Add compose-based backend runtime on python 3.14

README.md

@@ -9,8 +9,17 @@ Two separate Python packages live here:
 
 The repo also includes a Gitea Actions workflow at `.gitea/workflows/ci.yml` that tests and builds both packages on pushes to `main` and pull requests.
 
-## Backend setup
+## Docker backend (no image build)
 
+Run the backend directly from an official Python image without creating a Dockerfile:
+
+```bash
+docker compose up backend
+```
+
+This uses `python:3.14-slim`, installs `ffmpeg` and `openai-whisper` at container startup, mounts this repo into the container, and serves the API on `http://localhost:8000`.
+
+## Backend setup
 ```bash
 cd backend
 pip install -e .
@@ -50,3 +59,4 @@ whisper-remote ./audio.mp3 --model base --language en --output-format txt
 - backend-side cleanup of uploaded and generated files after each request
 
 By default the CLI prints the returned transcript to stdout. Use `--to-file` to save it locally.
+

docker-compose.yml

@@ -0,0 +1,22 @@
+services:
+  backend:
+    image: python:3.14-slim
+    working_dir: /app/backend
+    ports:
+      - "8000:8000"
+    volumes:
+      - ./:/app
+      - whisper_cache:/root/.cache
+    environment:
+      - PYTHONUNBUFFERED=1
+    command: >-
+      sh -lc "
+      apt-get update
+      && apt-get install -y --no-install-recommends ffmpeg
+      && rm -rf /var/lib/apt/lists/*
+      && pip install --no-cache-dir -e . openai-whisper
+      && uvicorn server:app --app-dir src --host 0.0.0.0 --port 8000
+      "
+
+volumes:
+  whisper_cache: