{"id":"81eca933-4026-493b-97fe-99e1572abaee","shortId":"bzhMxD","kind":"skill","title":"azure-speech","tagline":"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 using Speech/Voice SDKs, STT/TTS, custom","description":"# Azure AI Speech Skill\n\nThis 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.\n\n## How to Use This Skill\n\n> **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\n\n> **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)\n\nThis skill requires **network access** to fetch documentation content:\n- **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.\n- **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.\n\n## Category Index\n\n| Category | Lines | Description |\n|----------|-------|-------------|\n| 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. |\n| 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 |\n| Decision Making | L65-L83 | 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 |\n| Architecture & Design Patterns | L84-L88 | 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. |\n| Limits & Quotas | L89-L97 | 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. |\n| Security | L98-L109 | 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. |\n| Configuration | L110-L144 | 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. |\n| Integrations & Coding Patterns | L145-L168 | Integrating Azure AI Speech into apps and voice agents: SDK/REST usage, telephony, TTS/avatars, translation, LLM/Foundry/Voice Live flows, consent, and automation patterns. |\n| 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. |\n\n### Troubleshooting\n| Topic | URL |\n|-------|-----|\n| Troubleshoot common Azure text to speech issues | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/faq-tts |\n| 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 |\n| Resolve common Azure Speech in Foundry issues | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/known-issues |\n| 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 |\n| Troubleshoot Speech service container deployments | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-faq |\n| Troubleshoot common Azure Speech SDK issues | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/troubleshooting |\n| Resolve common Voice Live API issues in Speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-faq |\n\n### Best Practices\n| Topic | URL |\n|-------|-----|\n| Prepare and locate audio data for batch transcription | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription-audio-data |\n| 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 |\n| Prepare training data for professional custom voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-voice-training-data |\n| 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 |\n| 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 |\n| 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 |\n| 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 |\n| Improve speech recognition with phrase lists | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/improve-accuracy-phrase-list |\n| Apply keyword recognition design and accuracy guidelines | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/keyword-recognition-guidelines |\n| Record high-quality samples for custom voice training | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/record-custom-voice-samples |\n| Back up and recover custom Speech and Voice resources | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/resiliency-and-recovery-plan |\n| Design microphone arrays optimized for Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-sdk-microphone |\n| 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 |\n\n### Decision Making\n| Topic | URL |\n|-------|-----|\n| Plan large-scale transcription with batch processing | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription |\n| Evaluate custom voice lite before professional voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/custom-neural-voice-lite |\n| Choose Embedded Speech for offline and hybrid scenarios | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/embedded-speech |\n| Evaluate device suitability for embedded speech models | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/embedded-speech-performance-evaluations |\n| Evaluate and compare custom speech model accuracy | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-inspect-data |\n| Train custom speech models and understand cost behavior | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-train-model |\n| 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 |\n| 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 |\n| Migrate from retired Speech intent recognition to Language or OpenAI | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-intent-recognition |\n| Migrate from Long Audio API to Batch synthesis | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-to-batch-synthesis |\n| 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 |\n| 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 |\n| 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 |\n| Assess capabilities and regions for personal voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-overview |\n| Decide when to use Whisper for speech tasks | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/whisper-overview |\n\n### Architecture & Design Patterns\n| Topic | URL |\n|-------|-----|\n| Design call center voice agents with Voice Live and