Overview
Tisane is a text analytics API specialized in detecting abusive content, hate speech, and cybercrime in user-generated text. It can identify personal attacks, profanity, sexual content, and other harmful language across 30+ languages. It is designed for content moderation platforms and law enforcement applications.
Beginner Tip
Tisane returns an "abuse" array with type labels like "personal_attack" or "hate_speech" — check this array first in your response handler. Use the "settings" object in your request to tune sensitivity thresholds for your specific moderation use case.
Available Data
The kind of data this API exposes, based on its documentation. We could not call the endpoint to confirm the exact field names.
Example Response
Illustrative shape only — we were not able to call this endpoint (it requires credentials or exposes no public sample URL), so the fields below show the kind of data this API returns rather than a recorded response.
{
"route": "Line 1",
"origin": "Station A",
"destination": "Station B",
"departure": "08:30",
"arrival": "09:15",
"status": "On Time",
"delays_min": 0
} Field Reference
abuse List of detected abusive content segments with type, severity, and text offset abuse[].type Category of abuse detected, e.g., "personal_attack", "hate_speech", "profanity", "sexual_advances" abuse[].severity Severity level of the detected abuse: "low", "medium", or "high" entities_detected Named entities such as people, places, and organizations found in the text sentiment Overall sentiment of the analyzed text: "positive", "negative", or "neutral" Implementation Example
Calls a real endpoint of this API. Replace any placeholder credentials with your own key.
const url = "https://api.tisane.ai/parse";
// Replace headers or query params with the values required by this API.
const response = await fetch(url, {
headers: {
"Authorization": "Bearer YOUR_API_KEY"
}
});
if (!response.ok) throw new Error(`Request failed: ${response.status}`);
const data = await response.json();
console.log(data); What Can You Build?
Note: These code examples are AI-generated and unverified. Always refer to the official API documentation for accurate usage.
Common Errors & Troubleshooting
Generated guidance based on this API's documentation, not observed by us. Treat it as a starting point and check against the provider's own error reference.
Metadata Score Breakdown
Estimated from metadata — endpoint not independently tested
Metadata estimate · endpoint not independently tested
Technical Specifications
Related Tags
Similar APIs
View All →apilayer languagelayer
apilayer languagelayer is a language detection API that identifies the language of any text across 173 supported languages.
Code Detection API
Code Detection API automatically identifies programming languages and detects code blocks within plain text or mixed content.
Semantria
Semantria is a powerful text analytics API by Lexalytics that provides sentiment analysis, entity extraction, and content categorization.
Watson Natural Language Understanding
IBM Watson Natural Language Understanding (NLU) is a powerful AI-driven API that extracts semantic meaning from text, including sentiment, entities, keywords, categories, and emotion.
ELI
ELI is a Natural Language Processing API specifically designed for the Thai language, offering tools like word segmentation, part-of-speech tagging, and named entity recognition.