# Piper neural-TTS HTTP server — the read-aloud backend Petal proxies to.
#
# One image, any voice: the model is named by PIPER_VOICE at runtime and
# downloaded into the shared /voices volume on first start. Each Piper server
# loads exactly one voice, so a new language is a new service in
# docker-compose.yml, not a new image (English and Chinese today; pt-PT lands
# with the Portuguese pair).
#
# python:3.12 rather than 3.13 — piper-tts pulls onnxruntime, whose wheel
# coverage for 3.13 still lags.
FROM python:3.12-slim

RUN pip install --no-cache-dir "piper-tts[http]" \
 && useradd -m -u 10002 piper

ENV PIPER_VOICE=en_US-amy-medium \
    PIPER_DATA_DIR=/voices \
    PIPER_PORT=5000

RUN mkdir -p /voices && chown piper:piper /voices
VOLUME ["/voices"]

COPY entrypoint.sh /usr/local/bin/entrypoint.sh
RUN chmod +x /usr/local/bin/entrypoint.sh

USER piper
EXPOSE 5000

# The server has no dedicated health route, so synthesizing a single word is
# the honest check: it proves the model loaded, not just that a port is open.
HEALTHCHECK --interval=60s --timeout=20s --start-period=180s --retries=3 \
  CMD python -c "import os,urllib.request,json; \
urllib.request.urlopen(urllib.request.Request('http://127.0.0.1:'+os.environ['PIPER_PORT']+'/', \
data=json.dumps({'text':'ok','voice':os.environ['PIPER_VOICE']}).encode(), \
headers={'Content-Type':'application/json'}), timeout=15).read(1)"

ENTRYPOINT ["/usr/local/bin/entrypoint.sh"]