AI TOOL PROFILE
Tisane Content Moderation API
- Customer Support
- Communication API
- Trust and Safety teams
- Gaming platform operators
- Online marketplace managers
- Threat intelligence organizations
Pricing
Pricing is tiered based on request volume, with a free plan offering 50,000 requests per month and paid plans starting at $99/month.
At a glance
- Best for
- Trust and Safety teams, Gaming platform operators, Online marketplace managers, Threat intelligence organizations
- Key use cases
- Gaming Community Moderation, Marketplace Trust and Safety, Threat Intelligence, Enterprise Communication Compliance
- Integrations
- Slack, Webex, Minecraft, Discord, YouTube
- Official website
- Visit tisane official website
How AI is used
Tisane is an NLP-driven API focused on the moderation of user-generated content. It is designed to identify problematic text, including hate speech, cyberbullying, and PII exfiltration, with a focus on language that uses obfuscation or errors to bypass standard filters.
The tool is intended for organizations managing online communities, such as gaming platforms, digital marketplaces, and threat intelligence teams. It supports several deployment methods, including SaaS, on-premise, and embedded options, allowing businesses to choose based on their privacy and infrastructure requirements.
Beyond filtering, the software supports translation of problematic language in 35 different languages and can extract specific topics or entities from text. This may help moderation teams understand the context of offensive content that standard translation tools may miss.
Buyers should confirm their monthly request volume and technical requirements, as different pricing tiers offer varying rate limits and levels of technical support.
Key Features
Content Moderation
Detects insults, hate speech, profanities, and sexual harassment in user text.
Adversarial Text Detection
Identifies algospeak, character substitutions, and obfuscated text designed to evade blocks.
Multilingual Support
Supports language identification and translation of problematic content across 35 languages.
PII Exfiltration Detection
Scans for the unauthorized sharing of personally identifiable information.
Flexible Deployment
Available as cloud-based SaaS, on-premise installation, or embedded within applications.
Entity and Topic Extraction
Supports topic modeling and the extraction of specific entities from user content.
Use Cases
Gaming Community Moderation
Monitoring in-game chat and usernames for insults and harassment.
Marketplace Trust and Safety
Detecting fraudulent schemes or adult advertising in user profiles.
Threat Intelligence
Identifying criminal activity and extremist content in user-generated data.
Enterprise Communication Compliance
Scanning messages in tools like Slack and Webex for HR compliance and inappropriate content.
Integrations
- Slack
- Webex
- Minecraft
- Discord
- YouTube
- Zapier
- Make
- Pipedream
- n8n
- Maltego
FAQ
What is Tisane and who is it for?
- Tisane is an NLP API designed for content moderation. It is primarily used by trust and safety teams, gaming platforms, and online marketplaces to detect problematic user-generated content.
Does Tisane offer a free version?
- Yes, there is a free community plan that includes 50,000 requests per month, though it does not include technical support or customization.
How is Tisane deployed?
- Tisane can be deployed as a cloud-based SaaS, installed on-premise on your own infrastructure, or embedded directly into server, desktop, or mobile applications.
Source category: Customer Support
Source subcategory: Communication API
More tools in Customer Support
Other published listings in the Customer Support category.
More tools in the Communication API software type
Related listings that share the same software type for comparison and shortlisting.
