azure-speech

What this skill does

# 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](https://github.com/MicrosoftDocs/mcp/blob/main/README.md)

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

| Category | Lines | Description |
|----------|-------|-------------|
| Troubleshooting | L36-L44 | Diagnosing 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 Practices | L45-L61 | Best practices for collecting and labeling audio/video, training custom voices/avatars, tuning recognition (phrases/keywords), optimizing latency/memory, and handling Voice Live agent behavior. |
| Decision Making | L62-L79 | Guidance on planning large-scale speech workloads, choosing embedded/offline or personal voice options, and migrating between Speech/Voice REST APIs, models, and regions. |
| Limits & Quotas | L80-L89 | Speech service limits, quotas, and throttling, plus lifecycle, training, deployment, and usage constraints for custom/professional voice and short-audio speech-to-text APIs. |
| Security | L90-L103 | Securing 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. |
| Configuration | L104-L136 | Configuring Azure AI Speech behavior: audio inputs, logging, storage, SSML, pronunciation, batch TTS/STT, Voice Live settings, containers, and SDK/CLI connection and tracing options. |
| Integrations & Coding Patterns | L137-L165 | Patterns and code to integrate Azure Speech/Voice Live with apps and telephony: SDK/REST usage, TTS/STT/translation, avatars, SSML, LLM/Foundry/Power Automate, and real-time agent flows. |
| Deployment | L166-L177 | 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. |

### Troubleshooting
| Topic | URL |
|-------|-----|
| 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 |
| Resolve common Azure Speech in Foundry issues | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/known-issues |
| 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 |
| Troubleshoot Azure Speech containers deployment issues | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-faq |
| Diagnose and fix common Azure Speech SDK issues | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/troubleshooting |

### Best Practices
| Topic | URL |
|-------|-----|
| Prepare and locate audio data for batch transcription | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription-audio-data |
| 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 |
| Prepare training data for professional custom voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-voice-training-data |
| 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 |
| 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 |
| Handle interrupted responses in Voice Live chat history | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-auto-truncation |
| Evaluate and benchmark Voice Live voice agents | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-voice-live-evaluate |
| Use phrase lists to improve Azure Speech recognition | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/improve-accuracy-phrase-list |
| Apply keyword recognition design and accuracy guidelines | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/keyword-recognition-guidelines |
| Record high-quality samples for custom voice training | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/record-custom-voice-samples |
| Back up and recover custom Speech and Voice resources | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/resiliency-and-recovery-plan |
| Design microphone arrays optimized for Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-sdk-microphone |
| 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 |

### Decision Making
| Topic | URL |
|-------|-----|
| Plan large-scale transcription with batch processing | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription |
| Evaluate custom voice lite before professional voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/custom-neural-voice-lite |
| Choose Embedded Speech for offline and hybrid scenarios | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/embedded-speech |
| Evaluate device suitability for embedded speech models | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/embedded-speech-performance-evaluations |
| Check Azure Speech language and voice availability | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support |
| 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 |
| 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 |
| Migrate from retired Speech intent recognition to Language or OpenAI | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-intent-recognition |
| Migrate from Long Audio API to Batch synthesis | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-to-batch-synthesis |
| 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 |
| 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 |
| Migrate Speech to text REST API v3.1 to v3.2 | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/migrate-v3-1-to-v3-2 |
| Assess capabilities and regions for personal voice | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-overvi