The open-source AI voice studio. Clone, dictate, create.
feat: add Docker + web deployment support
Claudio Casaleedfc6e99fefe
diff --git a/.dockerignore b/.dockerignorenew file mode 100644index 00000000..e0c4637b--- /dev/null+++ b/.dockerignore@@ -0,0 +1,46 @@+# Version control+.git+.github+.gitignore++# Desktop-only (not needed in web container)+tauri/+landing/+docs/+mlx-test/+scripts/++# Dependencies & build artifacts (rebuilt in Docker)+node_modules/+__pycache__/+*.pyc+*.pyo+*.egg-info/+dist/+build/+*.spec++# Data (will be bind-mounted)+data/+backend/data/++# IDE & OS+.vscode/+.idea/+*.swp+*.swo+.DS_Store+Thumbs.db++# Config files not needed in container+biome.json+.biomeignore+.bumpversion.cfg+.npmrc+Makefile+CHANGELOG.md+CONTRIBUTING.md+SECURITY.md+LICENSE+README.md+backend/README.mddiff --git a/Dockerfile b/Dockerfilenew file mode 100644index 00000000..4705f98c--- /dev/null+++ b/Dockerfile@@ -0,0 +1,79 @@+# ============================================================+# Voicebox — Local TTS Server with Web UI (CPU)+# 3-stage build: Frontend → Python deps → Runtime+# ============================================================++# === Stage 1: Build frontend ===+FROM oven/bun:1 AS frontend++WORKDIR /build++# Copy workspace config and frontend source+COPY package.json bun.lock ./+COPY app/ ./app/+COPY web/ ./web/++# Strip workspaces not needed for web build, and fix trailing comma+RUN sed -i '/"tauri"/d; /"landing"/d' package.json && \+ sed -i -z 's/,\n ]/\n ]/' package.json+RUN bun install --no-save+# Build frontend (skip tsc — upstream has pre-existing type errors)+RUN cd web && bunx --bun vite build+++# === Stage 2: Build Python dependencies ===+FROM python:3.11-slim AS backend-builder++WORKDIR /build++RUN apt-get update && apt-get install -y --no-install-recommends \+ git \+ build-essential \+ && rm -rf /var/lib/apt/lists/*++COPY backend/requirements.txt .+RUN pip install --no-cache-dir --prefix=/install -r requirements.txt+RUN pip install --no-cache-dir --prefix=/install \+ git+https://github.com/QwenLM/Qwen3-TTS.git+++# === Stage 3: Runtime ===+FROM python:3.11-slim++# Create non-root user for security+RUN groupadd -r voicebox && \+ useradd -r -g voicebox -m -s /bin/bash voicebox++WORKDIR /app++# Install only runtime system dependencies+RUN apt-get update && apt-get install -y --no-install-recommends \+ ffmpeg \+ curl \+ && rm -rf /var/lib/apt/lists/*++# Copy installed Python packages from builder stage+COPY --from=backend-builder /install /usr/local++# Copy backend application code+COPY --chown=voicebox:voicebox backend/ /app/backend/++# Copy built frontend from frontend stage+COPY --from=frontend --chown=voicebox:voicebox /build/web/dist /app/frontend/++# Create data directories owned by non-root user+RUN mkdir -p /app/data/generations /app/data/profiles /app/data/cache \+ && chown -R voicebox:voicebox /app/data++# Switch to non-root user+USER voicebox++# Expose the API port+EXPOSE 17493++# Health check — auto-restart if the server hangs+HEALTHCHECK --interval=30s --timeout=10s --retries=3 --start-period=60s \+ CMD curl -f http://localhost:17493/health || exit 1++# Start the FastAPI server+CMD ["uvicorn", "backend.main:app", "--host", "0.0.0.0", "--port", "17493"]diff --git a/docker-compose.yml b/docker-compose.ymlnew file mode 100644index 00000000..0a6fe366--- /dev/null+++ b/docker-compose.yml@@ -0,0 +1,42 @@+services:+ voicebox:+ build: .+ container_name: voicebox+ restart: unless-stopped++ ports:+ # Bind to localhost only for security+ - "127.0.0.1:17493:17493"++ volumes:+ # Bind-mount for generated audio (customize the host path as needed)+ # Host side: ./output/+ # Container side: /app/data/generations/+ - ./output:/app/data/generations++ # Named volume for profiles, DB, cache (persists across container restarts)+ - voicebox-data:/app/data++ # HuggingFace model cache (so models aren't re-downloaded on rebuild)+ - huggingface-cache:/home/voicebox/.cache/huggingface++ environment:+ - TTS_MODE=local+ - LOG_LEVEL=info++ networks:+ - voicebox-net++ deploy:+ resources:+ limits:+ cpus: '4'+ memory: 8G++networks:+ voicebox-net:+ driver: bridge++volumes:+ voicebox-data:+ huggingface-cache: