Story AI on Android
The Story AI choice belongs to the phone: pick once and every campaign on your device world uses those services, new or old. Who runs a particular table is still chosen in its campaign creator. The Story AI button on the home screen reopens the screen, and inside a campaign the Settings tab shows the device's choice.
No AI
No AI. A person runs the table from the DM seat, on this phone or on another device that joined, with the console, the binder and the map tools. Everything else, dice, sheets, initiative, maps, voice, is the same.
Your OpenAI API key
- Create a provider key with billing available, then paste it into Story AI.
- List the key's models and choose the Dungeon Master model. Choose a cheaper utility model if you want; leaving it blank uses the story model. Existing selections are kept when you return.
- Save. The server inside the app keeps the key and uses it for campaigns on this phone. A blank key field keeps it. Picture and transcription models are selected from the key's list when there is one clear recommendation; otherwise finish choosing them in Admin, Images or Speech.
The same key can read the story aloud if you select that option and a narration model is available. Storytelling and read-aloud are separate services; the Your world plays with card summarises both, plus pictures.
The phone sends the packed story, sheets and scene to the provider; it does no language-model work. Usage is billed to your key. Turn pictures off per campaign in Settings, Story AI if you prefer. See OpenAI and compatible keys and What leaves your machine.
Why only two doors
A local model needs a computer with at least 16 GB of graphics memory, and an agent program (Codex, Grok Build, Claude Code, opencode) is something a computer runs. Both doors exist on the desktop app. A phone that joins a desktop-hosted world or a self-hosted server gets whatever narrator that host has, so a group with one capable computer can still play from phones with a fully local AI.
Other backends
OpenRouter, a llama.cpp or Ollama server on another machine, ComfyUI at an address on your network, and narration (Kokoro, or any OpenAI-compatible speech server) are configured through the world's admin panel (account menu, Admin) on the phone, the same as on a self-hosted server: a text model section with a backend URL, model and key, and image and speech sections. The Story AI screen covers the common case; the admin panel covers the rest. A human Dungeon Master's dictation uses the phone's own speech recognizer.