Free tool · no sign-up
Toxicity and profanity checker
Paste a message and see how an AI moderation model reads it: toxicity, insults, hate speech, threats, sexual content, self-harm, advertising, profanity and slurs. It works in 26 languages, takes conversation context and your own rule, and stores nothing.
Scores go from 0 to 1. A category is flagged when its score passes the threshold (the tick on each bar); every server can set its own thresholds.
What it checks
Toxicity
Rude, disrespectful or aggressive messages, insults and threats included.
Insults, hate and threats
Attacks on a person, attacks on people for who they are, threats of violence or harm.
Profanity
Swearing and vulgar language. A swear word between friends is profanity, but not necessarily toxic: the two are scored apart.
Slurs
Racial, xenophobic, antisemitic, homophobic, transphobic and ableist slurs from word lists in six languages, found even inside friendly sentences.
Sexual content, self-harm and advertising
Each with its own score and threshold.
Your own rule
Write a rule in plain language, such as “No spoilers”, and see how the message scores against it.
How it works
- The same model as the VigiMod API: a multilingual model that reads each category as a sentence and answers whether the message matches it.
- Leetspeak, spaced letters and lookalike characters are normalized before scoring (“1d10t”, “i d i o t”).
- A category is flagged when its score passes its threshold, the tick on each bar. In the API every community can set its own thresholds.
- Messages are checked and discarded: nothing you type is stored or used to train models. The tool allows a few checks per minute.
Questions
Is the toxicity checker free?
Yes, with no account. For more than a few checks a minute, or to check messages from your own app, create a free API key: 120 messages per minute during the beta.
Which languages does it support?
It was trained on 26 languages and works best in English, Italian, Spanish, French, German and Portuguese. The slur lists cover those six.
What is the difference between toxicity and profanity?
Profanity is about the words (swearing, vulgar language); toxicity is about the intent (rude, hostile, aggressive). “This game is so damn good” has profanity but is friendly; a polite sentence can still be an insult.
Can I use it to replace Perspective API?
Yes: the VigiMod API answers the same comments:analyze requests as Perspective, with TOXICITY, PROFANITY and the other attributes. See the Perspective API alternative page.
Is what I type saved?
No. The message is sent to the model, scored and discarded. Only an anonymous count of checks is kept.
Keep learning
All guides- Basics · 5 min readFalse positives and false negatives in content moderationEvery moderation system makes two kinds of mistakes. What they are, what each one costs a community and how to keep both low.
- Intermediate · 6 min readHow to choose a moderation thresholdA score of 0.7 is not a decision. How thresholds work, why the default is only a starting point and a simple method to tune them on your own messages.
- Basics · 5 min readWhy context matters in chat moderationThe same sentence can be harmless or harmful depending on what came before. How conversation context changes moderation, with real examples.
Check messages from your own app
Free API key, 120 messages per minute during the beta.