Sightengine Text Moderation
API that detects insults, sexual content, discriminatory language and personal information such as emails, phone numbers and social security numbers in user text, including deliberate obfuscation, in many languages.
Find alternatives to Sightengine Text Moderation
What it does
- Guardrails and safety
Sources
- Pricing
-
Pricing page: Free tier 'Basic Content Moderation' (2,000 operations / month), Starter $29 /mo, Pro $99 /mo, Enterprise 'Custom number of operations', each with '+ $0.002 per additional op'. Plan table lists 'Text Moderation: Detect profanity, personal information and harmful text'.
- Description
-
Official documentation · 7 Nov 2026
Page copy: 'Our Text Moderation API has been designed and battle-tested on all sorts of text inputs. It is available in many languages'; 'Our smart filters will work even when users actively try to circumvent them. Using Natural Language Analysis and Proprietary Algorithms'.
- What it does
-
Official documentation · 7 Nov 2026
Page copy: 'Our Text Moderation API has been designed and battle-tested on all sorts of text inputs. It is available in many languages'; 'Our smart filters will work even when users actively try to circumvent them. Using Natural Language Analysis and Proprietary Algorithms'.
- Sold within
-
Official documentation · 7 Nov 2026
Presented as its own entry in the Products menu with its own page; no parent offering is named.
- Name
-
Official documentation · 7 Nov 2026
Page title 'Text Moderation API: Detect and filter inappropriate content in any text'; menu 'Text Moderation: Detect and filter unwanted text-based content.'
- URL
-
Official documentation · 7 Nov 2026
Product page, HTTP 200, read 2026-11-07.
Also from Sightengine
-
API models that score whether an image or a video was generated by an AI model, trained on generators such as Veo, Sora, Runway, Pika and Midjourney, sold on Sightengine's operations-based plans with a free tier.
-
Sightengine Deepfake Detection API service
An API model and web checker that uses face analysis to flag face swaps and other facial manipulations in images and videos, sold on Sightengine's operations-based plans from the Starter tier.
-
Sightengine AI Voice Detection API service
A REST API that scores whether a voice recording is AI-generated speech from its waveform alone, without watermarks or metadata, and breaks the verdict down across 55 named voice generators such as ElevenLabs, OpenAI, PlayHT and Resemble.
-
Sightengine AI Music Detection API service
An API and upload checker that flags AI-made music tracks from the audio content itself, trained on generators such as Suno, Udio, ElevenLabs, Riffusion and MusicGen, with API access on Sightengine's Pro plan and above.
-
Sightengine Image Moderation API service
API that classifies images against more than 100 moderation classes across fifteen top-level categories such as nudity, violence, hate symbols, weapons and drugs, returning scores so a platform can allow, block or escalate user-uploaded images.
-
Sightengine Video Moderation API service
API that moderates recorded videos and live streams for nudity, violence, gore, hate symbols, weapons and drugs, returning timestamped detections and per-policy thresholds so a platform can remove, blur or escalate only the offending segments.
-
Sightengine Audio Moderation API service
API that analyses the audio track of video and audio files in multiple languages across 18 categories such as profanity, hate, personal information, drugs and violence, returning the matching words with timestamps.
-
Sightengine Face Liveness Detection API service
Passive face anti-spoofing API that scores from a single selfie whether the face is a live person or a presentation attack such as a screen replay, printed photo, mask, deepfake or AI-generated face, with a rejection reason when the capture fails.
Open Sightengine in the directory
Something wrong here? Send a correction — quote this product id: sightengine-text-moderation.