agentsclimarketplace

Azure speech

Skill MicrosoftDocs/Agent-Skills/skills/azure-speech

Expert knowledge for Azure AI Speech development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building STT/TTS containers, custom voices, Voice Live apps, SSML workflows, or telephony integrations, and other Azure AI Speech related development tasks. Not for Azure AI Bot Service (use azure-bot-service), Azure Communication Services (use azure-communication-services), Azure AI Immersive Reader (use azure-immersive-reader), Azure Translator (use azure-translator).From its SKILL.md

Install
npx -y skills add MicrosoftDocs/Agent-Skills --skill azure-speech

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

20.8 KB, ~4.5k tokens by cl100k_base, as published. Nobody here has run it

Azure AI Speech Skill

This skill provides expert guidance for Azure AI Speech. Covers troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.

How to Use This Skill

IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g., L35-L120), use read_file with the specified lines. For categories with file links (e.g., [security.md](security.md)), use read_file on the linked reference file

IMPORTANT for Agent: If metadata.generated_at is more than 3 months old, suggest the user pull the latest version from the repository. If mcp_microsoftdocs tools are not available, suggest the user install it: Installation Guide

This skill requires network access to fetch documentation content:

  • Preferred: Use mcp_microsoftdocs:microsoft_docs_fetch with query string from=learn-agent-skill. Returns Markdown.
  • Fallback: Use fetch_webpage with query string from=learn-agent-skill&accept=text/markdown. Returns Markdown.

Category Index

CategoryLinesDescription
TroubleshootingL36-L44Diagnosing and resolving Azure AI Speech issues: session/ID lookup, Foundry integration errors, SDK CRL/compatibility problems, container deployment failures, and common SDK runtime bugs.
Best PracticesL45-L60Guidance on preparing audio/video data, improving transcription and synthesis quality/latency, designing microphones, managing SDK memory, handling live voice chats, and backing up custom voice resources.
Decision MakingL61-L77Guides for choosing Azure Speech/Embedded/Voice Live options, checking language/voice availability, and step-by-step migrations between Speech/voice REST APIs and legacy features.
Limits & QuotasL78-L86Speech service limits, quotas, and behaviors for text-to-speech and custom/professional voice models, including training duration, deployment constraints, and managing model/endpoint lifecycles.
SecurityL87-L100Securing Azure AI Speech: auth (Entra, RBAC), network isolation (VNet, Private Link, sovereign clouds), encryption/BYOK, BYOS storage, and consent/ID flows for personal and professional voice.
ConfigurationL101-L133Configuring Azure AI Speech behavior: audio I/O, logging, storage, SSML, pronunciation, batch TTS/STT, avatars, personal/pro voices, and Voice Live/SDK/CLI connection and telemetry settings.
Integrations & Coding PatternsL134-L164Patterns and code for integrating Azure Speech/Voice Live with apps, telephony, agents, REST/SDK/WS APIs, TTS/translation/avatars, SSML customization, and LLM/OpenAI workflows.
DeploymentL165-L176Deploying and scaling Azure AI Speech: Docker/Kubernetes containers, on-prem STT/TTS, custom speech models/endpoints, language ID, and batch/long-form synthesis workflows.

Troubleshooting

TopicURL
Retrieve Speech to text session and transcription IDs for supporthttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-get-speech-session-id
Resolve common Azure Speech in Foundry issueshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/known-issues
Resolve Azure AI Speech SDK CRL compatibility issueshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-to-sdk-1-48-2
Troubleshoot Azure Speech containers deployment issueshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-faq
Diagnose and fix common Azure Speech SDK issueshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/troubleshooting

Best Practices

TopicURL
Prepare and locate audio data for batch transcriptionhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription-audio-data
Create high-quality human-labeled speech transcriptionshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-human-labeled-transcriptions
Prepare training data for professional custom voicehttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-voice-training-data
Apply best practices to reduce Speech synthesis latencyhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-lower-speech-synthesis-latency
Track and manage Azure Speech SDK memory usagehttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-track-speech-sdk-memory-usage
Handle interrupted responses in Voice Live chat historyhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-auto-truncation
Use phrase lists to improve Azure Speech accuracyhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/improve-accuracy-phrase-list
Apply keyword recognition design and accuracy guidelineshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/keyword-recognition-guidelines
Record high-quality samples for custom voice traininghttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/record-custom-voice-samples
Back up and recover custom Speech and Voice resourceshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/resiliency-and-recovery-plan
Design microphone arrays optimized for Speech SDKhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-sdk-microphone
Prepare high-quality video samples for custom avatarshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/custom-avatar-record-video-samples

Decision Making

TopicURL
Evaluate custom voice lite before professional voicehttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/custom-neural-voice-lite
Choose Embedded Speech for offline and hybrid scenarioshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/embedded-speech
Evaluate device suitability for embedded speech modelshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/embedded-speech-performance-evaluations
Check Azure Speech language and voice availabilityhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support
Migrate Speech to text REST API from v3.2 to 2024-11-15https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-2024-11-15
Migrate Speech to text REST API 2024-11-15 to 2025-10-15https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-2025-10-15
Migrate from retired Speech intent recognition to Language or OpenAIhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-intent-recognition
Migrate from Long Audio API to Batch synthesishttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-to-batch-synthesis
Migrate from v3 text-to-speech to custom voice REST APIhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-to-custom-voice-api
Migrate Speech-to-text REST from v3.0 to v3.1https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-v3-0-to-v3-1
Migrate Speech to text REST API v3.1 to v3.2https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-v3-1-to-v3-2
Assess capabilities and regions for personal voicehttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-overview
Select models and pricing for Voice Live APIhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live