ACS | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-telephony |\n\n### Limits & Quotas\n| Topic | URL |\n|-------|-----|\n| 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 |\n| Deploy professional voice models to custom endpoints | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-deploy-endpoint |\n| Train professional voice models and understand duration | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-train-voice |\n| 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 |\n| Apply Azure Speech quotas, limits, and throttling guidance | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits |\n\n### Security\n| Topic | URL |\n|-------|-----|\n| Configure BYOS storage for Azure Speech resources | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/bring-your-own-storage-speech-resource |\n| Configure Microsoft Entra authentication for Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-configure-azure-ad-auth |\n| Manage voice talent consent for professional voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-create-consent |\n| Assign Azure RBAC roles for Speech resources | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/role-based-access-control |\n| Use Azure Speech service in sovereign clouds | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/sovereign-clouds |\n| 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 |\n| Secure Speech service with Virtual Network service endpoints | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-service-vnet-service-endpoint |\n| Secure Azure AI Speech with Private Link endpoints | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-private-link |\n\n### Configuration\n| Topic | URL |\n|-------|-----|\n| Configure Batch synthesis properties for text-to-speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-synthesis-properties |\n| Check status and retrieve batch transcription results | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription-get |\n| 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 |\n| Define UPS phonetic pronunciations for Speech to text | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/customize-pronunciation |\n| Configure OpenSSL on Linux for Azure Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-configure-openssl-linux |\n| Control and monitor Speech SDK service connections | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-control-connections |\n| 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 |\n| 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 |\n| Configure post-processing options for Speech recognition | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-post-processing |\n| Configure real-time speech recognition inputs and options | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-recognize-speech |\n| 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 |\n| Use visemes for facial animation with Speech service | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-speech-synthesis-viseme |\n| Configure Speech SDK audio input streams | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-use-audio-input-streams |\n| 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 |\n| Enable and configure Speech SDK diagnostic logging | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-use-logging |\n| Check Azure Speech language and voice availability | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support |\n| Configure audio and transcription logging for Speech recognition | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/logging-audio-transcription |\n| Upload and validate training datasets for professional voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-create-training-set |\n| Use correct regional endpoints for Azure Speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/regions |\n| Configure Speech containers storage, logging, and security | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-configuration |\n| Control speech output using SSML configuration | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup |\n| Configure pronunciation with SSML phonemes and lexicons | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-pronunciation |\n| Structure SSML documents and events for Speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-structure |\n| Configure voice and sound using SSML in Speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice |\n| Configure Speech CLI datastore search order and files | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/spx-data-store-configuration |\n| Configure output destinations for Speech CLI results | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/spx-output-options |\n| 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 |\n| 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 |\n| 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 |\n| Customize Voice Live input and output models | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-how-to-customize |\n| Configure language and locale for Voice Live API | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-language-support |\n\n### Integrations & Coding Patterns\n| Topic | URL |\n|-------|-----|\n| Integrate Speech service with call center telephony | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/call-center-telephony-integration |\n| Call Azure Speech fast transcription API in Foundry | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create |\n| Use Speech SDK APIs to