Dockerfile

# AmaniQuery VibeVoice - Hugging Face Spaces Dockerfile
# Dedicated TTS service using Microsoft VibeVoice model

FROM python:3.11-slim AS base

ARG CACHEBUST=2025-12-16

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PYTHONPATH=/app \
    PORT=7860 \
    HF_HOME=/app/models

# Install system dependencies for audio processing
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    curl \
    build-essential \
    ffmpeg \
    libsndfile1 \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Copy requirements for VibeVoice
COPY requirements.txt ./
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir torch torchaudio --index-url https://download.pytorch.org/whl/cpu && \
    pip install --no-cache-dir -r requirements.txt

# Pre-download VibeVoice model
RUN python -c "from huggingface_hub import snapshot_download; snapshot_download('microsoft/VibeVoice-Realtime-0.5B')"

# Copy VibeVoice library and app
COPY vibevoice/ ./vibevoice/
COPY app.py ./

# Create necessary directories
RUN mkdir -p /app/models /app/cache && \
    useradd --create-home --shell /bin/bash app && \
    chown -R app:app /app

USER app

EXPOSE ${PORT}

HEALTHCHECK --interval=30s --timeout=30s --start-period=120s --retries=3 \
    CMD curl -f http://localhost:${PORT}/health || exit 1

# Default voice configuration
ENV VIBEVOICE_DEVICE=cpu \
    VIBEVOICE_VOICE=Wayne \
    VIBEVOICE_CFG_SCALE=1.5

CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]