Labs · Free tools
Browser tools for readers
and card players
47 free tools. Most run locally in your browser: no text, no card file ever leaves your machine. A few static-data pages (the price table, the new-cards digest) are dated static snapshots, each labeled with its data-as-of date. The rules and parsers are the same ones our app pipeline actually uses — not demos.
Checkups
11
AI Flavor Checkup
Paste a Chinese passage; a phrase blacklist plus sentence-pattern quotas return a 0-5 score with every hit highlighted. Browser port of the v10.7 ruleset behind our card copy review.
Open tool →Card Checkup
Drop a character card (PNG / JSON / .charx): format version, field contents, token distribution, embedded lorebook, and the usual import-failure causes — in one pass.
Open tool →Token Counter
Paste text for a live token estimate, or drop a card for a field-by-field weigh-in — permanent, one-off and keyword-triggered tokens listed apart, with 2k/4k/8k window budget bars and honest per-family variance ranges.
Open tool →Impersonation Checker
Bot keeps speaking and deciding for you? The pattern is usually planted in the card. Drop it here and every speaking-for-you line gets flagged in place — with why it teaches the model, and a before/after rewrite.
Open tool →Card Slop Doctor
Does the card read machine-made? Measure it: stock phrases flagged by shelf (eight of them), AI-fixated names, W++ relic syntax, trait soup, interview-style examples — a density verdict with one rewrite direction per shelf.
Open tool →Book File Checkup
Drop a novel txt: chapter detection, word count, encoding, and audiobook length at four speeds — a 30MB tome parses locally with a real progress bar.
Open tool →Fiction Prose Stats
Sentence rhythm, dialogue ratio and verbatim repeats at a glance — dialogue bands referenced against 378 real chapter samples.
Open tool →Text X-Ray
A real neural net runs in your browser and tints every word by how easily the model guessed it — red for dead giveaways, teal for surprises. A statistical lens, not a detector; the calibration data is on the page.
Open tool →Narrative Fingerprint
Paste a chapter and read its structural accent — feelings named vs performed, retrospection, scent imagery — against calibrated human and AI bands, with evidence lines per axis. The fourth lens, answering the StoryScope paper.
Open tool →Context Window Lens
See exactly why your AI chat forgets: drag the window slider and watch turns slide out — or drop your own tavern .jsonl and run it on a real chat.
Open tool →Tavern Preset Viewer
Turn a preset JSON into a readable config sheet: every prompt block in injection order, sampling parameters checked against common defaults.
Open tool →Tavern debugging
9
Lorebook Trigger Simulator
Paste a chat and see which world info entries fire and why: keyword hits, constants and recursion chains all drawn out.
Open tool →Lorebook Migration Doctor
See what breaks before you move a lorebook: JanitorAI's 1% probability trap, Risu reviving disabled entries, Agnai dropping constant flags — five platform dialects compared, plus a keyword divergence lab.
Open tool →Lorebook Merger
Merge several World Info books into one: duplicates grouped by content similarity plus trigger-key overlap, pick what stays, key collisions listed for a ruling — exports clean SillyTavern JSON, ST entries passed through byte-faithfully.
Open tool →Novel to Lorebook Skeleton
Drop a txt/epub: chapter detection plus rule-counted characters, places and terms, exported as an ST World Info skeleton — trigger keys, chapter ranges and token budgets per entry, flesh left for you or an AI with the included brief.
Open tool →ST Regex Tester
Debug SillyTavern regex scripts online with a live before/after; catastrophic-backtracking patterns get caught by the same guard the app ships.
Open tool →ST Macro Playground
See exactly what {{char}} and {{random}} expand to — with a macro support table checked line-by-line against the actual engine.
Open tool →Greeting Preview
See your first_mes as a real chat bubble before you publish — and find out whether your 800-word opener arrives as 7 rapid-fire texts.
Open tool →Prompt Assembly Inspector
Drop a preset, card and lorebook, replay the moment you hit send: every message colored by source, every lorebook entry accounted for — the assembly floor where “preset not working” gets solved.
Open tool →Repetition & Sampler Doctor
Paste the looping replies (or drop a chat .jsonl) plus your sampler settings: a three-layer repetition report, ranked root causes, and a per-family settings checkup — every claim labeled with its evidence level.
Open tool →Cards & file tools
14
Card Shelf
Batch-drop the cards piling up in your downloads folder and browse them as a cover wall: full field view, greeting bubbles, lorebook entry badges. Stored locally, survives restarts — and any card hands off to the editors in one click.
Open tool →Card Studio
The light-tier editor for quick edits to one card: per-field editing with live token counts, dead lorebook entries flagged as you type, macro preview, v2/v3 JSON or PNG export. For drafts and deep diagnostics, use the Workbench.
Open tool →Card Workbench Pro
Card Studio's Pro tier, for people who write cards: multi-draft autosave, group-chat pack assembly, inline marks, and a live diagnostics rail — impersonation detection, slop scoring, per-field token budgets.
Open tool →Card Brief Bag
Can't write a card yet? Bag rough material — who they are, the world, the opening scene, taste tags, pasted excerpts — then send it to the app's butler agent, or copy a craft-rules-inlined task brief for any AI. Zero generation, zero upload on the page.
Open tool →PNG Card Embed & Extract
Convert between JSON and PNG character cards: drop a PNG to pull the raw JSON, or a JSON plus a base image to build a PNG card byte-by-byte.
