azure-ai
microsoft/azure-skills
Azure AI services skill for Search, Speech, OpenAI, and Document Intelligence in coding agents
What is azure-ai?
This skill equips coding agents with knowledge and tooling to work with Azure AI services including AI Search (full-text, vector, hybrid, semantic), Speech (speech-to-text, text-to-speech), OpenAI (GPT, embeddings, DALL-E), and Document Intelligence (OCR, form extraction). It surfaces MCP tool commands for Search and Speech when Azure MCP is enabled, and provides SDK quick-reference guides for Python, TypeScript, .NET, Java, and more.
- Enables AI Search queries including full-text, vector, hybrid, and semantic search via MCP tools or SDK
- Supports speech-to-text transcription and text-to-speech synthesis via MCP tools or SDK
- Provides SDK reference guides for AI Search, OpenAI, Speech, Document Intelligence, Vision, Translation, and Content Safety
- Maps each Azure AI service to its relevant MCP tool commands and Azure CLI equivalents
- Guides setup of Azure MCP server when not already enabled
- Covers AI enrichment features like entity extraction, OCR, and sentiment analysis
How to install azure-ai
npx skills add https://github.com/microsoft/azure-skills --skill azure-ai- An Azure subscription with relevant AI services provisioned
- Azure MCP server enabled (for MCP tool commands) or Azure CLI installed
- Appropriate Azure credentials/API keys for the target services
- npx available to install the skill via the skills CLI
How to use azure-ai
- 1.Install the skill: npx skills add https://github.com/microsoft/azure-skills --skill azure-ai
- 2.Verify Azure MCP is enabled; if not, run /azure:setup or enable via /mcp
- 3.For AI Search, use the azure__search MCP tool with commands: search_index_list, search_index_get, or search_query
- 4.For Speech, use the azure__speech MCP tool with commands: speech_transcribe or speech_synthesize
- 5.For OpenAI or Document Intelligence, use the Azure CLI (az cognitiveservices) or reference the provided SDK guides
- 6.Select the SDK reference for your language (Python, TypeScript, .NET, Java) from the skill's references directory
- 7.Consult linked Microsoft Learn documentation for deep-dive indexing, query, or transcription patterns
Use cases
- Querying an Azure AI Search index with keyword, vector, or hybrid search
- Transcribing audio files or synthesizing speech from text
- Extracting structured data from forms and documents using Document Intelligence
- Building embeddings or calling GPT models via Azure OpenAI
- Integrating content safety checks or image analysis into an application
- Developers building search features on top of Azure AI Search
- Engineers implementing speech interfaces (voice input/output) in applications
- Developers working with Azure OpenAI for GPT or embedding workflows
- Teams doing document processing, OCR, or form extraction on Azure
- Coding agent users who want guided Azure AI SDK usage across Python, TypeScript, .NET, and Java
azure-ai FAQ
MCP tools (azure__search, azure__speech) require Azure MCP to be enabled. If it is not, the skill instructs you to run /azure:setup or enable it via /mcp. SDK-based access works independently of MCP.
AI Search, Speech (speech-to-text and text-to-speech), Azure OpenAI (GPT, embeddings, DALL-E), Document Intelligence (OCR, form extraction), Vision, Translation, and Content Safety.
Python, TypeScript, .NET (C#), and Java are covered, though not every service has a reference for every language.
Yes. The skill covers full-text, vector, hybrid, and semantic search capabilities in Azure AI Search, accessible via the azure__search MCP tool or the AI Search SDK.
No. The skill assumes Azure AI services are already provisioned. It provides tooling and guidance for interacting with existing resources.
Full instructions (SKILL.md)
Source of truth, from microsoft/azure-skills.
name: azure-ai description: "Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech." license: MIT metadata: author: Microsoft version: "1.1.1"
Azure AI Services
Services
| Service | Use When | MCP Tools | CLI |
|---|---|---|---|
| AI Search | Full-text, vector, hybrid search | azure__search | az search |
| Speech | Speech-to-text, text-to-speech | azure__speech | - |
| OpenAI | GPT models, embeddings, DALL-E | - | az cognitiveservices |
| Document Intelligence | Form extraction, OCR | - | - |
MCP Server (Preferred)
When Azure MCP is enabled:
AI Search
azure__searchwith commandsearch_index_list- List search indexesazure__searchwith commandsearch_index_get- Get index detailsazure__searchwith commandsearch_query- Query search index
Speech
azure__speechwith commandspeech_transcribe- Speech to textazure__speechwith commandspeech_synthesize- Text to speech
If Azure MCP is not enabled: Run /azure:setup or enable via /mcp.
AI Search Capabilities
| Feature | Description |
|---|---|
| Full-text search | Linguistic analysis, stemming |
| Vector search | Semantic similarity with embeddings |
| Hybrid search | Combined keyword + vector |
| AI enrichment | Entity extraction, OCR, sentiment |
Speech Capabilities
| Feature | Description |
|---|---|
| Speech-to-text | Real-time and batch transcription |
| Text-to-speech | Neural voices, SSML support |
| Speaker diarization | Identify who spoke when |
| Custom models | Domain-specific vocabulary |
SDK Quick References
For programmatic access to these services, see the condensed SDK guides:
- AI Search: Python | TypeScript | .NET
- OpenAI: .NET
- Vision: Python | Java
- Transcription: Python
- Translation: Python | TypeScript
- Document Intelligence: .NET | TypeScript
- Content Safety: Python | TypeScript | Java
Service Details
For deep documentation on specific services:
- AI Search indexing and queries -> Azure AI Search documentation
- Speech transcription patterns -> Azure AI Speech documentation
Related skills
More from microsoft/azure-skills and the wider catalog.
finetuning
Fine-tune models on Azure AI Foundry with SFT, DPO, or RFT training methods.
azure-deploy
Execute Azure deployments for prepared applications with built-in error recovery and validation.
azure-diagnostics
Debug Azure production issues using AppLens, Azure Monitor, resource health, and systematic triage.
azure-prepare
Generate Azure deployment infrastructure (Bicep/Terraform, azure.yaml, Dockerfiles) for new or existing apps
azure-storage
Azure Storage skill: Blob, File Shares, Queue, Table, and Data Lake with access tier guidance and lifecycle management
azure-validate
Pre-deployment validation for Azure readiness with configuration, infrastructure, and RBAC checks.