Get the current state of the offline data installation. Always available — even before the bundle has finished downloading. Returns: state (pending/downloading/ready/failed), per-artifact progress, total bytes downloaded, data directory, CDN URL, manifest version, and any error.

Manually kick off (or re-trigger) the offline data download. Returns immediately while the install runs in the background. Idempotent — calling repeatedly while a download is in progress is a no-op. Use dictionary_status to track progress.

Get synonyms for a word in any language using the offline ConceptNet 5.7 SQLite (24M edges, 80+ languages).

Get antonyms (opposites) for a word in any language using offline ConceptNet.

Get semantically related words via Numberbatch embedding cosine (9.16M concepts × 300d) — much denser than ConceptNet RelatedTo edges. Falls back to ConceptNet RelatedTo when the embeddings aren't installed.

Embedding-based nearest neighbors via Numberbatch. Returns words from the same OR a different language, sorted by cosine similarity. Multilingual (78 languages).

Hypernyms (broader concepts) via offline ConceptNet IsA. E.g. dog -> mammal.

Hyponyms (narrower concepts) via offline ConceptNet IsA. E.g. dog -> poodle.

Meronyms (parts/components) via offline ConceptNet PartOf. E.g. car -> wheel.

Holonyms (wholes that contain this word) via offline ConceptNet reverse PartOf.

Derivation relations via offline ConceptNet DerivedFrom.

Etymologically related words / cognates via offline ConceptNet EtymologicallyRelatedTo.

Typical uses (UsedFor) via offline ConceptNet. E.g. knife -> cutting.

Typical actions (CapableOf) via offline ConceptNet. E.g. dog -> bark.

Typical locations (AtLocation) via offline ConceptNet. E.g. book -> library.

Translate a word to another language via offline ConceptNet's cross-lingual Synonym links. Returns the same concept expressed in different languages.

All edges (every relation type) for a word in one call from offline ConceptNet.

Look up definitions for a word from the offline Wiktextract corpus (4,755 languages, 10.5M entries). Returns part-of-speech, definitions per sense, IPA, etymology, and translations grouped by language.

Get a brief plain-text summary of a word's senses from the offline Wiktextract data. Concatenates the first definition of each sense.

Return etymology text for a word from the offline Wiktextract corpus.

Return IPA pronunciation(s) for a word from the offline Wiktextract corpus.

Prefix-search the offline Wiktextract corpus for words matching a query. Useful when you don't know the exact spelling.

Return a random word entry from the offline Wiktextract corpus, optionally filtered to a language.

Find words that rhyme with the input word. English only — backed by the offline CMU Pronouncing Dictionary.

Find English words that sound similar to the input (homophones / soundalikes) via offline CMU dict.

Find words/phrases meaning approximately the same as the input via offline Numberbatch embedding cosine. Multilingual — works in any of the 78 languages Numberbatch covers.

Find English words matching a spelling pattern via offline CMU dict. '?' = any single letter, '*' = any zero+ letters. Useful for crosswords.

Get autocomplete suggestions for a partial English word via offline CMU dict (shortest matches first).