Screen text for profanity and blocklist matches
One step with Microsoft Azure. We can help you get access.
Look something up
Screen text for profanity and blocklist matches
with Microsoft Azure
Use Microsoft Azure: its Microsoft Azure Content Moderator Client Text Moderation API lets you screen text for profanity and blocklist matches in a single step (POST /contentmoderator/moderate/v1.0/ProcessText/Screen/). capabilities.work can help you get signed up and connected.
- How do I check user comments for profanity before publishing them?
- Can I screen text against my own custom blocklist and detect personal data at the same time?
- What's the maximum length of text I can send for moderation?
Say it to your AI assistant
- Screen this text for profanity: {text}.
- Check {text} against custom blocklist {list_id} and flag any PII ({pii}).
- Moderate {text} in language {language} with classification turned on ({classify}).
For your developer
POST /contentmoderator/moderate/v1.0/ProcessText/Screen/ in Microsoft Azure Content Moderator Client Text Moderation API. Full spec on APIs.io.