Review & deliver
Literess, the editor who acts
No cardFirst 5 pages freeYour work never trains AI
What does a second reader do besides read?
She works in two ways: as an editor who reads and comments, and as an agent who takes actions you confirm, or applies them without the click once you turn on Allow All. Both draw on the same memory as the rest of Transept: your glossary, your styleguide, and the decisions behind your past translations.
She reads and flags what went flat
Literess reads the translation the way an editor would and leaves inline comments where the tone has gone neutral, the meaning has drifted, or a term has slipped.
She remembers you between documents
Tell her you prefer British spelling, or that you’re halfway through a sci-fi trilogy, and she remembers it next time. She also draws on your glossary, styleguide, past translations, and the decisions behind them, so no session starts from a blank slate.
She acts when you say so
Ask her to translate a document, run a proofread workflow, draft a new document, invite a teammate, or set your default glossary. By default she proposes it on a card with its cost and does it once you confirm. With Allow All on, her changes apply without the click, and inviting a teammate still asks first.
She finds her way around the app
Ask her to open the glossary, jump to the CRM board, or start a workflow in the builder. Literess navigates the editor and the app for you, so “show me…” and “set up…” take one sentence instead of a hunt through menus.
Why an agent, not a chatbot?
Grounded in your memory
She knows your terms, your voice, and your past decisions, so her comments and actions follow how you already work instead of a generic best guess.
She does it for you
A chatbot tells you what to do. Literess does it: she runs the workflow, drafts the doc, or moves the card, and asks you first unless you’ve turned on Allow All.
A human still decides
Literess flags, suggests, and drafts, and you decide what she may apply. She works beside you as a literary editor, and you still decide what sounds right.
~1,000 calls measured
We logged the reasoning on roughly a thousand real translation calls. On plain text the pricier Pro model thinks about half as much as Flash. The harder the sentence, the more any model reasons, whatever its tier. Literess uses Pro to plan and decide, and hands routine work to cheaper models.
What we measured— Don’t take our word for it —
The editor, in miniature
A working slice of the real app: Literess, the glossary, the styleguide, workflows, and translation memory are all live. Click around.
Simple pricing
Every plan comes with monthly credits. You spend them only on AI work, at the price each action shows before you click. No sales call and no contract: start free and add a credit pack whenever you need more.
One credit covers one source word in Standard mode. Pro mode uses a more capable model and costs 3 credits per source word. Chinese and Japanese source text is counted per character. Manual edits, exports, comments and translation memory are free: you spend credits only when AI translates, rewrites or checks your text, or reads a document to build a glossary or styleguide. Every paid action shows its price on the button before you click. See the price list.
Free
Always freeFor your first projects
Unlimited users
Translated with Pro, proofread with Standard. About 11 on Standard alone.
- Pro mode: a more capable model for nuance, 3 credits per source word
- Standard quality: fast, accurate, faithful
- Translation memory: your past translations, reused to keep new ones consistent
- Workflows: chain translation, proofreading, and checks into one run
- Glossary, styleguide, QA, import / export: all included
- Notion, Drive, TMX / XLIFF: import, export, and bring your own memory
- 68 languages: from Spanish to Tagalog
- Batch translation of whole documents
- 10 lifetime messages with Literess: your AI literary editor, who remembers your projects and preferences
- No card required
Starter
For regular client work
Unlimited users
- Literess: your AI literary editor, who drafts, proofreads, and sets things up for you
- API, MCP & webhooks: automate runs, or let AI assistants work in your account
- Teams: invite anyone for free; add €29 seats to fund a shared credit pool (60,000 credits a month each)
- Top up anytime: pack credits never expire
Pro
For higher volumeFor agencies & large catalogs
Unlimited users
- Over 3× Starter’s credits: headroom for batch work and full catalogs
- Priority support: a direct line and faster replies
- Predictable bill: most months need no extra credit packs
Prices are in euros and exclude VAT. If VAT applies to your purchase, checkout shows it before you pay, and a business with a valid EU VAT ID pays the net price under reverse charge. You can buy credit packs on any plan, including Free: 30,000 credits for €19, 100,000 for €55 or 300,000 for €149. Pack credits never expire. Creating a team and inviting people is free. To share credits, add two or more seats: each seat adds its plan’s monthly credits to the team’s pool, all on one invoice. Cancel anytime and keep your plan until the end of the period you’ve paid for. We give refunds for faults on our side that we can’t fix and for billing mistakes, and EU consumers can withdraw within 14 days and get back the unused part.
FAQ
- Literess can create and run workflows (including translating a document), draft a new document, move a job across your CRM board, invite a teammate, and set workspace defaults such as your glossary or styleguide. By default you confirm each action first, and anything that spends credits shows its cost before it runs. With Allow All on, her actions apply without the click, except inviting a teammate, which always asks.
- Yes. She keeps up to 20 notes per account and also draws on your projects, preferences, glossary, styleguide, and past translations. You can review or clear her notes whenever you like.
- Yes, to try her out: the Free plan includes 10 messages with Literess in total. Starter (€29/mo) and Pro (€79/mo) keep her with you, with memory across your documents.
- Literess uses the same frontier models as the rest of Transept, currently Google’s Gemini family. She is the workflow and memory layer around the model, not a separate service.
Built for work you answer for
Private by default
Your text is never used to train AI, not by us and not by any provider we use, and it stays out of our logs. Delete your account and your text is deleted with it.
How we handle dataSecurity you can check
Hosted in Germany, in Hetzner’s ISO 27001-certified data center. Every sub-processor is listed, and a DPA is one email away.
All sub-processorsGive it context
Glossaries, styleguides, translation memory and per-string notes go with every request. You set them up once per project.
GlossariesYou’re the human in the loop
The AI drafts; you decide. Review every change side by side, keep or revert it, and send a review link when a client needs to look.
Review linksAPI, MCP and webhooks
The full API on Starter and Pro. Connect Claude or another AI assistant over MCP, or start runs from your own tools.
Developer guideSomething bigger?
Large catalogs, custom workflows, a DPA for procurement. Transept stays self-serve; write to us for the rest.
support@transept.ai