handle recognition results | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/get-speech-recognition-results |\n| Integrate custom models with Voice Live BYOM | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-bring-your-own-model |\n| Implement text-to-speech synthesis with Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-speech-synthesis |\n| Implement speech translation with Azure Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-translate-speech |\n| 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 |\n| Add proactive greetings to Voice Live agents | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-proactive-messages |\n| Call the LLM-speech API for transcription and translation | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/llm-speech |\n| Integrate Azure Speech with Azure OpenAI chat | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/openai-speech |\n| Add and manage user consent for personal voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-create-consent |\n| Create personal voice projects via Custom Voice API | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-create-project |\n| Use Power Automate connector for Speech batch transcription | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/power-automate-batch-transcription |\n| Use Speech to text REST API endpoints and parameters | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-speech-to-text |\n| Call Text-to-speech REST API for voice synthesis | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech |\n| Use SSML phonetic alphabets with Azure Speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-ssml-phonetic-sets |\n| Generate Speech service REST clients from Swagger | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/swagger-documentation |\n| 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 |\n| 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 |\n| Use Voice Live WebSocket events and properties | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-how-to |\n\n### Deployment\n| Topic | URL |\n|-------|-----|\n| Use Batch synthesis API for long-form text-to-speech | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-synthesis |\n| Deploy custom speech models and endpoints | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-deploy-model |\n| Scale Speech containers with batch processing kit | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-batch-processing |\n| Run custom speech to text containers with Docker | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-cstt |\n| Deploy and run Speech containers with Docker | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-howto |\n| Run Speech containers on Kubernetes with Helm | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-howto-on-premises |\n| Deploy language identification containers with Docker | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-lid |\n| Deploy neural text to speech containers with Docker | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-ntts |\n| Deploy speech to text containers for on-premises use | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-stt |","tags":["azure","speech","agent","skills","microsoftdocs","agent-skills","agentic-skills","agentskill","ai-agents","ai-coding","azure-functions","azure-kubernetes-service"],"capabilities":["skill","source-microsoftdocs","skill-azure-speech","topic-agent","topic-agent-skills","topic-agentic-skills","topic-agentskill","topic-ai-agents","topic-ai-coding","topic-azure","topic-azure-functions","topic-azure-kubernetes-service","topic-azure-openai","topic-azure-sql-database","topic-azure-storage"],"categories":["Agent-Skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/MicrosoftDocs/Agent-Skills/azure-speech","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add MicrosoftDocs/Agent-Skills","source_repo":"https://github.com/MicrosoftDocs/Agent-Skills","install_from":"skills.sh"}},"qualityScore":"0.698","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 497 github stars · SKILL.md body (20,617 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-04-22T00:53:37.731Z","embedding":null,"createdAt":"2026-04-18T22:00:10.107Z","updatedAt":"2026-04-22T00:53:37.731Z","lastSeenAt":"2026-04-22T00:53:37.731Z","tsv":"'-01':1333,1345,1346 '-10':778,1332 '-11':761,774 '-15':762,775,779 '/en-us/azure/ai-services/speech-service/batch-synthesis':1619 '/en-us/azure/ai-services/speech-service/batch-synthesis-properties':1047 '/en-us/azure/ai-services/speech-service/batch-transcription':698 '/en-us/azure/ai-services/speech-service/batch-transcription-audio-data':549 '/en-us/azure/ai-services/speech-service/batch-transcription-get':1057 '/en-us/azure/ai-services/speech-service/bring-your-own-storage-speech-resource':957 '/en-us/azure/ai-services/speech-service/bring-your-own-storage-speech-resource-speech-to-text':1067 '/en-us/azure/ai-services/speech-service/call-center-telephony-integration':1386 '/en-us/azure/ai-services/speech-service/custom-neural-voice-lite':708 '/en-us/azure/ai-services/speech-service/customize-pronunciation':1078 '/en-us/azure/ai-services/speech-service/embedded-speech':719 '/en-us/azure/ai-services/speech-service/embedded-speech-performance-evaluations':729 '/en-us/azure/ai-services/speech-service/faq-tts':472 '/en-us/azure/ai-services/speech-service/fast-transcription-create':1397 '/en-us/azure/ai-services/speech-service/get-speech-recognition-results':1408 '/en-us/azure/ai-services/speech-service/how-to-bring-your-own-model':1418 '/en-us/azure/ai-services/speech-service/how-to-configure-azure-ad-auth':967 '/en-us/azure/ai-services/speech-service/how-to-configure-openssl-linux':1089 '/en-us/azure/ai-services/speech-service/how-to-control-connections':1099 '/en-us/azure/ai-services/speech-service/how-to-custom-speech-create-project':1111 '/en-us/azure/ai-services/speech-service/how-to-custom-speech-deploy-model':1628 '/en-us/azure/ai-services/speech-service/how-to-custom-speech-human-labeled-transcriptions':561 '/en-us/azure/ai-services/speech-service/how-to-custom-speech-inspect-data':739 '/en-us/azure/ai-services/speech-service/how-to-custom-speech-model-and-endpoint-lifecycle':900 '/en-us/azure/ai-services/speech-service/how-to-custom-speech-train-model':750 '/en-us/azure/ai-services/speech-service/how-to-custom-speech-upload-data':1122 '/en-us/azure/ai-services/speech-service/how-to-custom-voice-training-data':571 '/en-us/azure/ai-services/speech-service/how-to-get-speech-session-id':485 '/en-us/azure/ai-services/speech-service/how-to-lower-speech-synthesis-latency':582 '/en-us/azure/ai-services/speech-service/how-to-post-processing':1133 '/en-us/azure/ai-services/speech-service/how-to-recognize-speech':1145 '/en-us/azure/ai-services/speech-service/how-to-select-audio-input-devices':1157 '/en-us/azure/ai-services/speech-service/how-to-speech-synthesis':1430 '/en-us/azure/ai-services/speech-service/how-to-speech-synthesis-viseme':1168 '/en-us/azure/ai-services/speech-service/how-to-track-speech-sdk-memory-usage':593 '/en-us/azure/ai-services/speech-service/how-to-translate-speech':1440 '/en-us/azure/ai-services/speech-service/how-to-use-audio-input-streams':1177 '/en-us/azure/ai-services/speech-service/how-to-use-codec-compressed-audio-input-streams':1189 '/en-us/azure/ai-services/speech-service/how-to-use-logging':1199 '/en-us/azure/ai-services/speech-service/how-to-voice-agent-integration':1456 '/en-us/azure/ai-services/speech-service/how-to-voice-live-auto-truncation':605 '/en-us/azure/ai-services/speech-service/how-to-voice-live-interim-response':618 '/en-us/azure/ai-services/speech-service/how-to-voice-live-proactive-messages':1466 '/en-us/azure/ai-services/speech-service/improve-accuracy-phrase-list':627 '/en-us/azure/ai-services/speech-service/keyword-recognition-guidelines':637 '/en-us/azure/ai-services/speech-service/known-issues':495 '/en-us/azure/ai-services/speech-service/language-support':1209 '/en-us/azure/ai-services/speech-service/llm-speech':1479 '/en-us/azure/ai-services/speech-service/logging-audio-transcription':1220 '/en-us/azure/ai-services/speech-service/migrate-2024-11-15':765 '/en-us/azure/ai-services/speech-service/migrate-2025-10-15':782 '/en-us/azure/ai-services/speech-service/migrate-intent-recognition':795 '/en-us/azure/ai-services/speech-service/migrate-to-batch-synthesis':806 '/en-us/azure/ai-services/speech-service/migrate-to-custom-voice-api':821 '/en-us/azure/ai-services/speech-service/migrate-to-sdk-1-48-2':506 '/en-us/azure/ai-services/speech-service/migrate-v3-0-to-v3-1':834 '/en-us/azure/ai-services/speech-service/migrate-v3-1-to-v3-2':847 '/en-us/azure/ai-services/speech-service/openai-speech':1489 '/en-us/azure/ai-services/speech-service/personal-voice-create-consent':1500 '/en-us/azure/ai-services/speech-service/personal-voice-create-project':1511 '/en-us/azure/ai-services/speech-service/personal-voice-overview':857 '/en-us/azure/ai-services/speech-service/power-automate-batch-transcription':1522 '/en-us/azure/ai-services/speech-service/professional-voice-create-consent':977 '/en-us/azure/ai-services/speech-service/professional-voice-create-training-set':1231 '/en-us/azure/ai-services/speech-service/professional-voice-deploy-endpoint':910 '/en-us/azure/ai-services/speech-service/professional-voice-train-voice':920 '/en-us/azure/ai-services/speech-service/record-custom-voice-samples':649 '/en-us/azure/ai-services/speech-service/regions':1241 '/en-us/azure/ai-services/speech-service/resiliency-and-recovery-plan':661 '/en-us/azure/ai-services/speech-service/rest-speech-to-text':1534 '/en-us/azure/ai-services/speech-service/rest-speech-to-text-short':933 '/en-us/azure/ai-services/speech-service/rest-text-to-speech':1547 '/en-us/azure/ai-services/speech-service/role-based-access-control':987 '/en-us/azure/ai-services/speech-service/sovereign-clouds':997 '/en-us/azure/ai-services/speech-service/speech-container-batch-processing':1638 '/en-us/azure/ai-services/speech-service/speech-container-configuration':1251 '/en-us/azure/ai-services/speech-service/speech-container-cstt':1649 '/en-us/azure/ai-services/speech-service/speech-container-faq':514 '/en-us/azure/ai-services/speech-service/speech-container-howto':1659 '/en-us/azure/ai-services/speech-service/speech-container-howto-on-premises':1669 '/en-us/azure/ai-services/speech-service/speech-container-lid':1678 '/en-us/azure/ai-services/speech-service/speech-container-ntts':1689 '/en-us/azure/ai-services/speech-service/speech-container-stt':1702 '/en-us/azure/ai-services/speech-service/speech-encryption-of-data-at-rest':1010 '/en-us/azure/ai-services/speech-service/speech-sdk-microphone':671 '/en-us/azure/ai-services/speech-service/speech-service-vnet-service-endpoint':1021 '/en-us/azure/ai-services/speech-service/speech-services-private-link':1032 '/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits':944 '/en-us/azure/ai-services/speech-service/speech-ssml-phonetic-sets':1557 '/en-us/azure/ai-services/speech-service/speech-synthesis-markup':1260 '/en-us/azure/ai-services/speech-service/speech-synthesis-markup-pronunciation':1270 '/en-us/azure/ai-services/speech-service/speech-synthesis-markup-structure':1280 '/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice':1291 '/en-us/azure/ai-services/speech-service/spx-data-store-configuration':1302 '/en-us/azure/ai-services/speech-service/spx-output-options':1312 '/en-us/azure/ai-services/speech-service/swagger-documentation':1567 '/en-us/azure/ai-services/speech-service/text-to-speech-avatar/avatar-gestures-with-ssml':1578 '/en-us/azure/ai-services/speech-service/text-to-speech-avatar/batch-synthesis-avatar-properties':1322 '/en-us/azure/ai-services/speech-service/text-to-speech-avatar/custom-avatar-record-video-samples':683 '/en-us/azure/ai-services/speech-service/text-to-speech-avatar/real-time-synthesis-avatar':1591 '/en-us/azure/ai-services/speech-service/troubleshooting':523 '/en-us/azure/ai-services/speech-service/voice-live-api-reference-2025-10-01':1336 '/en-us/azure/ai-services/speech-service/voice-live-api-reference-2026-01-01-preview':1350 '/en-us/azure/ai-services/speech-service/voice-live-faq':534 '/en-us/azure/ai-services/speech-service/voice-live-how-to':1601 '/en-us/azure/ai-services/speech-service/voice-live-how-to-customize':1360 '/en-us/azure/ai-services/speech-service/voice-live-language-support':1371 '/en-us/azure/ai-services/speech-service/voice-live-telephony':886 '/en-us/azure/ai-services/speech-service/whisper-overview':868 '/microsoftdocs/mcp/blob/main/readme.md)':166 '2024':760,773 '2025':777,1331 '2026':1344 '3':137 'ac':883 'accept':205 'access':171 'accuraci':633,736 'add':1457,1490 'agent':86,130,189,203,308,422,878,1446,1452,1463 'ai':8,37,47,311,364,390,416,443,498,1024 'alphabet':1551 'anim':1162 'api':225,291,528,756,771,800,818,927,1326,1340,1368,1392,1401,1472,1508,1528,1541,1608 'app':419 'appli':572,628,934 'architectur':17,55,295,301,869 'array':664 'assess':848 'assign':978 'audio':348,392,542,799,930,1149,1172,1180,1211 'audio/video':249 'auth':366 'authent':961 'autom':433,1514 'avail':156,1206 'avatar':680,1319,1572,1587 'azur':2,7,36,46,222,310,317,338,363,389,415,442,465,488,497,517,586,935,952,979,989,1023,1084,1201,1237,1388,1435,1481,1484,1553 'azure-speech':1 'back':650 'batch':279,340,545,694,802,1037,1052,1314,1518,1606,1633 'batch/long-form':457 'batch/real-time':402 'behavior':747 'best':13,51,241,246,325,535,573 'build':304,1441 'byo':376,949,1059 'byom':1415 'call':305,875,1381,1387,1467,1535 'capabl':78,849 'capac':353 'categori':89,97,113,209,211 'center':306,876,1382 'chat':598,1486 'check':1048,1200 'choos':276,709 'cli':1186,1294,1308 'client':1562 'cloud':375,994 'code':25,63,409,1373 'combin':68 'common':221,464,487,516,525 'communic':318 'compar':732 'compat':502 'compress':1179 'configur':23,61,360,384,388,948,958,1033,1036,1058,1079,1123,1134,1148,1169,1178,1192,1210,1242,1257,1261,1281,1292,1303,1313,1361 'connect':1096 'connector':1515 'consent':382,431,971,1494 'contain':229,446,510,1244,1631,1644,1654,1662,1673,1684,1694 'content':73,175 'control':1090,1252,1568 'correct':1233 'cost':746 'cover':49 'creat':550,1100,1501 'crl':501 'crl/compatibility':233 'custom':35,251,398,451,567,644,654,679,700,733,741,815,892,906,1103,1117,1351,1410,1506,1621,1640 'custom/embedded/personal/whisper':281 'custom/pro':342 'data':543,564,1002 'data-at-rest':1001 'dataset':1115,1225 'datastor':1295 'decid':858 'decis':15,53,269,684 'defin':1068 'deploy':28,66,345,435,439,511,901,1602,1620,1650,1670,1679,1690 'descript':213 'design':18,56,296,324,631,662,870,874 'destin':1305 'develop':10 'devic':721,1151 'diagnos':218 'diagnost':1195 'doc':181 'docker':1646,1656,1675,1686 'docker/kubernetes':445 'document':76,174,1273 'durat':917 'e.g':101,117 'embed':710,724 'enabl':1190 'encrypt':1005 'encryption/keys':378 'endpoint':896,907,1018,1029,1235,1529,1625 'entra':367,960 'error':228 'evalu':282,699,720,730 'event':1275,1327,1341,1596 'expert':4,43 'facial':1161 'fallback':193 'fast':1390 'featur':278 'fetch':77,173,182,195 'file':107,115,122,127,1299 'fine':1106 'fine-tun':1105 'fix':220 'flow':430 'form':1612 'foundri':231,491,1394,1451 'gap':615 'generat':1558 'gestur':1573 'github.com':165 'github.com/microsoftdocs/mcp/blob/main/readme.md)':164 'greet':1459 'guid':163 'guidanc':44,274,302,355,941 'guidelin':634 'handl':260,594,1403 'helm':1666 'high':552,640,674 'high-qual':551,639,673 'human':555 'human-label':554 'hybrid':715 'id':238,455,480 'identif':1672 'implement':1419,1431,1579 'import':84,128 'improv':619 'includ':11,320 'index':90,210 'input':393,1140,1150,1173,1181,1354 'instal':160,162 'integr':24,62,321,408,414,1372,1377,1409,1480 'intent':787 'interact':266 'interim':607 'interrupt':268,596 'isol':370 'issu':232,469,492,503,520,529 'key':1007 'keyword':629 'kit':1635 'knowledg':5 'kubernet':1664 'l109':359 'l110':386 'l110-l144':385 'l120':104 'l144':387 'l145':412 'l145-l168':411 'l168':413 'l169':437 'l169-l180':436 'l180':438 'l35':103 'l35-l120':102 'l37':216 'l37-l47':215 'l47':217 'l48':244 'l48-l64':243 'l64':245 'l65':272 'l65-l83':271 'l83':273 'l84':299 'l84-l88':298 'l88':300 'l89':330 'l89-l97':329 'l97':331 'l98':358 'l98-l109':357 'label':556 'languag':454,790,1203,1362,1671 'languages/voices':397 'larg':690 'large-scal':689 'latenc':253,579,614 'latest':145 'learn':188,202 'learn-agent-skil':187,201 