What Is Immersion Mode? AI Images, Sound, and Voice in Embertold

Text is the foundation of Embertold. But with Immersion Mode enabled, your adventure becomes something more.

What Immersion Mode Does

When you toggle Immersion Mode on, the Game Master gains access to a suite of multimedia tools. As it narrates your adventure, it can:

• Generate scene images — Landscape illustrations of your current environment
• Create sound effects — One-shot audio for dramatic moments (a sword clash, a door creaking, thunder)
• Set ambient soundscapes — Continuous background audio that matches your environment (tavern chatter, forest sounds, dungeon echoes)
• Voice NPCs — Every NPC speaks with a unique AI-generated voice, with emotion and personality

All of this happens automatically. You don't need to request it, the AI decides when a moment deserves visual or audio enhancement.

Scene Images

As you explore, the AI generates landscape images of key scenes. Enter a grand throne room? You'll see it. Step into a misty forest? It's illustrated before your eyes.

The images match the narrative's art style and are consistent with the universe's aesthetic. They appear inline with the text, making your adventure feel like an illustrated novel.

Sound Effects and Ambient Soundscapes

Dramatic moments get punctuated with one-shot sound effects. New locations get an ambient soundscape change, a layered mix of looping, one-shot, and interval sounds that shifts with a smooth crossfade as you move around the world. A single turn triggers one or the other, never both, so the audio never piles up.

NPC Voices

Every NPC in Embertold can speak with their own voice. When the AI introduces a new character, it assigns them a voice that matches their personality and description, a gruff dwarven blacksmith sounds different from an elegant elven diplomat, and that voice, with emotional delivery layered on top, stays with them for as long as they're part of the story.

Natural Flow

Messages with audio content, sound effects, ambient changes, and voice lines, auto-reveal during playback. Instead of clicking through each message manually, the narrative flows cinematically: you hear the sound, read the text, and the story continues. This creates a pacing that feels deliberate and immersive, like watching a scene unfold rather than clicking through slides.

What About Credits?

Immersion features use credits for generation. But here's the key: cached content is free.

Embertold uses a similarity-based caching system. If the AI generates a scene image for "a misty forest at dawn," that image is cached. The next time any player encounters a similar scene, the cached image is served instantly, no credits used.

The same applies to sound effects and voices. Over time, the cache grows richer, and more content becomes free for everyone.

You can see exactly how many credits each message consumed directly in the gameplay UI, a small badge shows the cost, so you always know what's being spent, and every account gets a monthly credit allowance so immersion is never entirely gated behind a purchase.

Turning It On

Immersion Mode is a toggle in your session settings. Turn it on for the full experience, or keep it off if you prefer pure text. You can switch at any time during gameplay.

When it's off, the AI only uses previously cached assets, no new generation, no credits consumed. You still get images and sounds when a cache hit is found.

Text tells the story. Immersion Mode makes you feel it.