← the studio
A MoreSalamander · StudioLabs production

my-AI-story

Seed a world — characters, a theme, a loose direction — and my-AI-story writes a coherent serialized story, episode after episode, narrated with a distinct voice per character. Every episode is verified against a series bible, so episode 7 still remembers episode 1.

Many episodes, one story. Continuity is the thread.

What it is

A series that remembers itself.

The hard part of long-form generation isn't writing a page — it's writing page 200 without contradicting page 1. my-AI-story drafts a series bible (the canonical source of truth for characters, world facts, and the arc), then writes each episode against it and refuses to keep anything that breaks canon. Where my-AI-stro verifies knowledge, this verifies narrative continuity — same thesis, new medium.

Watch it run

The model drafts an episode; the bible catches what breaks canon.
my-AI-story · live pipelineattempt 1
bible
draft
continuity
gate ●
structure
gate ●
speaker
gate ●
tts
cue
gate ○
mixed WAV
Three blocking ● gates protect the story: continuity (consistent with the bible), structure (beats well-formed), speaker (every line assigned to a character). Sound cues are non-blocking — an unresolvable bed is dropped, never fails the episode. Continuity is the premise.

The three moves

Explain · Synthesize · Verify — against canon.
01 · Explain

The series bible — canonical characters, world facts, and the arc — is the source of truth. New canon (a death, a reveal) is folded back in through a verified update, so the constraints grow with the story.

02 · Synthesize

A local LLM drafts prose and speaker-tagged dialogue for each episode; a local TTS engine renders a distinct voice per character and stitches them into one narrated episode.

03 · Verify

Before a word is kept: continuity against the bible, structure of the beats, and speaker assignment — all blocking. No quiet contradictions; episode 7 still remembers episode 1.

Best at — and the honest limit

Long-running coherence, narrated.

my-AI-story holds a serialized world together across many episodes and renders it as multi-voice audio, entirely on local models — Ollama for synthesis, a local TTS for voices. Nothing leaves the machine.

What it can't do: the gates verify consistency — that the story doesn't contradict itself — not that the prose is great writing. It guarantees continuity, and is honest that voice and craft are a human's to judge.