VISIONDetection APIs
Each page covers one kind of harmful content that Detectivision's API finds in text or images, such as nudity, hate speech, toxicity, violence or self-harm. It says which flags find it and what the answer contains, and shows a request you can send. For every flag and what each one means, see the flags page of the docs.
Find swear words in chat, comments and usernames in ten languages with one API call: separate flags for profanity and insults, no word list to maintain.
Find hate speech, racism and sexism in text written in ten languages, and hateful images, with one API call. Each flag comes with how sure it is.
Detect nudity and sexual content in images, and sexual language in text written in ten languages, with one API call and a confidence for each finding.
Spot talk of suicide and self-harm in messages written in ten languages, so the right people can reach out in time. One API call per text.
Check comments and chat messages for insults, hate, harassment and self-harm in ten languages, with a flag for each kind of toxicity.
Detect insults, hate speech, racism, sexism and sexual harassment in Turkish text, and in English too, with one API call and a confidence per flag.
Find violent images before they are posted. One API call per image tells you whether it shows violence and how sure the check is.