add a simple python fastapi server to serve whisper models for speech-to-text and piper for text-to-speech

audio_server/Containerfile

@@ -0,0 +1,19 @@
+FROM python:3.14.4-slim AS builder
+
+WORKDIR /app
+COPY pyproject.toml requirements.txt ./
+COPY src src
+
+RUN pip wheel --no-cache-dir --no-deps --wheel-dir wheels .
+
+FROM python:3.14.4-slim AS runner
+
+COPY --from=builder /app/wheels /wheels
+RUN pip install --no-cache /wheels/* && rm -rf /wheels
+RUN apt update
+RUN apt -y install ffmpeg
+
+WORKDIR /app
+
+EXPOSE 8000
+CMD ["uvicorn", "audio_server:app", "--host", "0.0.0.0", "--port", "8000"]