This skill provides expert guidance for Azure Speech in Foundry Tools. 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), useread_filewith the specified lines. For categories with file links (e.g.,[security.md](security.md)), useread_fileon the linked reference file
IMPORTANT for Agent: If
metadata.generated_atis more than 3 months old, suggest the user pull the latest version from the repository. Ifmcp_microsoftdocstools 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_fetchwith query stringfrom=learn-agent-skill. Returns Markdown. - Fallback: Use
fetch_webpagewith query stringfrom=learn-agent-skill&accept=text/markdown. Returns Markdown.
Category Index
| Category | Lines | Description |
|---|---|---|
| Troubleshooting | L36-L43 | Diagnosing and fixing common Azure Speech issues across TTS, STT, SDK, containers, CRL compatibility, and retrieving session/transcription IDs for support. |
| Best Practices | L44-L61 | Best practices for audio/video prep, custom voice/avatar training, latency and memory tuning, accuracy boosts (phrases/keywords), reliability (CRL, backups), and Voice Live handling/evaluation |
| Decision Making | L62-L75 | Guidance on choosing access methods and devices, and step-by-step migration paths between Speech/Custom Voice/STT/TTS APIs, Long Audio, and retired intent recognition features. |
| Limits & Quotas | L76-L82 | Managing custom speech/voice models and endpoints, plus quotas, capacity limits, and scaling constraints for Azure Speech workloads. |
| Security | L83-L94 | Securing Azure AI Speech: auth (Entra, RBAC), network isolation (VNet, Private Link, sovereign clouds), encryption/BYOK, BYOS storage, and consent/compliance for personal/professional voice. |
| Configuration | L95-L128 | Configuring Azure Speech behavior: recognition, TTS, avatars, containers, logging, storage, SSML, audio inputs, language/diarization, and Voice Live/SDK runtime and tracing options. |
| Integrations & Coding Patterns | L129-L164 | Patterns and APIs for integrating Azure Speech and Voice Live with apps, agents, telephony, and WebRTC, including STT, TTS, avatars, translation, function calling, and streaming events. |
| Deployment | L165-L175 | Deploying and running Azure Speech services (STT, TTS, language ID) via containers, Kubernetes/Helm, and batch APIs, including custom models and on-premises setups. |
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 |
| 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
Decision Making
Limits & Quotas
| Topic | URL |
|---|---|
| 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 |
| Custom voice endpoint limits for Speech service | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-deploy-endpoint |
| Review quotas and limits for Azure Speech workloads | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits |