developer tool_use skill risk: low
Azure Python Transcription SDK Guide
Provides installation instructions, authentication code, batch and real-time transcription examples, and best practices for the azure-ai-transcription Python client.
SKILL 1 file
SKILL.md
---
name: azure-ai-transcription-py
description: "Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization."
---
# Azure AI Transcription SDK for Python
Client library for Azure AI Transcription (speech-to-text) with real-time and batch transcription.
## Installation
```bash
pip install azure-ai-transcription
```
## Environment Variables
```bash
TRANSCRIPTION_ENDPOINT=https://<resource>.cognitiveservices.azure.com
TRANSCRIPTION_KEY=<your-key>
```
## Authentication
Use subscription key authentication (DefaultAzureCredential is not supported for this client):
```python
import os
from azure.ai.transcription import TranscriptionClient
client = TranscriptionClient(
endpoint=os.environ["TRANSCRIPTION_ENDPOINT"],
credential=os.environ["TRANSCRIPTION_KEY"]
)
```
## Transcription (Batch)
```python
job = client.begin_transcription(
name="meeting-transcription",
locale="en-US",
content_urls=["https://<storage>/audio.wav"],
diarization_enabled=True
)
result = job.result()
print(result.status)
```
## Transcription (Real-time)
```python
stream = client.begin_stream_transcription(locale="en-US")
stream.send_audio_file("audio.wav")
for event in stream:
print(event.text)
```
## Best Practices
1. **Enable diarization** when multiple speakers are present
2. **Use batch transcription** for long files stored in blob storage
3. **Capture timestamps** for subtitle generation
4. **Specify language** to improve recognition accuracy
5. **Handle streaming backpressure** for real-time transcription
6. **Close transcription sessions** when complete
## When to Use
This skill is applicable to execute the workflow or actions described in the overview.
## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
REQUIRED CONTEXT
- task clearly matches transcription workflow
ROLES & RULES
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
EXPECTED OUTPUT
- Format
- markdown
- Constraints
- include code examples
- list best practices
- specify when to use and limitations
EXAMPLES
Includes code examples for installation, authentication, batch transcription, and real-time transcription.
CAVEATS
- Missing context
- How the AI should format responses or use the provided code/examples
- Python version or dependency constraints
- Ambiguities
- The phrase 'workflow or actions described in the overview' is unclear because no explicit overview section exists.
QUALITY
- OVERALL
- 0.50
- CLARITY
- 0.75
- SPECIFICITY
- 0.65
- REUSABILITY
- 0.25
- COMPLETENESS
- 0.55
IMPROVEMENT SUGGESTIONS
- Replace the generic 'When to Use' paragraph with explicit instructions on when and how an agent should invoke or reference this skill.
- Add a required output format section for any code or explanations generated from this prompt.
USAGE
Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.
MORE FOR DEVELOPER
- Playwright Web App Testing Toolkitdevelopertool_use
- MCP Server Builder Guidedevelopertool_use
- Claude Skill Creation Guidedevelopertool_use
- Letta Platform Meta Agent Creator Guidedevelopertool_use
- Standalone Solr Search Engine Simulatordevelopertool_use
- AutoGPT Autonomous Agent Platform Guidedevelopertool_use
- CLIP Model Code Examples and Guidedevelopertool_use
- Lambda Labs GPU Cloud Guidedevelopertool_use
- Phoenix AI Observability Platform Guidedevelopertool_use
- Pinecone Vector Database Python Guidedevelopertool_use
- SGLang LLM Serving Framework Guidedevelopertool_use
- CrewAI Multi-Agent Orchestration Guidedevelopertool_use
- llama.cpp CPU GPU Inference Guidedevelopertool_use
- Whisper Speech Recognition Model Guidedevelopertool_use
- Claude Code Model Router with Cost Loggingdevelopertool_use
- Chroma Embedding Database Usage Guidedevelopertool_use
- Context7 Library Documentation Expertdevelopercoding
- Structured Python Production Code Generatordevelopercoding
- Minimax Music API Generation Agentdevelopercreative
- Angular Standalone Directive Generatordevelopercoding
- Pytest Unit Test Suite Generatordevelopercoding
- Unity Architecture Specialistdevelopercoding
- iOS App Store Compliance Auditordeveloperanalysis
- Reusable Enterprise Website Template Architectdevelopersoftware_engineering
- Web Typography CSS Generatordevelopercoding