k hrs, Fish 10M hrs).
#   * Designed for full-duplex dialogue (Moshi heritage) — may surface
#     conversational quality the others lack.
#
# All tunables live in .env — edit that, not this file.

services:
  kyutai-tts:
    image: local/kyutai-tts:${KYUTAI_TTS_TAG}
    build:
      context: https://github.com/NillPointer/Kyutai-TTS-Server.git#${KYUTAI_TTS_SHA}
      dockerfile: Dockerfile
    container_name: kyutai-tts
    restart: unless-stopped
    runtime: nvidia
    ports:
      - "${KYUTAI_TTS_BIND:-0.0.0.0}:${KYUTAI_TTS_PORT}:8000"
    environment:
      - NVIDIA_VISIBLE_DEVICES=${KYUTAI_TTS_GPU_DEVICES:-0}
      # Kyutai's en/fr bilingual model on HF. Switch to a different
      # checkpoint via .env without rebuilding.
      - KYUTAI_MODEL=${KYUTAI_TTS_MODEL:-kyutai/tts-1.6b-en_fr}
      - HF_HOME=/app/hf_cache
    volumes:
      - ${KYUTAI_TTS_CACHE_DIR}:/app/hf_cache
      - ${KYUTAI_TTS_VOICES_DIR}:/app/voices:ro
    healthcheck:
      # NillPointer wrapper's actual endpoints (verified at runtime via
      # /openapi.json): just /health (root) and /v1/audio/speech (POST).
      # No /v1/models, no /v1/audio/voices — those 404. /health is the
      # liveness signal. 127.0.0.1 explicit to dodge IPv4/IPv6 localhost
      # race.
      test: ["CMD-SHELL", "python3 -c \"import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5).status==200 else 1)\""]
      interval: 30s
      timeout: 10s
      retries: 3
      # First boot pulls the Kyutai checkpoint (~3-6 GB) + warms.
      start_period: 600s
    labels:
      - homepage.group=AI Systems
      - homepage.name=Kyutai TTS
      - homepage.icon=mdi-radio-tower
      - homepage.description=Ultra-low-latency streaming TTS — 220 ms on solo GPU, EN/FR (irv-ml1)
      - homepage.href=http://10.100.79.3:${KYUTAI_TTS_PORT}