Open tool →Card Slimmer
Card PNG too big to upload? Re-encodes only the artwork — the card chunks are copied out of the original file, re-embedded untouched and byte-verified before download. Honest when it didn't shrink.
Open tool →Card Diff
Drop two versions of the same card: word-level field diffs, lorebook entries paired into added / removed / modified, token deltas on the checkup's ruler — changes hiding outside visible fields get called out.
Open tool →Card Poster Maker
Drop a card, get a share-ready promo image: portrait / banner / 4:5 layouts, palette pulled from the art, an editable one-line pitch — reads only public display fields, never the definition or lorebook.
Open tool →Chat Skin Previewer
Eleven cultural-motif chat skins rendered live — fold-out thoughts, themed status bar, scene card, tappable choices. Paste your own text to try one on, rename the fields, export a regex pack for SillyTavern or the app.
Open tool →Card Format Converter
Upgrade v1/v2 cards to v3 or normalize v3 down to v2 — downgrades list every dropped field and ask before download, with a three-generation comparison table.
Open tool →JanitorAI ⇄ Card Converter
Paste a JanitorAI personality blob, get a v2/v3 card — or drop a tavern card and get paste-ready text per creation box, weighed against JanitorAI's own 1,500-token guidance, losses listed.
Open tool →TXT to EPUB Converter
Turn a txt into a real ebook: production-grade chapter detection, GBK rescue, a canvas-typeset cover, packaged as EPUB 3 — passes EPUBCheck with zero errors.
Open tool →Image Vectorizer
Convert PNG / JPG / WebP into clean SVG vectors: the open-source VTracer engine as WebAssembly, four presets, slide-to-compare — no watermark, unlimited.
Open tool →Expression Pack Workshop
Batch-drop your sprite art: auto-assigned to SillyTavern's 28 expression slots, transparency-checked, tried on in a bubble fitting room, zipped flat for first-try import. Zero AI generation.
Open tool →Cost & pricing
3
AI Reading Cost Calculator
What a 2M-word audiobook actually costs, in real prices — 19 mainstream models at list prices, with a “what 5,000 sign-up credits buy” comparison.
Open tool →LLM API Price Table
1,300+ models from 30 providers in one sortable table: input, output, cache-read price and context window.
Open tool →Prompt Cache Savings Calculator
How much caching saves on long chats, at real price spreads — hit-rate anchors from our instrumented four-way benchmark.
Open tool →Play & share
7
Turing Arena — Human or AI?
One blind question a day: two passages continue the same classic novel — one is the author's real next paragraph, one is a live model imitation. In our double-blind study LLM judges scored 12%; see if you can beat them. Wordle-style scorecard, streaks stored locally.
Open tool →Fan-Card Maker
Frame a favorite character as a collectible card or bookmark, drawn on canvas and downloaded as PNG; rarity is the card's real community standing.
Open tool →Try Your Book
Drop a txt into a web phone simulator and read it with real pagination and page turns — first three chapters sample locally.
Open tool →Chat Log to Image
Drop a tavern .jsonl or paste "Name: text" lines, pick the range worth showing, and get one typeset long image — four themes, auto-paged into a zip for long chats.
Open tool →Story Theater
Drop a novel txt and it plays as a visual novel on the spot — name tags, scene splits, typewriter dialogue, zero AI calls.
Open tool →Chat Archaeology
Dig a tavern chat export into a relationship report: days and floors, late-night share, the most rerolled message, what it would cost at list prices — the share card carries numbers, never your words.
Open tool →Chat Log Converter
Drop a tavern .jsonl and get the whole chat as clean text: Markdown ready to paste into a post, or a standalone HTML page with reading typography — hidden floors filtered with an honest count.
Open tool →Content library
2
New Cards Weekly
Recent community character cards on one page: cover, tags, lorebook size and a one-line hook, each linking to a detail page.
Open tool →TTS Voice Gallery
96 voices reading the same sentence: Qwen-TTS (49, incl. dialects), Grok Voice (26), OpenAI (13), CosyVoice2 (8) — loudness-normalized, loaded only when you press play.
Open tool →Experimental tools
1
Tech previews: working end to end, with honest limits documented on each page. Results vary by input — read the on-page “what it can't do” section first.
Resource pages from the same toolbox
Not interactive tools, but free and built from the same production assets.
Official prompt template library
20+ official prompt packs on one page: continuation styles, story-option directors, video and image wrappers — full text, copy-ready, with a detail page per template.
Foreverse Research
Benchmarks you can recompute: the nine-model continuation leaderboard, the four-way tavern comparison, and the citable research archive — raw chains and JSON snapshots included.
Fiction Bench — continuation leaderboard
Nine models, two genres, 20 consecutive rounds each, double-blind judging: which LLM actually writes fiction like your book, with failure taxonomy and cost per 10k characters.
Foreverse vs SillyTavern benchmark
Same model, same key, byte-identical scripts, one metering gateway: measured cache hit rates, cost, deep-lore recall, and long-chat memory across four setups.
What these tools don't do
They don't store your input, so there's no “smarter in the cloud” tier; and they aren't truth oracles — the flavor checkup flags known patterns, not authorship, and the card checkup reports format facts, not quality scores. Each tool page has a “what it can't catch” section; read it before trusting a result.