azure-ai
microsoft/azure-skills
Access Azure AI Search, Speech, OpenAI, and Document Intelligence services for search, transcription, and OCR.
What is azure-ai?
Integrates Azure AI services including AI Search (full-text, vector, hybrid), Speech (transcription, text-to-speech), OpenAI models, and Document Intelligence. Use when you need semantic search, speech processing, embeddings, or form/document extraction.
- Query AI Search indexes with full-text, vector, and hybrid search
- Transcribe speech to text and synthesize text to speech with neural voices
- Extract data from forms and documents with OCR
- List and retrieve search index details
- Support speaker diarization and custom speech models
- Access GPT models and embeddings via Azure OpenAI
How to install azure-ai
npx skills add https://github.com/microsoft/azure-skills --skill azure-ai- Azure subscription with AI Search, Speech, or Document Intelligence resources provisioned
- Azure MCP server enabled (or run `/azure:setup` to configure)
- Appropriate Azure credentials and service endpoints configured
How to use azure-ai
- 1.Install the skill via `npx skills add https://github.com/microsoft/azure-skills --skill azure-ai`
- 2.Enable Azure MCP via `/mcp` or run `/azure:setup` if not already enabled
- 3.Use `azure__search` tools to list indexes, get details, or query with `search_query`
- 4.Use `azure__speech` tools to transcribe audio with `speech_transcribe` or generate speech with `speech_synthesize`
- 5.Reference SDK guides for programmatic access in Python, TypeScript, .NET, or Java
Use cases
- Build semantic search over document collections using vector embeddings
- Transcribe audio files or real-time speech input for accessibility or analysis
- Extract structured data from scanned forms or PDFs
- Implement hybrid search combining keyword matching with semantic similarity
- Generate speech output with multiple neural voices and SSML support
- Backend developers integrating Azure AI services
- Search engineers building semantic or vector search
- Applications requiring speech-to-text or text-to-speech
- Document processing and data extraction workflows
- Teams using Azure cloud infrastructure
azure-ai FAQ
Full-text search uses linguistic analysis and stemming for keyword matching. Vector search finds semantic similarity using embeddings. Hybrid search combines both approaches for better relevance.
Yes, Azure MCP must be enabled. If not already active, run `/azure:setup` or enable it via `/mcp`.
Yes, the Speech service supports custom models for domain-specific vocabulary and improved accuracy.
Document Intelligence handles forms, PDFs, and scanned documents for structured data extraction and OCR.
SDK references are provided for Python, TypeScript, .NET, and Java for programmatic access to all services.
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: "1.2.1"
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.
