A structured workspace for long-form writing
QINGYAN is an AI writing studio for novelists and screenwriters. Story maps, character files, and foreshadowing stay in order; the AI only drafts proposals inside your structure, and nothing reaches the manuscript until you approve it.
In a dusty filing cabinet the protagonist finds a second signature stamp — the same hand as the suicide note in chapter one.
A chat window can't hold a novel. QINGYAN breaks long-form work into manageable structure — then lets the AI operate strictly inside it.
Volumes, arcs, and chapter-level beats unfold layer by layer. Conflicts and gaps are visible at a glance.
Desires, wounds, and knowledge boundaries stay on record — chapter two hundred still sounds like chapter one.
Every thread records where it is planted and where it pays off. Deadlines surface before setups go stale.
Every AI edit arrives as a highlighted diff. Accept or reject line by line — the final word is yours.
Honorifics, banned words, and narrative voice become hard constraints the AI must draft under.
Timelines, lore, and character states are checked automatically — contradictions never reach the manuscript.
One structure, shaped for every kind of long-form work.
Daily updates strain outlines, buffers, and memory.
The story map owns the structure, foreshadow alerts fire on time, and offline mode keeps the streak alive.
Many scenes, many speakers — voices drift.
Beat sheets are organized by scene; character files hold every line to its voice.
Clue fairness and timelines break quietly.
Foreshadow tracking and continuity audits catch logic gaps before they merge.
Canon is vast; readers catch every drift.
Build a canon library once — relevant files are injected before every draft.
Several titles at once — styles bleed together.
Isolated workspaces, per-book style rules, one shared credit pool.
Hundreds of thousands of words — where to start?
Import the draft, rebuild the outline, regenerate chapter by chapter at your own pace.
Five stages, each confirmed by you before the next one begins.
Write the premise and genre direction; set the tone of the whole book.
World rules and character files take shape; boundaries are made explicit.
Volumes and chapter beats unfold layer by layer; foreshadowing is placed.
Prose follows your style rules — the AI drafts, you decide.
Only after continuity checks and your line-by-line review does text reach the manuscript.
Work files are stored on your device by default. Accounts, subscriptions, credits, and AI tasks are handled by QINGYAN services. You can keep editing, searching, and exporting offline, then reconnect for AI collaboration.Write locally, without being tied to a network.
Switch freely between fast and quality tiers — or bring your own key and write with the models you already trust.
On Pro and above, paste your own API key in client settings: usage bills to your own account and no longer consumes platform credits.
The AI may draft; the final word is always yours.
Work files stay on your device; account and usage services stay in sync.
AI needs a connection; writing does not have to be online all the time.
Pure credit-based billing: generation is charged at actual usage — roughly 1× on Fast, 1.3× on the Quality baseline. Daily check-ins and chapter missions earn credits back. No hidden fees.
For trying whether it fits.
For serial authors on a daily schedule.
For heavy drafting and relentless revision.
For studios and hyper-productive authors.
Subscriptions renew monthly or yearly and can be cancelled anytime; credits expire at month's end and are deducted by actual usage (≈1× Fast, ≈1.3× Quality baseline). Pro and above can plug in their own model API, so generation stops consuming platform credits. Prices are billed in CNY.
Outlines, character files, foreshadow states, and existing prose are compiled into structured context and injected per task. Output returns as proposals, and only after continuity checks and your line-by-line review does it merge — the structure holds, so the memory holds.
In the current version, work files are stored on your device by default. Sign-in, subscriptions, credits, and AI tasks are handled by QINGYAN services. When you start an AI task, the context needed for that task is sent to the selected service; review the scope before submitting.
Yes. Outline editing, character files, drafting, search, and export are all available offline; reconnect anytime to summon the AI assistant.
No. AI output appears as a proposal or diff first. It is written into the work only after continuity checks and your line-by-line review; you can reject a proposal when it does not fit.
One account can be signed in on up to 3 devices at once. In the current version, each device keeps its own work library, while subscriptions and credits are shared across devices.
Sign in and go — work files stay on your device by default, while accounts and AI features connect when needed.
Installers and release notes ship through GitHub Releases. On first launch of an unsigned app, Windows may show SmartScreen — choose "Run anyway".