Apply moderation rules across 50+ languages with translation-aware detection.
Messages are automatically language-detected and translated internally before being evaluated against your toxicity and spam rules. This means a toxic message in Korean, Arabic, or Portuguese is caught with the same accuracy as English.
Over 50 languages are supported including: English, Spanish, French, German, Portuguese, Russian, Japanese, Korean, Chinese, Arabic, Hindi, Turkish, and more.
Enable under Dashboard → Auto Moderation → Multi-Lingual. No additional setup is needed — once enabled, all existing rules apply across all detected languages automatically.