Welcome to Azure Cognitive Services Documentation
Azure Cognitive Services provide cloud-based AI capabilities that developers can use to build intelligent applications without requiring deep machine learning expertise. These services span across vision, speech, language, decision, and search, enabling you to add advanced AI features to your applications easily.
Leverage the power of Microsoft's cutting-edge AI research and make your applications more engaging, accessible, and intelligent. Whether you're building a new application or enhancing an existing one, Cognitive Services offers the building blocks for a wide range of AI-powered solutions.
Getting Started
To begin using Azure Cognitive Services, you'll need an Azure subscription. You can create a free account to explore services with free tiers.
- Sign up for an Azure account.
- Create a Cognitive Services resource in the Azure portal. This will provide you with an API key and endpoint.
- Choose a service and start integrating its API into your application.
Refer to the individual service pages for detailed setup and usage instructions.
Vision Services
Empower your applications with the ability to "see" and interpret visual information.
Computer Vision
Analyze images to detect objects, text, faces, and generate descriptions. Extract information from images to automate tasks and gain insights.
Key Features:
- Image Analysis (tags, captions, categories)
- Optical Character Recognition (OCR)
- Landmark Detection
- Adult Content Detection
Learn more about Computer Vision API.
Face API
Detect, analyze, and recognize human faces in images. Verify identities and find similar faces.
Key Features:
- Face Detection (attributes like age, emotion, glasses)
- Face Recognition and Verification
- Face Grouping
Explore the Face API documentation.
Form Recognizer
Extract text, key-value pairs, and table data from your documents (PDFs, JPEGs, PNGs, TIFFs). Train custom models for your specific document types.
Key Features:
- Prebuilt Models for Invoices, Receipts, IDs
- Custom Model Training
- Layout Analysis
Discover the capabilities of Form Recognizer.
Speech Services
Add voice capabilities to your applications, enabling natural interaction through speech.
Speech to Text
Transcribe spoken audio into text in real-time or batch mode. Supports numerous languages and dialects.
// Example: Basic Speech to Text
const SpeechSDK = require("microsoft-cognitiveservices-speech-sdk");
const speechConfig = SpeechSDK.SpeechConfig.fromSubscription("YOUR_SPEECH_KEY", "YOUR_SPEECH_REGION");
const audioConfig = SpeechSDK.AudioConfig.fromDefaultMicrophoneInput();
const recognizer = new SpeechSDK.SpeechRecognizer(speechConfig, audioConfig);
recognizer.recognizeOnceAsync(
result => {
console.log(`RECOGNIZED: Text=${result.text}`);
recognizer.close();
},
error => {
console.log(`ERRORED: ${error}`);
recognizer.close();
});
Dive into the Speech to Text API.
Text to Speech
Convert written text into natural-sounding, lifelike speech. Choose from a wide variety of voices and languages.
Explore the Text to Speech API.
Speaker Recognition
Identify or verify speakers based on their voice. Useful for authentication and personalized experiences.
Learn about Speaker Recognition.
Language Services
Understand and process human language for insights and automation.
Text Analytics
Extract key phrases, detect sentiment, identify entities, and more from your text data.
Key Features:
- Sentiment Analysis
- Key Phrase Extraction
- Named Entity Recognition (NER)
- Language Detection
Get started with Text Analytics.
Translator
Translate text between a vast number of languages, enabling global communication.
Discover the Translator API.
QnA Maker
Create conversational question-and-answer bots from existing FAQ documents, URLs, or unstructured data.
Build intelligent bots with QnA Maker.
Decision Services
Make smarter decisions in your applications with recommendations and content moderation.
Anomaly Detector
Identify unusual patterns and outliers in time-series data to detect anomalies.
Learn about Anomaly Detector.
Content Moderator
Detect potentially offensive, unwelcome, or unsafe content in text, images, and videos.
Implement content moderation with the Content Moderator API.
Search Services
Integrate web search capabilities into your applications.
Bing Search APIs
Access Bing's powerful search capabilities to find relevant information on the web, including web pages, images, news, and videos.
SDKs and Tools
We provide comprehensive SDKs for popular programming languages like Python, C#, Java, JavaScript, and Go. Use these SDKs to simplify integration with Cognitive Services.
You can also explore our Quickstarts and Tutorials for hands-on experience.
Sample Code
Find a rich collection of code samples and examples on our GitHub repository. These samples cover various use cases and demonstrate how to leverage the full potential of Cognitive Services.
Support
For technical assistance, visit the Azure Support page or explore our Community Forums.