Skip to main content

08-minuspod.md

kstack: book: Centerpoint Home Lab chapter: Utilities page: MinusPod tags: [minuspod, podcasts, transcription, whisper, ai, cuda]

Overview

emptyMinusPod is an AI-powered podcast manager and transcriber. It manages podcast feeds, downloads episodes, and transcribes audio using a local Whisper model. Summaries and notes are generated via an LLM (Qwen3:14b) through the Ollama API. The container runs with NVIDIA GPU access (RTX 5080) for accelerated Whisper inference. Internal-only access. Episode data is retained for 180 days.

Access

Type URL Auth Internal https://minuspod.home.local MinusPod own auth (Step-CA TLS)

No external route — LAN access only.

Configuration

Image: ttlequals0/minuspod:2.1.9
Runtime: CUDA 12.9 / NVIDIA runtime (RTX 5080)

Key Environment Variables

Variable Value / Notes BASE_URL https://minuspod.home.local WHISPER_BACKEND local WHISPER_DEVICE cuda WHISPER_MODEL medium LLM_PROVIDER ollama OPENAI_BASE_URL https://ollama.home.local/v1 OPENAI_MODEL qwen3:14b OPENAI_API_KEY REDACTED RETENTION_PERIOD 4320 hours (180 days) MINUSPOD_TRUSTED_PROXY_COUNT 1 NVIDIA_VISIBLE_DEVICES all NVIDIA_DRIVER_CAPABILITIES compute,utility

Traefik Labels

traefik.http.routers.minuspod.rule: Host(`minuspod.home.local`)
traefik.http.routers.minuspod.entrypoints: websecure
traefik.http.routers.minuspod.tls.certresolver: step-ca
traefik.http.services.minuspod.loadbalancer.server.port: 8000

Volumes / Bind Mounts

Host Path Container Path Purpose /home/jeeves/dockers/minuspod/data /app/data Episode database and downloads

Note: The data directory is under /home/jeeves/dockers/ (not docker/) — this is the actual bind mount path as confirmed by docker inspect.

AI Integration

MinusPod uses two AI components:

Component Model Transport Purpose Whisper medium Local CUDA inference (RTX 5080) Audio transcription Qwen3:14b qwen3:14b Ollama API at ollama.home.local/v1 Summaries and notes

OPENAI_BASE_URL points to the internal Ollama instance (which exposes an OpenAI-compatible API). The OPENAI_MODEL is qwen3:14b — this model must be present in Ollama. Verify with docker exec ollama ollama list.

Notes / Gotchas

    The Whisper medium model on CUDA provides a good balance of speed and accuracy. Upgrade to large-v3 if accuracy is more important than speed (uses more VRAM). The RTX 5080 has 16GB GDDR7 — ample for either. RETENTION_PERIOD=4320 hours = 180 days. Episodes older than this are automatically removed. Adjust if long-term episode storage is needed. MINUSPOD_TRUSTED_PROXY_COUNT=1 tells MinusPod to trust one level of proxy headers (Traefik) for correct IP and protocol detection. The bind mount path is /home/jeeves/dockers/minuspod/data (note: dockers, not docker). This is different from the convention used by most other stacks. Ensure qwen3:14b is loaded in Ollama before enabling LLM summaries: 
    docker exec ollama ollama pull qwen3:14b

    Last Updated: 2026-06-17

    Back to top