Which languages can Lyro analyse through Tisane?

Tisane covers 27 languages for detection, sentiment, and abuse analysis, and Get Supported Languages returns the current list with the code for each. Lyro calls it before submitting text, so an unsupported language is caught up front instead of coming back as an empty result.

Can Lyro use Tisane to match any two entities?

People only, for now. Compare Entities currently supports the person entity type and returns the specific differences between two compound names, which is enough to decide whether two records describe the same individual. Any other entity type has to be handled through Analyze Text or a similarity score.

Can Lyro rewrite a reply in the customer's language?

Transform Text handles both translation between languages and paraphrasing within a single one, so a draft can be reworded for the language the customer wrote in or simplified without changing language at all. It is a single call, so Lyro applies it to the draft rather than running it as a separate step.

Why route moderation through Tisane rather than asking a model?

Analyze Text returns structured linguistic output - abuse types, entities, topics, and aspect-based sentiment - drawn from a fixed feature set you can enumerate with List Feature Values. That makes a flag auditable against a known category, which a free-form model judgement is not.

Tisane MCP integration

Detects the language of a message, flags abuse types and sentiment, scores text similarity, and paraphrases or translates a passage.

Connect Tisane See all integrations

13actions available

Three actions you can hand over today

Every action runs live through MCP. Nothing to build, nothing to maintain.

Analyze text
Lyro performs deep linguistic analysis to extract meaning, entities, and sentiment from customer messages. Your team understands not just what customers say, but what they actually need.
Calculate semantic similarity
Lyro finds how closely related two messages are, even if worded completely differently. Your team matches similar customer issues to existing solutions instantly.
Detect language
Lyro automatically identifies the language of incoming customer messages. Your team routes multilingual conversations to the right agent without guessing or asking.

See all 13 actions

How businesses use Tisane + Lyro

Each card is one request a support team gets, and the Tisane actions Lyro runs to close it.

Detect the language before anything else runs
Lyro strips any markup out of the incoming text, identifies its language code, and confirms that language is on Tisane's supported list, so an analysis is not run against something the API cannot read.
Detect LanguageGet Supported LanguagesExtract Text
Flag abusive content with the reason attached
Analyze Text returns the abuse types, entities, topics, and aspect-based sentiment it finds, and Lyro can enumerate the valid abuse types and tags first, so a flag arrives with a category rather than a bare score.
Analyze TextList Feature Values
Tell whether two messages are really the same
Lyro scores the semantic similarity of two fragments from 0 to 1 and compares two person names to decide whether they refer to the same individual, so a duplicate is identified rather than assumed.
Calculate Semantic SimilarityCompare EntitiesList Word Senses
Look up what a word or concept actually covers
Lyro walks up from a concept to its broader parent or down to the narrower ones and lists a lexeme's inflected forms, so a term is matched by meaning rather than by exact spelling.
List HypernymsList HyponymsList Inflections

How it works

Get started in 3 steps

Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Tisane actions it has and picks the ones a request needs.

01
Connect Tisane
Authorize the Tisane account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Tisane actions that close it and chains as many as the request needs.
03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free

Tisane · Lyro

Everything else about Tisane

Setup, permissions, and the limits of what Lyro can do inside Tisane.

Tisane covers 27 languages for detection, sentiment, and abuse analysis, and Get Supported Languages returns the current list with the code for each. Lyro calls it before submitting text, so an unsupported language is caught up front instead of coming back as an empty result.

Every action available in Tisane

All 13 actions your agent can call on Tisane, straight from the live MCP connection.

Analyze text
Analyze input text for detailed NLU insights.
Calculate semantic similarity
Calculate semantic similarity between two text fragments.
Compare entities
Compare two compound named entities and identify differences.
Detect language
Detect the language of the provided text.
Extract text
Extract raw text from markup content.
Get family details
Fetch metadata for a family from Tisane language models, including definition, description, hypernyms, and external references (Wikidata, WordNet).
Get supported languages
List all languages supported by the API.
List feature values
List feature values for a particular category such as entity types, subtypes, abuse types, and tags.
List hypernyms
List all hypernyms related to a family.
List hyponyms
List all hyponyms related to a family.
List inflections
Retrieve inflected forms of a specified lexeme within a given language family.
List word senses
Fetch all senses (meanings) related to a word.
Transform text
Translate or paraphrase text.