DeepReference documentation
Find setup instructions, feature details, and the limits you should know before starting a job. Begin with the quickstart, or open the article for the tool you are using now.
Getting started
Overview
An overview of the dashboard translator, document jobs, editors, language assets, and review tools.
Quickstart
Run a first text translation or upload a first document from the dashboard.
Plans and billing
See the current plan limits, included workflow tools, word-counting rules, billing options, and capacity top-ups.
Account and preferences
Change the interface language, document-completion emails, password, security options, and account deletion settings.
Translation
Text translation
Translate up to 20,000 characters from the dashboard with language, domain, tone, mode, glossary, and Translation Memory controls.
Document translation
Upload DOCX, PDF, XLSX, or PPTX files, translate their text, and rebuild the result in the original file type.
Languages and regional variants
DeepReference supports 45 languages with automatic source detection, and regional variants you select on demand when the difference matters.
Domains
Twelve specialized domains (legal, medical, financial, technical and more) steer the model toward the vocabulary and conventions of your field.
Tone and mode
Mode controls how closely the translation follows the source structure (natural vs. literal). Tone controls the register of the result: nine tones on top of the standard voice.
Editors
Translation editor
Review source and target segments side by side with Translation Memory, terminology, QA, comments, status, and per-segment retranslation.
Document editor
Review and edit a translated DOCX in its rendered page layout, with tables, headings, images, and segment tools in view.
Smart suggestions
Complete words and phrases from the active glossary, approved termbase entries, and Translation Memory while editing a target segment.
Quality assurance checks
Check target segments for missing placeholders, formatting-tag differences, unusual length, inconsistent translations, and glossary violations.
Spellcheck
Use the browser's spelling dictionary for the target language while editing a segment.
Formatting and special characters
How formatting survives translation, what the editor toolbar offers, and where to find special characters.
Comments, history and review
Add segment comments, inspect saved versions, and restore an earlier target text during team review.
Language assets
Glossary
Store approved term pairs for a language pair and apply them during text translation, document translation, and review.
Translation memory
Save approved source and target segments, reuse exact matches, and review fuzzy matches when similar text appears.
Concordance search
Search Translation Memory for a word or phrase and review the source and target segments where it appeared.
Terminology extraction and termbase
Find bilingual term candidates in translated documents, review them, and save approved entries to a termbase.
Project tools
Analysis report
See the source-word total, internal repetitions, translation-memory coverage, and a transparent workload estimate before you begin a job.
Revision comparison
Compare a revised DOCX with an earlier translated version, review the changed sentences, and retranslate only the new or modified material.
Locale formatting and punctuation
Optional rules for number formats, quotation marks, and punctuation spacing in the target language.
CAT settings reference
Every workflow setting in one place: translation defaults, TM matching, quality checks, locale formatting, non-translatables, presets, and data retention.
Exporting your work
Download translated documents in their original layout, export to PDF or plain text, or retrieve the original file.
Security and teams
API
API overview and authentication
REST endpoints for Business and Enterprise accounts to translate text and read current word usage with API-key authentication.
POST /v1/translate
Translate a piece of text with your account's settings and language assets. The core endpoint of the API.
GET /v1/usage
Read the used, limit, and remaining word counts for the current billing period.