Dockerfile.gpu

# GPU-Accelerated Kokoro TTS Dockerfile
FROM nvidia/cuda:12.1.1-runtime-ubuntu22.04

# Environment variables
ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    HF_HOME=/root/.cache/huggingface \
    PORT=8880 \
    DEFAULT_VOICE=af_heart \
    DEBIAN_FRONTEND=noninteractive

# Install Python 3.10 and system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3.10 \
    python3.10-dev \
    python3-pip \
    espeak-ng \
    ffmpeg \
    libsndfile1 \
    curl \
    git \
    && rm -rf /var/lib/apt/lists/* \
    && ln -s /usr/bin/python3.10 /usr/bin/python

WORKDIR /app

# Copy requirements and install python packages with CUDA PyTorch
COPY requirements.txt .
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cu121 && \
    pip install --no-cache-dir -r requirements.txt

# Pre-download default weights into cache
RUN python -c "from kokoro import KPipeline; KPipeline(lang_code='a')"

# Copy application code
COPY app/ /app/app/

EXPOSE 8880

HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
    CMD curl -f http://localhost:${PORT}/health || exit 1

CMD ["sh", "-c", "uvicorn app.main:app --host 0.0.0.0 --port ${PORT}"]