1---2name: azure-speech3description: Expert knowledge for Azure AI Speech development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building STT/TTS, custom speech or voice models, Voice Live/avatars, batch jobs, or telephony voice agents, and other Azure AI Speech related development tasks. Not for Azure Communication Services (use azure-communication-services), Azure AI Bot Service (use azure-bot-service), Azure AI Video Indexer (use azure-video-indexer), Azure Translator (use azure-translator).4---5# Azure AI Speech Skill67This skill provides expert guidance for Azure AI Speech. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.89## How to Use This Skill1011> **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 file1213> **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](https://github.com/MicrosoftDocs/mcp/blob/main/README.md)1415This skill requires **network access** to fetch documentation content:16- **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.17- **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.1819## Category Index2021| Category | Lines | Description |22|----------|-------|-------------|23| Troubleshooting | L37-L47 | Diagnosing and fixing common Azure Speech/Text-to-Speech/Voice Live API and SDK errors, container and Foundry issues, CRL/compatibility problems, and retrieving session/transcription IDs for support. |24| Best Practices | L48-L64 | Best practices for audio/video prep, custom voice/avatars, latency and memory tuning, phrase/keyword optimization, and handling real-time Voice Live interactions and interruptions |25| Decision Making | L65-L82 | Guidance on choosing speech features (batch STT, custom/embedded/personal/Whisper), evaluating models/devices, and step‑by‑step migration between Speech API versions and services |26| Architecture & Design Patterns | L83-L87 | Architectural guidance for building call center voice agents using Azure AI Speech with Voice Live and Azure Communication Services, including integration patterns and design best practices. |27| Limits & Quotas | L88-L96 | Quotas, limits, and usage patterns for Azure Speech: batch TTS, custom/pro voice training & deployment, and short audio STT, plus throttling and capacity planning guidance. |28| Security | L97-L108 | Configuring security for Azure AI Speech: auth (Entra, RBAC), network isolation (VNet, Private Link, sovereign clouds), BYOS storage, encryption/keys, and voice talent consent management. |29| Configuration | L109-L143 | Configuring Azure AI Speech/Voice: audio inputs, logging, storage, SSML, languages/voices, custom speech & voice training, batch/real-time settings, and Voice Live/avatars options. |30| Integrations & Coding Patterns | L144-L168 | Patterns and APIs for integrating Azure Speech into apps and voice agents: telephony, SDK/REST, TTS/avatars, translation, OpenAI/Foundry, Voice Live, consent, and automation workflows. |31| Deployment | L169-L180 | Deploying and scaling Azure AI Speech: Docker/Kubernetes containers, on-prem STT/TTS, custom speech models/endpoints, language ID, and batch/long-form synthesis workflows. |3233### Troubleshooting34| Topic | URL |35|-------|-----|36| Troubleshoot common Azure text to speech issues | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/faq-tts |37| Retrieve Speech to text session and transcription IDs for support | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-get-speech-session-id |38| Resolve common Azure Speech in Foundry issues | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/known-issues |39| Resolve Azure AI Speech SDK CRL compatibility issues | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-to-sdk-1-48-2 |40| Troubleshoot Speech service container deployments | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-faq |41| Troubleshoot common Azure Speech SDK issues | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/troubleshooting |42| Resolve common Voice Live API issues in Speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-faq |4344### Best Practices45| Topic | URL |46|-------|-----|47| Prepare and locate audio data for batch transcription | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription-audio-data |48| Create high-quality human-labeled speech transcriptions | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-human-labeled-transcriptions |49| Prepare training data for professional custom voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-voice-training-data |50| Apply best practices to reduce Speech synthesis latency | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-lower-speech-synthesis-latency |51| Track and manage Azure Speech SDK memory usage | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-track-speech-sdk-memory-usage |52| Handle user interruptions and chat truncation in Voice Live | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-auto-truncation |53| Use interim responses in Voice Live to reduce latency gaps | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-interim-response |54| Improve speech recognition with phrase lists | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/improve-accuracy-phrase-list |55| Apply keyword recognition design and accuracy guidelines | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/keyword-recognition-guidelines |56| Record high-quality samples for custom voice training | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/record-custom-voice-samples |57| Back up and recover custom Speech and Voice resources | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/resiliency-and-recovery-plan |58| Design microphone arrays optimized for Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-sdk-microphone |59| Prepare high-quality video samples for custom avatars | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/custom-avatar-record-video-samples |6061### Decision Making62| Topic | URL |63|-------|-----|64| Plan large-scale transcription with batch processing | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription |65| Evaluate custom voice lite before professional voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/custom-neural-voice-lite |66| Choose Embedded Speech for offline and hybrid scenarios | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/embedded-speech |67| Evaluate device suitability for embedded speech models | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/embedded-speech-performance-evaluations |68| Evaluate and compare custom speech model accuracy | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-inspect-data |69| Migrate Speech to text REST API from v3.2 to 2024-11-15 | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-2024-11-15 |70| Migrate Speech to text REST API from 2024-11-15 to 2025-10-15 | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-2025-10-15 |71| Migrate from retired Speech intent recognition to Language or OpenAI | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-intent-recognition |72| Migrate from Long Audio API to Batch synthesis | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-to-batch-synthesis |73| Migrate from v3 text-to-speech to custom voice REST API | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-to-custom-voice-api |74| Migrate Speech-to-text REST from v3.0 to v3.1 | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-v3-0-to-v3-1 |75| Migrate Speech-to-text REST from v3.1 to v3.2 | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-v3-1-to-v3-2 |76| Assess capabilities and regions for personal voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-overview |77| Decide when to use Whisper for speech tasks | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/whisper-overview |7879### Architecture & Design Patterns80| Topic | URL |81|-------|-----|82| Design call center voice agents with Voice Live and ACS | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-telephony |8384### Limits & Quotas85| Topic | URL |86|-------|-----|87| Manage custom speech model and endpoint lifecycle | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-model-and-endpoint-lifecycle |88| Deploy professional voice models to custom endpoints | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-deploy-endpoint |89| Train professional voice models and understand duration | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-train-voice |90| Use Speech-to-text REST API for short audio | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-speech-to-text-short |91| Apply Azure Speech quotas, limits, and throttling guidance | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits |9293### Security94| Topic | URL |95|-------|-----|96| Configure BYOS storage for Azure Speech resources | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/bring-your-own-storage-speech-resource |97| Configure Microsoft Entra authentication for Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-configure-azure-ad-auth |98| Manage voice talent consent for professional voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-create-consent |99| Assign Azure RBAC roles for Speech resources | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/role-based-access-control |100| Use Azure Speech service in sovereign clouds | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/sovereign-clouds |101| Manage Speech service data-at-rest encryption and keys | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-encryption-of-data-at-rest |102| Secure Speech service with Virtual Network service endpoints | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-service-vnet-service-endpoint |103| Secure Azure AI Speech with Private Link endpoints | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-private-link |104105### Configuration106| Topic | URL |107|-------|-----|108| Configure Batch synthesis properties for text-to-speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-synthesis-properties |109| Check status and retrieve batch transcription results | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription-get |110| Configure BYOS storage for Speech to text | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/bring-your-own-storage-speech-resource-speech-to-text |111| Define UPS phonetic pronunciations for Speech to text | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/customize-pronunciation |112| Configure OpenSSL on Linux for Azure Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-configure-openssl-linux |113| Control and monitor Speech SDK service connections | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-control-connections |114| Create and manage custom speech fine-tuning projects | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-create-project |115| Prepare and upload datasets for custom speech training | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-upload-data |116| Configure post-processing options for Speech recognition | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-post-processing |117| Configure real-time speech recognition inputs and options | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-recognize-speech |118| Select and configure audio input devices in Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-select-audio-input-devices |119| Use visemes for facial animation with Speech service | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-speech-synthesis-viseme |120| Configure Speech SDK audio input streams | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-use-audio-input-streams |121| Configure compressed audio input for Speech SDK and CLI | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-use-codec-compressed-audio-input-streams |122| Enable and configure Speech SDK diagnostic logging | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-use-logging |123| Check Azure Speech language and voice availability | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support |124| Configure audio and transcription logging for Speech recognition | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/logging-audio-transcription |125| Upload and validate training datasets for professional voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-create-training-set |126| Use correct regional endpoints for Azure Speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/regions |127| Configure Speech containers storage, logging, and security | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-configuration |128| Control speech output using SSML configuration | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup |129| Configure pronunciation with SSML phonemes and lexicons | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-pronunciation |130| Structure SSML documents and events for Speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-structure |131| Configure voice and sound using SSML in Speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice |132| Configure Speech CLI datastore search order and files | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/spx-data-store-configuration |133| Configure output destinations for Speech CLI results | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/spx-output-options |134| Configure batch synthesis properties for TTS avatars | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/batch-synthesis-avatar-properties |135| 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 |136| 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 |137| Customize Voice Live input and output models | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-how-to-customize |138| Configure language and locale for Voice Live API | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-language-support |139140### Integrations & Coding Patterns141| Topic | URL |142|-------|-----|143| Integrate Speech service with call center telephony | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/call-center-telephony-integration |144| Call Azure Speech fast transcription API in Foundry | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create |145| Use Speech SDK APIs to handle recognition results | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/get-speech-recognition-results |146| Integrate custom models with Voice Live BYOM | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-bring-your-own-model |147| Implement text-to-speech synthesis with Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-speech-synthesis |148| Implement speech translation with Azure Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-translate-speech |149| Build real-time voice agents with Voice Live and Foundry Agent Service | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-agent-integration |150| Connect MCP servers to Azure Voice Live sessions | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-mcp-server |151| Add proactive greetings to Voice Live agents | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-proactive-messages |152| Call the LLM-speech API for transcription and translation | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/llm-speech |153| Integrate Azure Speech with Azure OpenAI chat | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/openai-speech |154| Add and manage user consent for personal voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-create-consent |155| Create personal voice projects via Custom Voice API | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-create-project |156| Use Power Automate connector for Speech batch transcription | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/power-automate-batch-transcription |157| Use Speech to text REST API endpoints and parameters | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-speech-to-text |158| Call Text-to-speech REST API for voice synthesis | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech |159| Use SSML phonetic alphabets with Azure Speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-ssml-phonetic-sets |160| Generate Speech service REST clients from Swagger | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/swagger-documentation |161| Control text to speech avatar gestures with SSML | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/avatar-gestures-with-ssml |162| Implement real-time text-to-speech avatar streaming | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/real-time-synthesis-avatar |163| Use Voice Live WebSocket events and properties | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-how-to |164165### Deployment166| Topic | URL |167|-------|-----|168| Use Batch synthesis API for long-form text-to-speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-synthesis |169| Deploy custom speech models and endpoints | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-deploy-model |170| Scale Speech containers with batch processing kit | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-batch-processing |171| Run custom speech to text containers with Docker | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-cstt |172| Deploy and run Speech containers with Docker | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-howto |173| Run Speech containers on Kubernetes with Helm | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-howto-on-premises |174| Deploy language identification containers with Docker | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-lid |175| Deploy neural text to speech containers with Docker | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-ntts |176| Deploy speech to text containers for on-premises use | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-stt |
luokai0