← LeaderboardThe Skill Leaderboard

azure-ai

Build and troubleshoot Azure AI Search, Speech, OpenAI, and Document Intelligence apps. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, Speech SDK logs, session ID, result ID, OCR, convert text to speech.

Published by microsoft ↗microsoft/skills

Try your first task

A source-grounded starter task has not been verified for this skill yet.

SKILL.md

name: azure-aidescription: "Build and troubleshoot Azure AI Search, Speech, OpenAI, and Document Intelligence apps. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, Speech SDK logs, session ID, result ID, OCR, convert text to speech."license: MITmetadata:   author: Microsoft  version: "1.2.3"

Azure AI Services

Services

ServiceUse WhenMCP ToolsCLI
AI SearchFull-text, vector, hybrid searchazure__searchaz search
SpeechSpeech-to-text, text-to-speech, SDK logsazure__speech-
OpenAIGPT models, embeddings, DALL-E-az cognitiveservices
Document IntelligenceForm extraction, OCR--

MCP Server (Preferred)

When Azure MCP is enabled:

AI Search

  • azure__search with command search_index_list - List search indexes
  • azure__search with command search_index_get - Get index details
  • azure__search with command search_query - Query search index

Speech

  • azure__speech with command speech_transcribe - Speech to text
  • azure__speech with command speech_synthesize - Text to speech

If Azure MCP is not enabled: In Copilot CLI or Claude Code, ask the user to run /mcp and enable Azure MCP; in other hosts, ask the user to enable Azure MCP through the host's MCP configuration.

AI Search Capabilities

FeatureDescription
Full-text searchLinguistic analysis, stemming
Vector searchSemantic similarity with embeddings
Hybrid searchCombined keyword + vector
AI enrichmentEntity extraction, OCR, sentiment

Speech Capabilities

FeatureDescription
Speech-to-textReal-time and batch transcription
Text-to-speechNeural voices, SSML support
Speaker diarizationIdentify who spoke when
Custom modelsDomain-specific vocabulary
Client SDK diagnosticsSpeech SDK client diagnostics for log collection, offline analysis, features, and session/result IDs (no MCP or login required)

SDK Quick References

For programmatic access to these services, see the condensed SDK guides:

Service Details

For deep documentation on specific services: