DeepL

Get a single custom instruction from a style rule set.

get-custom-instruction

Get metadata for a single glossary: name, available dictionaries, and creation time. This does not fetch any glossary entries. Use get-glossary-dictionary-entries to fetch entries.

get-glossary-info

Get all entries in a glossary's dictionary for a specific language pair. Entries are returned as TSV (tab-separated source/target pairs, newline-separated).

get-glossary-dictionary-entries

Get a single style rule set with full detail: its enabled predefined style rules and its custom instructions. A translation that passes this set's styleId applies both; the instructions do not have to be repeated on the translate call.

get-style-rule-set

List all translation glossaries with metadata: id, name, available dictionaries, and creation time. This does not fetch any glossary entries. Use get-glossary-dictionary-entries to fetch entries. Every tool here works on translation glossaries only, and only on the ids this tool returns.

list-glossaries

List the predefined style rules a style rule set can enable, for one authoring language, plus the full supported-language list. These are DeepL's own rules; they are not the caller's saved style rule sets (use list-style-rule-sets for those). Omit language only when the rules for every language are needed. A supported language with no rules entry supports custom instructions only.

list-predefined-style-rules

Get the source language codes supported by DeepL for translation, e.g. 'EN' or 'DE'. Use one of these for the sourceLang parameter of translate-text.

get-source-languages

List the caller's style rule sets with metadata: id, name, and authoring language. Use get-style-rule-set to fetch the full detail including its enabled style rules and custom instructions. The ids returned here are style rule set ids, not glossary ids: the glossary tools reject them.

list-style-rule-sets

Get the target language codes supported by DeepL for translation, e.g. 'EN-US' or 'DE'. Use one of these for the targetLang parameter of translate-text.

get-target-languages

Permanently delete entries from a glossary's dictionary for one language pair, named by their source terms. The dictionary's other entries are left alone. Read the current entries with get-glossary-dictionary-entries first; a source term that is not in the dictionary is reported back in notFound rather than failing the call.

remove-glossary-entries

Rename a glossary. Its entries are untouched. Use list-glossaries to find the glossary id.

rename-glossary

Rephrase text in the same or a different language using DeepL.

rephrase-text

Replace every entry in a glossary's dictionary for one language pair with the entries you send: anything you leave out is deleted. Read the current entries with get-glossary-dictionary-entries first, or use update-glossary-entries to add and change entries without dropping the rest. If the glossary has no dictionary for the language pair yet, one is created. To remove the language pair altogether use delete-glossary-dictionary.

replace-glossary-dictionary

Translate text to one or more target languages using DeepL. Use this for plain text provided directly in the conversation — snippets, strings, messages, or passages pasted by the user. Do not use this to translate a file or document (e.g. Word, PowerPoint, Excel, PDF, HTML, .txt, .srt, .xlf/.xliff) — even if you can already read its contents — because it returns plain text and discards the document's layout and formatting. For files, use upload-document instead. Review the optional parameters and use those that apply for best results. When using a glossary, you must specify the source language as well as the target language. If the user references a glossary by name, use list-glossaries to look up its id. An unknown glossaryId is silently ignored (translation proceeds without it). An administrator may assign a language system (style profile) to the account, whose glossaries and style rule set can replace the glossaryId and styleId passed here; 'appliedCustomizations' in the result says so when it happened, per target language. Every target language is translated in one call; the result holds one entry per language, and a language DeepL refused is reported in 'failures' while the others still translate. Multiple texts are supported and translated independently; within each target language, results correlate to the inputs by position. If any text is blank, the whole request is rejected.

translate-text

Fully replace a custom instruction. label and prompt are both required even when only one changes. A hidden or missing instruction is reported as not found or not accessible.

update-custom-instruction

Add or change entries in a glossary's dictionary for one language pair. The entries you send are merged: a new source term is added, a source term already in the dictionary gets the target term you send, and every other entry is left alone. If the glossary has no dictionary for the language pair yet, one is created. Use remove-glossary-entries to delete entries.

update-glossary-entries

Update a style rule set. version and language must come from the latest get-style-rule-set. rules is replacement data: omit it to preserve the enabled style rules, pass {} to disable all of them, or pass the complete desired enabled set using list-predefined-style-rules keys.

update-style-rule-set

Translate a whole file or document, preserving its original layout and formatting. Use this — not translate-text — whenever the user wants to translate a file or document (rather than text typed into the conversation), even if its contents are already visible to you; translate-text would strip the formatting. For plain text pasted into the conversation, use translate-text instead. Supported file extensions in this deployment: .docx, .doc, .pptx, .ppt, .xlsx, .xls, .pdf, .htm, .html, .txt, .xlf, .xliff, .srt, .png, .jpg, .jpeg. PNG and JPEG files are limited to 3 MB; limits for other formats depend on the user's plan. This call starts the translation and returns secure upload links. Several target languages take one upload: the file is transferred once and translated into each language, so 'targets' holds one entry per language and each language is billed as its own translation. A language DeepL refused is reported in 'failures' while the others still translate. An administrator may assign a language system (style profile) to the account, whose glossaries and style rule set can replace the glossaryId and styleId passed here; 'appliedCustomizations' on a target says so when it happened, per target language.

upload-document