Narration, scene art and ambience

Three optional layers sit on top of the text: a voice that reads the Dungeon Master aloud, pictures painted for scenes and faces, and a bed of ambience and music. Each depends on a service the server has, and each fails soft: when the service is missing the layer stays off, or a placeholder stands in, and the session carries on.

Narration

With Narration on in the campaign's Settings tab, every Dungeon Master passage is read aloud in the campaign's narrator voice, picked from the voices the speech server lists (Kokoro offers ten; Heart, a warm female voice, is its default). Playback starts when the first audio chunk is ready; the rest streams in as it is generated. Each listener has their own mute, volume and replay in the voice dock, and a read-aloud button sits on every passage. Audio is generated once per passage and cached on the server; a passage that could not be read aloud says why. A slow speech request is retried once, with a timeout that grows with the passage, and a passage that has gone stale is skipped with a note rather than played late.

Browsers hold sound back until you click the page. When yours does, a Narration is waiting banner on the table counts what is held; one click plays the newest passage, and the older ones keep their replay buttons.

Every speaker can have a voice. The Narration and character voices group has the voice controls: the party, the cast and each kind of monster take a voice, players set their own character's, and Cast the others fills in the rest from the sheet, the NPC's traits and the story. A quoted line is read in the voice of whoever the prose says spoke it.

Narration needs a speech service the server can reach: Kokoro, or any OpenAI-compatible speech server (OpenAI's own included), chosen in the admin panel under Speech on a self-hosted server. On a device world the app's Settings has a Narration and sound card for the same choice: OpenAI's voices on the saved key, a Kokoro found on this computer or on your network, or on screen only, with Hear a sample. When speech is unavailable, the table settings say why nothing will be read aloud. Story AI chooses who writes the story; Narration chooses whether those words are spoken.

Faces and theatre inserts

Theatre inserts in Table settings, Atmosphere puts a portrait and name over the scene when an NPC speaks. The presentation choice applies to the whole table.

Scene art, portraits and maps

With an image backend the Dungeon Master paints inline scene art as the story moves, location pictures for new places, and character portraits at creation. At a table playing in another language, the picture prompt is rewritten into English first, since image models read English best. Every picture can also be uploaded by hand wherever the AI would paint one; without either, painted portraits for each race and class stand in. On an app-hosted world the OpenAI key that tells the story can also paint, once an image model is selected; on a self-hosted server the administrator chooses ComfyUI, an OpenAI-compatible image model, or a FLUX worker. Pictures are queued behind narration on a shared GPU, so a scene picture can arrive a little after its paragraph. On the desktop, an agent you already have can paint too: Codex and Grok Build, once one test picture succeeds on your machine. The Settings tab sets pictures on or off, their shape, fast or slow quality, and the campaign's Art style; scene pictures take a look that suits the setting, and painted maps carry no labels. Battle maps themselves are painted on your device from terrain and never need an image backend.

An old or interrupted request shows Image tool requested with a Generate button, so nothing is lost when a backend was busy.

Ambience and music

A catalogue of 78 cues in three layers (a room bed, music, and stings) is driven by the Dungeon Master, by a human DM from the console, or inferred from the scene when Follows the scene is on; a place or a fight's kind of scene picks its sound. Each listener has a volume, and ambience ducks under narration.

The Sound control in the table header (inside Table menu on a phone) opens the Sound panel: what is playing now, the Room and Music rows with several takes per cue, Next to skip to another take, a level for each layer, and tile pickers for whoever steers the story.

The sound library is open-licensed recordings (public domain, Creative Commons and OpenGameArt), each credited on the server's licences page. A self-hosted server set up from the source has it already. The desktop and Android apps leave it out of the installer: the first launch's Voices and music step and the app's Settings, Narration and sound, offer Download the sound library (about 75 MB, kept across app updates), and so do the Sound panel and the admin panel's Sound library card for an admin at a table with no library. The table hears the first cue when it lands. Players joining someone else's world hear the host's library.

Where the switches are