Installation
Initialize the client
Detect unsafe content
Scan a single text input for harmful content across all KOSA categories.Detect grooming patterns
Analyze a conversation history for grooming indicators.Analyze emotions
Evaluate emotional well-being from conversation text.Analyze voice
Upload an audio file for transcription and safety analysis.Hook integration
The SDK exports a
useTuteliq hook for convenient usage within React components.Fraud detection and safety extended
These methods cover financial exploitation, romance scams, and coercive behaviour targeting minors. Other endpoints —detectAppFraud, detectMuleRecruitment, detectGamblingHarm, detectCoerciveControl, and detectRadicalisation — follow the same call pattern shown here.
Detect social engineering
Identify manipulation tactics designed to trick a child into disclosing information or taking unsafe actions.Detect romance scam
Analyze text for romantic manipulation patterns that may indicate an adult posing as a peer.Detect vulnerability exploitation
Detect attempts to identify and target emotional or situational vulnerabilities in a child.Analyse multiple endpoints in one request
Run multiple detection endpoints on a single piece of content in one API call.analyseMulti is billed per detection endpoint, not per request.Error handling
The SDK throws typed errors that you can catch and inspect.Configuration options
Next steps
API Reference
Explore the full API specification.
Node.js SDK
See the Node.js SDK guide.