Limits & Quotas

TopicURL
Text to speech FAQs including limits and behaviorhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/faq-tts
Manage custom speech model and endpoint lifecyclehttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-model-and-endpoint-lifecycle
Deploy professional voice models to custom endpointshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-deploy-endpoint
Train professional voice models and understand durationhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-train-voice
Reference quotas and limits for Azure Speechhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits

Security

TopicURL
Configure BYOS storage for Azure Speech resourceshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/bring-your-own-storage-speech-resource
Configure Microsoft Entra authentication for Speech SDKhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-configure-azure-ad-auth
Configure consent requirements for personal voice projectshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-create-consent
Create personal voice projects with consent and IDshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-create-project
Add and manage voice talent consent for professional voicehttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-create-consent
Assign Azure RBAC roles for Speech resourceshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/role-based-access-control
Configure Speech service in Azure sovereign cloudshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/sovereign-clouds
Manage Speech service data-at-rest encryption and keyshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-encryption-of-data-at-rest
Secure Speech service with Virtual Network service endpointshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-service-vnet-service-endpoint
Secure Azure AI Speech with Private Link endpointshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-private-link

Configuration

TopicURL
Configure Batch synthesis properties for text-to-speechhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-synthesis-properties
Check status and retrieve batch transcription resultshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription-get
Configure BYOS storage for Speech to texthttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/bring-your-own-storage-speech-resource-speech-to-text
Define UPS phonetic pronunciations for Speech to texthttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/customize-pronunciation
Configure OpenSSL on Linux for Azure Speech SDKhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-configure-openssl-linux
Control and monitor Speech SDK service connectionshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-control-connections
Select and configure audio input devices in Speech SDKhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-select-audio-input-devices
Use visemes for facial animation with Speech servicehttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-speech-synthesis-viseme
Configure Speech SDK audio input streamshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-use-audio-input-streams
Configure compressed audio input for Speech SDK and CLIhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-use-codec-compressed-audio-input-streams
Enable and configure Speech SDK diagnostic logginghttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-use-logging
Configure interim responses for Voice Live latencyhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-interim-response
Configure OpenTelemetry tracing for Voice Live SDKhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-telemetry
Configure audio and transcription logging for Speech recognitionhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/logging-audio-transcription
Create and manage personal voice speaker profileshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-create-voice
Upload and validate training datasets for professional voicehttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-create-training-set
Configure Azure Speech text-to-speech avatar optionshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/quickstarts/get-started-text-to-speech-avatar
Use correct Azure Speech regional endpointshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/regions
Configure Speech containers storage, logging, and securityhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-configuration
Control speech output using SSML configurationhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup
Configure pronunciation with SSML phonemes and lexiconshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-pronunciation
Structure SSML documents and events for Speechhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-structure
Configure Speech CLI datastore search order and fileshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/spx-data-store-configuration
Configure output destinations for Speech CLI resultshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/spx-output-options
Configure batch synthesis properties for TTS avatarshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/batch-synthesis-avatar-properties
Reference Voice Live API events, models, and settings (2025-10-01)https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-api-reference-2025-10-01
Reference Voice Live API events and settings (2026-01-01-preview)https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-api-reference-2026-01-01-preview
Configure Voice Live WebSocket events and settingshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-how-to
Configure language and locale support in Voice Livehttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-language-support

Integrations & Coding Patterns

TopicURL
Integrate Speech service with call center telephonyhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/call-center-telephony-integration
Call Azure Speech fast transcription API in Foundryhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create
Use Speech SDK APIs to handle recognition resultshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/get-speech-recognition-results
Integrate custom models with Voice Live API (BYOM)https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-bring-your-own-model
Implement text-to-speech synthesis with Speech SDKhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-speech-synthesis
Implement speech translation with Azure Speech SDKhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-translate-speech
Integrate Voice Live with Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-agent-integration
Implement function calling in Voice Live sessionshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-function-calling
Integrate Voice Live with Foundry hosted agentshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-hosted-agent-integration
Connect MCP servers to Voice Live sessionshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-mcp-server
Add proactive greeting messages to Voice Live agentshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-proactive-messages
Use Azure LLM Speech API for transcriptionhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/llm-speech
Use MAI-Transcribe with LLM Speech APIhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-transcribe
Integrate Azure Speech with Azure OpenAI chathttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/openai-speech
Integrate Azure Personal Voice into applicationshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-how-to-use
Use Power Automate connector for Speech batch transcriptionhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/power-automate-batch-transcription
Use Speech to text REST API endpoints and parametershttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-speech-to-text
Call Azure Speech-to-text short audio REST APIhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-speech-to-text-short
Call Speech text to speech REST API endpointshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech
Use SSML phonetic alphabets with Azure Speechhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-ssml-phonetic-sets
Use SSML to customize Azure Speech voiceshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice
Generate Speech service REST clients from Swaggerhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/swagger-documentation
Control text to speech avatar gestures with SSMLhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/avatar-gestures-with-ssml
Implement real-time text-to-speech avatar streaminghttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/real-time-synthesis-avatar
Use Voice Live WebSocket API events and modelshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-api-reference-2026-04-10
Integrate with Voice Live preview WebSocket APIhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-api-reference-2026-06-01-preview
Integrate Voice Live API with telephony systemshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-telephony

Deployment

TopicURL
Use Batch synthesis API for long-form text-to-speechhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-synthesis
Deploy custom speech models and endpointshttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-deploy-model
Scale Speech containers with batch processing kithttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-batch-processing
Run custom speech to text containers with Dockerhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-cstt
Deploy and run Speech containers with Dockerhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-howto
Run Speech containers on Kubernetes with Helmhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-howto-on-premises
Deploy language identification containers with Dockerhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-lid
Deploy neural text to speech containers with Dockerhttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-ntts
Deploy speech to text containers for on-premises usehttps://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-stt

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.