'learn.microsoft.com':471,484,494,505,513,522,533,548,560,570,581,592,604,617,626,636,648,660,670,682,697,707,718,728,738,749,764,781,794,805,820,833,846,856,867,885,899,909,919,932,943,956,966,976,986,996,1009,1020,1031,1046,1056,1066,1077,1088,1098,1110,1121,1132,1144,1156,1167,1176,1188,1198,1208,1219,1230,1240,1250,1259,1269,1279,1290,1301,1311,1321,1335,1349,1359,1370,1385,1396,1407,1417,1429,1439,1455,1465,1478,1488,1499,1510,1521,1533,1546,1556,1566,1577,1590,1600,1618,1627,1637,1648,1658,1668,1677,1688,1701 'learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-synthesis':1617 'learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-synthesis-properties':1045 'learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription':696 'learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription-audio-data':547 'learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription-get':1055 'learn.microsoft.com/en-us/azure/ai-services/speech-service/bring-your-own-storage-speech-resource':955 'learn.microsoft.com/en-us/azure/ai-services/speech-service/bring-your-own-storage-speech-resource-speech-to-text':1065 'learn.microsoft.com/en-us/azure/ai-services/speech-service/call-center-telephony-integration':1384 'learn.microsoft.com/en-us/azure/ai-services/speech-service/custom-neural-voice-lite':706 'learn.microsoft.com/en-us/azure/ai-services/speech-service/customize-pronunciation':1076 'learn.microsoft.com/en-us/azure/ai-services/speech-service/embedded-speech':717 'learn.microsoft.com/en-us/azure/ai-services/speech-service/embedded-speech-performance-evaluations':727 'learn.microsoft.com/en-us/azure/ai-services/speech-service/faq-tts':470 'learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create':1395 'learn.microsoft.com/en-us/azure/ai-services/speech-service/get-speech-recognition-results':1406 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-bring-your-own-model':1416 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-configure-azure-ad-auth':965 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-configure-openssl-linux':1087 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-control-connections':1097 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-create-project':1109 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-deploy-model':1626 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-human-labeled-transcriptions':559 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-inspect-data':737 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-model-and-endpoint-lifecycle':898 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-train-model':748 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-upload-data':1120 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-voice-training-data':569 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-get-speech-session-id':483 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-lower-speech-synthesis-latency':580 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-post-processing':1131 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-recognize-speech':1143 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-select-audio-input-devices':1155 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-speech-synthesis':1428 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-speech-synthesis-viseme':1166 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-track-speech-sdk-memory-usage':591 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-translate-speech':1438 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-use-audio-input-streams':1175 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-use-codec-compressed-audio-input-streams':1187 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-use-logging':1197 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-agent-integration':1454 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-auto-truncation':603 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-interim-response':616 'learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-proactive-messages':1464 'learn.microsoft.com/en-us/azure/ai-services/speech-service/improve-accuracy-phrase-list':625 'learn.microsoft.com/en-us/azure/ai-services/speech-service/keyword-recognition-guidelines':635 'learn.microsoft.com/en-us/azure/ai-services/speech-service/known-issues':493 'learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support':1207 'learn.microsoft.com/en-us/azure/ai-services/speech-service/llm-speech':1477 'learn.microsoft.com/en-us/azure/ai-services/speech-service/logging-audio-transcription':1218 'learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-2024-11-15':763 'learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-2025-10-15':780 'learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-intent-recognition':793 'learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-to-batch-synthesis':804 'learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-to-custom-voice-api':819 'learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-to-sdk-1-48-2':504 'learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-v3-0-to-v3-1':832 'learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-v3-1-to-v3-2':845 'learn.microsoft.com/en-us/azure/ai-services/speech-service/openai-speech':1487 'learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-create-consent':1498 'learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-create-project':1509 'learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-overview':855 'learn.microsoft.com/en-us/azure/ai-services/speech-service/power-automate-batch-transcription':1520 'learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-create-consent':975 'learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-create-training-set':1229 'learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-deploy-endpoint':908 'learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-train-voice':918 'learn.microsoft.com/en-us/azure/ai-services/speech-service/record-custom-voice-samples':647 'learn.microsoft.com/en-us/azure/ai-services/speech-service/regions':1239 'learn.microsoft.com/en-us/azure/ai-services/speech-service/resiliency-and-recovery-plan':659 'learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-speech-to-text':1532 'learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-speech-to-text-short':931 'learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech':1545 'learn.microsoft.com/en-us/azure/ai-services/speech-service/role-based-access-control':985 'learn.microsoft.com/en-us/azure/ai-services/speech-service/sovereign-clouds':995 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-batch-processing':1636 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-configuration':1249 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-cstt':1647 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-faq':512 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-howto':1657 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-howto-on-premises':1667 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-lid':1676 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-ntts':1687 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-stt':1700 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-encryption-of-data-at-rest':1008 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-sdk-microphone':669 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-service-vnet-service-endpoint':1019 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-private-link':1030 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits':942 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-ssml-phonetic-sets':1555 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup':1258 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-pronunciation':1268 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-structure':1278 'learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice':1289 'learn.microsoft.com/en-us/azure/ai-services/speech-service/spx-data-store-configuration':1300 'learn.microsoft.com/en-us/azure/ai-services/speech-service/spx-output-options':1310 'learn.microsoft.com/en-us/azure/ai-services/speech-service/swagger-documentation':1565 'learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/avatar-gestures-with-ssml':1576 'learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/batch-synthesis-avatar-properties':1320 'learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/custom-avatar-record-video-samples':681 'learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/real-time-synthesis-avatar':1589 'learn.microsoft.com/en-us/azure/ai-services/speech-service/troubleshooting':521 'learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-api-reference-2025-10-01':1334 'learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-api-reference-2026-01-01-preview':1348 'learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-faq':532 'learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-how-to':1599 'learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-how-to-customize':1358 'learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-language-support':1369 'learn.microsoft.com/en-us/azure/ai-services/speech-service/voice-live-telephony':884 'learn.microsoft.com/en-us/azure/ai-services/speech-service/whisper-overview':866 'lexicon':1267 'lifecycl':897 'limit':20,58,327,333,887,938 'line':99,111,212 'link':116,125,373,1028 'linux':1082 'list':624 'lite':702 'live':224,265,315,429,527,602,611,881,1325,1339,1353,1367,1414,1449,1462,1594 'live/avatars':406 'llm':1470 'llm-speech':1469 'llm/foundry/voice':428 'local':69,1364 'locat':93,541 'log':394,1196,1214,1246 'long':798,1611 'long-form':1610 'make':16,54,270,685 'manag':383,585,891,968,998,1102,1492 'markdown':192,208 'mcp':151,178 'memori':255,589 'metadata.generated':132 'microphon':663 'microsoft':180,959 'microsoftdoc':152,179 'migrat':288,751,766,783,796,807,822,835 'model':726,735,743,894,904,914,1328,1357,1411,1623 'models/devices':283 'models/endpoints':453 'monitor':1092 'month':138 'network':170,369,1016 'neural':1680 'offlin':713 'old':139 'on-prem':447 'on-premis':1696 'openai':792,1485 'openssl':1080 'optim':258,665 'option':407,1127,1142 'order':1297 'output':1254,1304,1356 'paramet':1531 'pattern':19,26,57,64,297,322,336,410,434,871,1374 'person':853,1496,1502 'phonem':1265 'phonet':1070,1550 'phrase':623 'phrase/keyword':257 'plan':354,688 'plus':350 'post':1125 'post-process':1124 'power':1513 'practic':14,52,242,247,326,536,574 'prefer':176 'prem':449 'premis':1698 'prep':250 'prepar':539,562,672,1112 'preview':1347 'privat':372,1027 'proactiv':1458 'problem':234 'process':695,1126,1634 'profession':566,704,902,912,973,1227 'project':1108,1504 'pronunci':1071,1262 'properti':1039,1316,1598 'provid':42 'pull':143 'qualiti':553,641,675 'queri':184,198 'quick':71 'quick-refer':70 'quota':21,59,328,332,888,937 