What languages does the profanity filter support?
Our profanity filter supports 20+ languages including English, Spanish, French, German, Portuguese, and more. We continuously update our word lists.
Can I add custom words to filter?
Yes! Premium plans allow you to add custom blocklists and allowlists to tailor the filtering to your community standards.
How does spam detection work?
Our spam detector uses machine learning to analyze text patterns, link density, repetition, and other signals to identify spam with high accuracy.
Is the API suitable for real-time chat moderation?
Absolutely. Our APIs have sub-100ms response times, making them perfect for real-time chat, comments, and live content moderation.
Is there a free tier available?
Yes! The free tier includes 1,000 API calls per month for development and testing purposes. Commercial use requires a paid plan. Check our pricing page for details.
Can you detect leetspeak variations?
Yes! Our filter catches creative spellings like a$$, sh1t, and f**k by normalizing text and using pattern matching to identify profanity regardless of spelling tricks.
What are the rate limits?
Rate limits vary by plan. Check our pricing page for details. Our plans support high-volume moderation with sub-100ms response times for real-time use.
How do you handle false positives?
Our filter aims to minimize false positives using context-aware detection. Premium plans offer allowlist customization to whitelist specific terms for your use case.
How does the profanity count help with moderation?
The API returns a count of profane words detected. You can use this to implement tiered moderation—for example, auto-censor single instances but flag content with multiple violations for review.
Do you provide auto-censored text?
Yes! The API can return auto-censored versions of text with profanity replaced by asterisks or your custom replacement character.
