Dockerfile

# Studio Server - AI-powered studio utilities for video production
# Supports: TTS (Qwen3-TTS), Face Embedding (InsightFace), Transcription (Whisper)

FROM pytorch/pytorch:2.5.1-cuda12.4-cudnn9-runtime

WORKDIR /app

# Install system dependencies (including build tools for insightface)
RUN apt-get update && apt-get install -y --no-install-recommends \
    libsndfile1 \
    ffmpeg \
    sox \
    libsox-dev \
    libgl1-mesa-glx \
    libglib2.0-0 \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application
COPY backends/ ./backends/
COPY server.py .

# Environment variables - defaults
ENV TTS_BACKEND=qwen3-tts
ENV FACE_ENABLED=true
ENV FACE_BACKEND=insightface
ENV TRANSCRIPTION_ENABLED=true
ENV TRANSCRIPTION_BACKEND=whisper

# Expose port
EXPOSE 8000

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=300s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"

# Run server
CMD ["python", "server.py"]