'rang':100 'rbac':368,980 'read':106,121 'real':262,1136,1443,1581 'real-tim':261,1135,1442,1580 'recognit':621,630,788,1130,1139,1217,1404 'record':638 'recov':653 'reduc':576,613 'refer':72,126,1323,1337 'region':851,1234 'relev':94 'remot':75 'repositori':149 'requir':169 'resolv':486,496,524 'resourc':658,954,984 'respons':608 'rest':755,770,817,827,840,926,1004,1527,1540,1561 'result':1054,1309,1405 'retir':785 'retriev':236,473,1051 'return':191,207 'role':981 'run':1639,1652,1660 'sampl':642,677 'scale':441,691,1629 'scenario':716 'sdk':227,500,519,588,668,964,1086,1094,1154,1171,1184,1194,1400,1427,1437 'sdk/rest':423 'sdks':33 'search':1296 'section':95 'secur':22,60,356,361,945,1011,1022,1248 'security.md':118,119 'select':1146 'servic':294,319,509,991,1000,1013,1017,1095,1165,1379,1453,1560 'session':477 'session/transcription':237 'set':403,1330,1343 'short':347,929 'skill':39,41,83,168,190,204 'skill-azure-speech' 'sound':1284 'source-microsoftdocs' 'sovereign':374,993 'specifi':110 'speech':3,9,38,48,277,290,312,339,365,399,417,444,452,468,474,489,499,508,518,531,557,577,587,620,655,667,711,725,734,742,752,767,786,813,824,837,864,893,923,936,953,963,983,990,999,1012,1025,1044,1062,1073,1085,1093,1104,1118,1129,1138,1153,1164,1170,1183,1193,1202,1216,1238,1243,1253,1277,1288,1293,1307,1378,1389,1399,1423,1426,1432,1436,1471,1482,1517,1524,1539,1554,1559,1571,1586,1616,1622,1630,1641,1653,1661,1683,1691 'speech-to-text':823,836,922 'speech/text-to-speech/voice':223 'speech/voice':32,391 'ssml':396,1256,1264,1272,1286,1549,1575 'status':1049 'step':285,287 'storag':377,395,950,1060,1245 'stream':1174,1588 'string':185,199 'structur':1271 'stt':280,349 'stt/tts':34,450 'suggest':140,157 'suitabl':722 'support':240,482 'swagger':1564 'synthesi':458,578,803,1038,1315,1424,1544,1607 'talent':381,970 'task':865 'telephoni':425,1383 'text':466,476,754,769,811,826,839,925,1042,1064,1075,1421,1526,1537,1569,1584,1614,1643,1681,1693 'text-to-speech':810,1041,1420,1536,1583,1613 'text/markdown':206 'throttl':351,940 'time':263,1137,1444,1582 'tool':153 'topic':461,537,686,872,889,946,1034,1375,1603 'topic-agent' 'topic-agent-skills' 'topic-agentic-skills' 'topic-agentskill' 'topic-ai-agents' 'topic-ai-coding' 'topic-azure' 'topic-azure-functions' 'topic-azure-kubernetes-service' 'topic-azure-openai' 'topic-azure-sql-database' 'topic-azure-storage' 'track':583 'train':344,401,563,646,740,911,1119,1224 'transcript':479,546,558,692,1053,1213,1391,1474,1519 'translat':427,1433,1476 'troubleshoot':12,50,214,460,463,507,515 'truncat':599 'tts':341,1318 'tts/avatars':426 'tune':256,1107 'understand':745,916 'up':1069 'upload':1114,1221 'url':462,538,687,873,890,947,1035,1376,1604 'usag':335,424,590 'use':29,31,81,87,105,120,177,194,309,606,861,921,988,1158,1232,1255,1285,1398,1512,1523,1548,1592,1605,1699 'user':142,159,595,1493 'v3':809 'v3.0':829 'v3.1':831,842 'v3.2':758,844 'valid':1223 'version':146,292 'via':1505 'video':676 'virtual':1015 'visem':1159 'vnet':371 'voic':264,307,314,343,380,400,405,421,526,568,601,610,645,657,701,705,816,854,877,880,903,913,969,974,1205,1228,1282,1324,1338,1352,1366,1413,1445,1448,1461,1497,1503,1507,1543,1593 'voice/avatars':252 'webpag':196 'websocket':1595 'whisper':862 'workflow':459","prices":[{"id":"9788c7ef-410b-421c-8f02-0e9b4521115f","listingId":"81eca933-4026-493b-97fe-99e1572abaee","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"MicrosoftDocs","category":"Agent-Skills","install_from":"skills.sh"},"createdAt":"2026-04-18T22:00:10.107Z"}],"sources":[{"listingId":"81eca933-4026-493b-97fe-99e1572abaee","source":"github","sourceId":"MicrosoftDocs/Agent-Skills/azure-speech","sourceUrl":"https://github.com/MicrosoftDocs/Agent-Skills/tree/main/skills/azure-speech","isPrimary":false,"firstSeenAt":"2026-04-18T22:00:10.107Z","lastSeenAt":"2026-04-22T00:53:37.731Z"}],"details":{"listingId":"81eca933-4026-493b-97fe-99e1572abaee","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"MicrosoftDocs","slug":"azure-speech","github":{"repo":"MicrosoftDocs/Agent-Skills","stars":497,"topics":["agent","agent-skills","agentic-skills","agentskill","ai","ai-agents","ai-coding","azure","azure-functions","azure-kubernetes-service","azure-openai","azure-sql-database","azure-storage","azure-virtual-machine","claude-code","github-copilot","microsoft-learn","openai-codex","skills"],"license":"cc-by-4.0","html_url":"https://github.com/MicrosoftDocs/Agent-Skills","pushed_at":"2026-04-19T02:43:40Z","description":"Curated Agent Skills for Microsoft & Azure – giving AI coding assistants structured, real-time expertise from Microsoft Learn docs.","skill_md_sha":"ddc04f2d8c43754ed0049944bf104c39c008fb08","skill_md_path":"skills/azure-speech/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/MicrosoftDocs/Agent-Skills/tree/main/skills/azure-speech"},"layout":"multi","source":"github","category":"Agent-Skills","frontmatter":{"name":"azure-speech","description":"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 using Speech/Voice SDKs, STT/TTS, custom speech or neural voices, Voice Live/avatars, or telephony flows, 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 Notification Hubs (use azure-notification-hubs), Azure AI Video Indexer (use azure-video-indexer).","compatibility":"Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation."},"skills_sh_url":"https://skills.sh/MicrosoftDocs/Agent-Skills/azure-speech"},"updatedAt":"2026-04-22T00:53:37.731Z"}}