12 Services from ai.kagurazaka.dev

Extracts named entities (persons, locations, organizations, dates, etc.) with character offsets and confidence scores from text using Amazon Comprehend, with optional language auto-detection.

Detects explicit, suggestive, violent, drug, hate, and other unsafe content in a JPEG or PNG image at a URL using Amazon Rekognition, returning a safe flag and any flagged labels.

Detects personally identifiable information (names, addresses, emails, phone numbers, SSNs, credit cards, passwords, IPs, etc.) in English or Spanish text using Amazon Comprehend, returning entity types, offsets, confidence scores, and a redacted version of the text.

Reads printed and handwritten text from a JPEG, PNG, TIFF, or single-page PDF at a URL using Amazon Textract, returning full text, per-line content, confidence scores, and bounding box positions.

Detects words and lines of text in a JPEG or PNG image at a URL using Amazon Rekognition, returning up to 100 words with positions.

Classifies the sentiment of a text (positive, negative, neutral, mixed) using Amazon Comprehend and returns a confidence score for each class, with automatic language detection.

Detects the dominant language of a text (over 100 languages) using Amazon Comprehend, analyzing up to the first 1000 characters and returning ranked language codes with confidence scores.

Detects objects, scenes, activities, and concepts in a JPEG or PNG image at a URL using Amazon Rekognition, returning labels with confidence scores, categories, parent labels, and instance counts.

Translates up to 1500 characters of text between any of Amazon Translate's 75 supported languages, with automatic source language detection and optional formal/informal tone.

Detects up to 100 faces in a JPEG or PNG image URL using Amazon Rekognition, returning position, age range, emotions, facial attributes, pose, and image quality for each face — without identifying anyone.

Extracts key noun phrases from text using Amazon Comprehend, returning each phrase with its character offsets and confidence score, with automatic language detection.

Converts text to speech using Amazon Polly and returns a signed URL to the audio file, valid for one hour.