tts_server/Dockerfile

FROM nvidia/cuda:11.8.0-runtime-ubuntu22.04

ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV COQUI_TTS_CACHE=/models
ENV TORCH_HOME=/models

WORKDIR /app

RUN printf 'deb http://archive.ubuntu.com/ubuntu jammy main universe\n\
deb http://archive.ubuntu.com/ubuntu jammy-updates main universe\n\
deb http://archive.ubuntu.com/ubuntu jammy-security main universe\n' > /etc/apt/sources.list

RUN apt-get update && apt-get install -y \
    python3 \
    python3-pip \
    git \
    ffmpeg \
    espeak-ng \
    libsndfile1 \
    && rm -rf /var/lib/apt/lists/*

RUN pip3 install --no-cache-dir --upgrade pip

# CUDA Torch (PINNED)
RUN pip3 install --no-cache-dir \
    torch==2.5.1+cu118 \
    torchvision==0.20.1+cu118 \
    torchaudio==2.5.1+cu118 \
    --index-url https://download.pytorch.org/whl/cu118

# Coqui TTS
RUN pip3 install --no-cache-dir \
    TTS[all]==0.22.0 \
    fastapi \
    uvicorn

# Transformers version compatible with XTTS
RUN pip3 install --no-cache-dir "transformers>=4.30.0,<4.32.0"

RUN mkdir -p /models /voices

EXPOSE 5002

VOLUME ["/models", "/voices"]

ENTRYPOINT ["python3", "-m", "uvicorn", "tts_server:app", "--host", "0.0.0.0", "--port", "5002"]