Tisane

Overview

Tisane provides a suite of natural language processing (NLP) APIs designed for text analysis and content moderation, offering developers tools to understand and manage textual data programmatically. Established in 2015, the platform focuses on identifying and categorizing various aspects of human language, from sentiment and intent to potentially harmful content such as hate speech and profanity. This functionality is delivered through a RESTful API, allowing integration into diverse applications across web, mobile, and backend systems.

The core utility of Tisane lies in its ability to process unstructured text and extract meaningful insights. For instance, its Text Analysis API can dissect sentences to identify named entities—persons, organizations, locations—and determine the overall sentiment (positive, negative, neutral) expressed within a piece of text. This is particularly valuable for applications in customer support, where analyzing feedback can provide actionable insights into user satisfaction, or in social media monitoring, where tracking public opinion about a brand or topic is critical. The API supports a broad range of languages, extending its applicability to global markets and multilingual content.

Beyond general text analysis, Tisane specializes in content moderation. Its Profanity Filter and Hate Speech Detection capabilities are designed to help platforms maintain brand safety and foster positive user environments. These features can automatically flag or filter content that violates community guidelines, reducing the need for manual review processes. This makes Tisane suitable for social networks, forums, gaming platforms, and e-commerce sites that deal with user-generated content. For academic researchers, Tisane offers tools to analyze large text corpora for linguistic patterns, aiding studies in social sciences, linguistics, and digital humanities.

Developers can integrate Tisane using various SDKs, including Python, Node.js, Java, PHP, Ruby, Go, C#, and Rust, simplifying API calls and data handling. The platform offers a free tier for initial exploration and development, providing up to 500,000 requests per month. This allows teams to prototype solutions and assess the API's capabilities before committing to paid plans. Tisane also emphasizes data privacy and compliance, particularly with GDPR regulations, which is a key consideration for applications handling user data in the European Union.

Compared to broader AI platforms like Google Cloud Natural Language API or Amazon Comprehend, Tisane carves out a niche with its focused approach to content moderation and linguistic analysis, often providing more granular control over specific types of harmful content detection. This specialization can be advantageous for organizations whose primary need is robust and accurate content filtering rather than a general-purpose NLP toolkit. For example, a gaming company might choose Tisane to specifically target in-game chat toxicity, while a marketing firm might use it to analyze brand mentions for sentiment trends. The detailed Tisane API reference documentation outlines the various endpoints and parameters for these specialized tasks.

Key features

• Text Analysis API: Processes raw text to extract linguistic information, including part-of-speech tagging, sentence boundaries, and dependency parsing, providing a foundational understanding of textual structure.
• Profanity Filter: Identifies and flags profanity, vulgarity, and offensive language across multiple languages, assisting in maintaining appropriate content standards.
• Hate Speech Detection: Utilizes machine learning models to detect various forms of hate speech, including discrimination based on race, religion, gender, and sexual orientation, contributing to safer online environments.
• Sentiment Analysis: Determines the emotional tone of text, classifying it as positive, negative, or neutral, valuable for understanding public opinion and customer feedback.
• Named Entity Recognition (NER): Automatically identifies and categorizes key entities in text, such as names of persons, organizations, locations, dates, and quantities, supporting data extraction and information retrieval.
• Extensive Language Support: Offers analysis capabilities across a wide array of languages, enabling global content moderation and multilingual application development.
• Developer SDKs: Provides client libraries for Python, Node.js, Java, PHP, Ruby, Go, C#, and Rust, simplifying integration and reducing development time.
• GDPR Compliance: Adheres to General Data Protection Regulation (GDPR) standards, ensuring consumer data privacy and protection for users in the EU.

Pricing

Tisane offers a free tier for developers and organizations with lower usage requirements, and structured paid plans for higher volumes. Pricing is primarily based on the number of API requests per month.

Pricing as of May 2026. For the most current details, refer to the official Tisane pricing information.

Common integrations

Tisane's API is designed for flexible integration into various platforms and workflows. Developers typically integrate Tisane into:

• Social Media Platforms: For real-time content moderation, filtering user-generated posts, comments, and direct messages to detect hate speech or profanity.
• Customer Support Systems: To analyze incoming tickets, chat logs, and customer feedback for sentiment and key topics, allowing for better prioritization and response management.
• E-commerce Websites: Moderating product reviews and user comments to ensure brand safety and prevent spam or inappropriate content.
• Online Gaming Platforms: Monitoring in-game chat and user profiles for toxic behavior, profanity, and hate speech to foster a positive gaming environment.
• Academic and Research Tools: Integrating into data analysis pipelines for large-scale linguistic research, sentiment analysis of public discourse, or content classification.
• Content Management Systems (CMS): Automating the review process for user-submitted articles, blog comments, or forum posts before publication.

Alternatives

• OpenAI: Offers a broad range of AI models, including advanced language models for text generation, summarization, and more general-purpose natural language understanding tasks.
• Google Cloud Natural Language API: Provides robust NLP services for entity recognition, sentiment analysis, syntax analysis, and content classification, integrated within the Google Cloud ecosystem.
• Amazon Comprehend: An AWS service offering NLP capabilities such as sentiment analysis, entity recognition, keyphrase extraction, and topic modeling, designed for integration into AWS-based applications.

Getting started

To begin using Tisane, developers typically sign up for an API key, then use one of the provided SDKs to make requests. The following Python example demonstrates how to perform a basic text analysis, specifically checking for profanity.

import requests
import json

# Replace with your actual API key from Tisane
API_KEY = "YOUR_TISANE_API_KEY"

def analyze_text_for_profanity(text_to_analyze):
    headers = {
        "X-API-KEY": API_KEY,
        "Content-Type": "application/json"
    }
    payload = {
        "language": "en", # Specify the language of the text
        "text": text_to_analyze,
        "settings": {
            "filter": {
                "profanity": True # Request profanity filtering
            }
        }
    }
    
    try:
        response = requests.post("https://api.tisane.ai/v1/analyze", headers=headers, data=json.dumps(payload))
        response.raise_for_status() # Raise an HTTPError for bad responses (4xx or 5xx)
        
        analysis_results = response.json()
        
        if "filter" in analysis_results and "profanity" in analysis_results["filter"]:
            profanity_status = analysis_results["filter"]["profanity"]
            print(f"Profanity detected: {profanity_status['detected']}")
            if profanity_status["detected"]:
                print("Details:")
                for item in profanity_status["items"]:
                    print(f"  Word: '{item['word']}', Severity: {item['severity']}")
        else:
            print("No profanity filter results found in the response.")

    except requests.exceptions.HTTPError as http_err:
        print(f"HTTP error occurred: {http_err} - {response.text}")
    except requests.exceptions.ConnectionError as conn_err:
        print(f"Connection error occurred: {conn_err}")
    except requests.exceptions.Timeout as timeout_err:
        print(f"Timeout error occurred: {timeout_err}")
    except requests.exceptions.RequestException as req_err:
        print(f"An error occurred: {req_err}")
    except json.JSONDecodeError:
        print(f"Failed to decode JSON from response: {response.text}")

# Example usage:
text1 = "This is a perfectly fine sentence."
text2 = "What the heck is wrong with this stupid comment?"

print("Analyzing text 1:")
analyze_text_for_profanity(text1)
print("\nAnalyzing text 2:")
analyze_text_for_profanity(text2)

This Python script uses the requests library to send a POST request to the Tisane API. It specifies the language as English and requests profanity filtering. The response is then parsed to check if profanity was detected and to display any identified words along with their severity. Developers can find more detailed examples and language-specific instructions in the Tisane documentation.