The Tuteliq .NET SDK provides an async client for the Tuteliq child safety API. It supports .NET 6.0+ and ships with full XML documentation and nullable reference type annotations.
Installation
Install via NuGet:
dotnet add package Tuteliq
Initialize the client
using Tuteliq;
var tuteliq = new TuteliqClient("YOUR_API_KEY");
Never hardcode API keys in source code. Use IConfiguration, user secrets, or a secrets manager.
using Microsoft.Extensions.Configuration;
var config = new ConfigurationBuilder()
.AddUserSecrets<Program>()
.Build();
var tuteliq = new TuteliqClient(config["Tuteliq:ApiKey"]);
Detect unsafe content
Scan a single text input for harmful content across all KOSA categories.
var result = await tuteliq.DetectUnsafeAsync(
text: "Let's meet at the park after school, don't tell your parents",
ageGroup: AgeGroup.TenToTwelve
);
Console.WriteLine(result.Safe); // false
Console.WriteLine(result.Severity); // Severity.High
Console.WriteLine(result.Categories); // [Category.Grooming, Category.Secrecy]
Detect grooming patterns
Analyze a conversation history for grooming indicators.
var result = await tuteliq.DetectGroomingAsync(
messages: new[]
{
new Message(Role.Stranger, "Hey, how old are you?"),
new Message(Role.Child, "I'm 11"),
new Message(Role.Stranger, "Cool. Do you have your own phone?"),
new Message(Role.Stranger, "Let's talk on a different app, just us"),
},
ageGroup: AgeGroup.TenToTwelve
);
Console.WriteLine(result.GroomingDetected); // true
Console.WriteLine(result.RiskScore); // 0.92
Console.WriteLine(result.Stage); // GroomingStage.Isolation
Analyze emotions
Evaluate emotional well-being from conversation text.
var result = await tuteliq.AnalyzeEmotionsAsync(
text: "Nobody at school talks to me anymore. I just sit alone every day.",
ageGroup: AgeGroup.ThirteenToFifteen
);
Console.WriteLine(result.Emotions); // [Emotion { Label = "sadness", Score = 0.87 }, ...]
Console.WriteLine(result.Distress); // true
Console.WriteLine(result.RiskLevel); // RiskLevel.Elevated
Analyze voice
Upload an audio file for transcription and safety analysis.
var audioBytes = await File.ReadAllBytesAsync("recording.wav");
var result = await tuteliq.AnalyzeVoiceAsync(
file: audioBytes,
ageGroup: AgeGroup.ThirteenToFifteen
);
Console.WriteLine(result.Transcript);
Console.WriteLine(result.Safe);
Console.WriteLine(result.Emotions);
Dependency injection
The SDK provides extension methods for IServiceCollection to integrate with ASP.NET Core dependency injection.
// Program.cs or Startup.cs
builder.Services.AddTuteliq(options =>
{
options.ApiKey = builder.Configuration["Tuteliq:ApiKey"];
options.Timeout = TimeSpan.FromSeconds(30);
options.Retries = 2;
});
ITuteliqClient into your controllers or services:
public class ModerationService
{
private readonly ITuteliqClient _tuteliq;
public ModerationService(ITuteliqClient tuteliq)
{
_tuteliq = tuteliq;
}
public async Task<bool> IsContentSafe(string text, AgeGroup ageGroup)
{
var result = await _tuteliq.DetectUnsafeAsync(text, ageGroup);
return result.Safe;
}
}
Error handling
The SDK throws typed exceptions that you can catch and inspect.
using Tuteliq;
try
{
var result = await tuteliq.DetectUnsafeAsync(
text: "some content",
ageGroup: AgeGroup.TenToTwelve
);
}
catch (TuteliqException ex)
{
Console.WriteLine(ex.Code); // e.g. "AUTH_INVALID_KEY"
Console.WriteLine(ex.Message); // human-readable description
Console.WriteLine(ex.Status); // HTTP status code
}
Configuration options
var tuteliq = new TuteliqClient(new TuteliqOptions
{
ApiKey = config["Tuteliq:ApiKey"],
BaseUrl = "https://api.tuteliq.ai", // default
Timeout = TimeSpan.FromSeconds(30), // request timeout
Retries = 2 // automatic retries on failure
});
Next steps
