API_KEY
tisane_api_key
Developer setup
No fields declared in this snapshot.
User connection
- API Subscription Keygeneric_api_key · stringRequired
TISANE
Tisane Labs provides natural language processing APIs for content analysis, language detection, entity comparison, semantic similarity, text extraction, and translation.
Description is untrusted, display-only upstream metadata. It never becomes policy, OAuth scope authority, or an agent instruction.
Pakkawork boundary
Research catalogue metadata only. No Pakkawork OAuth, credential, host, quota, executor, or verifier is enabled.
15
Action summaries
Display-only definitions
0
Trigger types
Not installed instances
1
Auth modes
Field names, never values
No
Execution
No runtime adapter
Authentication map
API_KEY
No fields declared in this snapshot.
Capability index
Showing 1–15 of 15 actions
TISANE_ANALYZE_TEXT
Analyze text for sentiment, abuse, entities, topics, sentence structure, and other requested NLU details. Output sections vary with the text and settings.
Untrusted display-only summary
TISANE_CALCULATE_TEXT_SIMILARITY
Calculate semantic similarity between two same-language or cross-language text fragments. A result of -1 is an observed provider sentinel, not a normal 0-to-1 similarity score.
Untrusted display-only summary
TISANE_COMPARE_PERSON_ENTITIES
Compare two person-name entities, including cross-language names, and report whether Tisane considers them the same, different, or not single entities.
Untrusted display-only summary
TISANE_DETECT_LANGUAGE
Tool to detect the language of the provided text. Use when you need to identify the language code.
Untrusted display-only summary
TISANE_DETECT_LANGUAGES
Detect one or more languages in text, optionally segmenting it, and return offsets plus provider-native integer confidence scores.
Untrusted display-only summary
TISANE_EXTRACT_TEXT
Remove markup, scripts, styles, and JSON structure from UTF-8 text content and return the provider's raw cleaned text.
Untrusted display-only summary
TISANE_GET_FAMILY_DETAILS
Tool to fetch metadata for a family from Tisane language models, including definition, description, hypernyms, and external references (Wikidata, WordNet). Use when you need detailed information about a specific family concept by its numeric identifier.
Untrusted display-only summary
TISANE_GET_SUPPORTED_LANGUAGES
Tool to list all languages supported by the API. Use when needing to discover available languages for text analysis or processing. Call before submitting text to ensure support.
Untrusted display-only summary
TISANE_LIST_FEATURE_VALUES
Tool to list feature values for a particular category such as entity types, subtypes, abuse types, and tags. Use when you need to discover valid values for a specific feature category before analysis or filtering.
Untrusted display-only summary
TISANE_LIST_HYPERNYMS
Tool to list all hypernyms related to a family. A hypernym is a parent concept (e.g., vehicle is a hypernym of truck). Use when you need to understand the conceptual hierarchy or broader categories for a given family ID.
Untrusted display-only summary
TISANE_LIST_HYPONYMS
Tool to list all hyponyms related to a family. A hyponym is a child concept (e.g., 'truck' is a hyponym of 'vehicle'). Use when you need to discover more specific concepts within a semantic family.
Untrusted display-only summary
TISANE_LIST_INFLECTIONS
Tool to retrieve inflected forms of a specified lexeme within a given language family. Use when you need to get all grammatical variants of a word.
Untrusted display-only summary
TISANE_LIST_LANGUAGES
List Tisane language records and whether each language model is currently loaded.
Untrusted display-only summary
TISANE_LIST_WORD_SENSES
Tool to fetch all senses (meanings) related to a word. Use when you need to explore word definitions, families, features, and lemma information for linguistic analysis.
Untrusted display-only summary
TISANE_TRANSFORM_TEXT
Translate text to another language, or paraphrase it by using the same source and target language. Returns the provider's raw transformed text.
Untrusted display-only summary
Provenance
The detail snapshot comes from an attributed MIT-licensed repository revision. Safe local icons use exact-match CC0 Simple Icons symbols; unmatched brands use monograms.
Remote text is plain display metadata only. It must never become an agent prompt, execution policy, OAuth grant, or executable instruction.