Build from a whole document
A glossary or style guide is only as good as the reading behind it. Rather than pull terms and voice from one page, Transept can read a whole document, however long, and draft a glossary or a style guide from all of it, then hand you a draft to review.
What does building from a whole document do?
Both a glossary and a style guide can be built from a document you have already worked with. You can point the build at just the page you have open, or at the whole document. The whole-document run reads every block, not a sample, so the terms it pins and the voice it captures reflect the full text, which is what you want before you reuse them across a project.
| Current page | Whole document | |
|---|---|---|
| Reads | the page you have open | every block, in waves |
| Length limit | one page | none (uncapped) |
| Cost | small, one page | billed by words read, estimated first |
| Best for | a quick starting draft | a thorough, consistent result |
How do I start one?
For a style guide, open the Style guides tab, use its Generate button, and choose the whole document instead of the current page. For a glossary, ask Literess to build one from a document you have worked with; she extracts the candidate terms. Either way, pick the whole-document option to get the wave-by-wave read rather than a single page.
How do the waves work?
A long document does not fit in one pass, so the whole-document build splits it into waves. Each wave reads a stretch of the document and refines what the earlier waves found: a term the first wave was unsure of gets confirmed or dropped as later waves see it used again, and a style guide’s read of the voice sharpens as more of the text goes by. There is no block cap; a book-length document takes more waves.
What will it cost, and how long will it take?
A whole-document build is billed in words, the words it reads while drafting. That total is known before it runs, so you get an estimate first: the word cost as an “up to N words” ceiling, an estimated time, and the number of waves the document will take. You only start the run once you have seen it.
The ceiling is an upper bound, not a flat fee. A build that finishes early bills only the words it actually read, so the final charge is at or below the “up to” figure. Reusing translation memory or a glossary you already have costs nothing; only the reading is billed.
Where does the result land?
Nothing is added to your library until you review it. A glossary build lands as a draft of candidate terms: you accept, reject, or edit each one in bulk, and only the ones you keep become glossary entries. A style guide build lands as a draft you can review and save as a version, so your active voice does not change until you decide it should.
Is there a limit on how long the document can be?
No. The whole-document build has no block cap because it reads in waves, so it scales to a book-length file. A longer document just means more waves, a higher word estimate, and more time, all of which you see before you start.
Am I charged if I discard the draft?
You are billed for the words the build reads, which happens while it drafts. Reviewing the result afterwards costs nothing more: accepting terms, saving the style guide, or discarding the draft does not add or remove any charge. The reading is what the estimate covered.
Can I build a glossary and a style guide from the same document?
Yes. They are two separate builds (one drafts terms, the other drafts voice), so run whichever you need, or both. Each has its own estimate before it starts. See Glossaries and Styleguides.
Is this the same as the “AI sync” glossary from a large-parallel run?
No. The AI sync glossary and style guide are built automatically during a large-parallel translation to keep parallel agents from drifting apart; this is a build you start yourself on a document, whenever you want. Both end as drafts you review before they join your library.
Still stuck? Ask Literess in the app, or write to [email protected].