e7ae616385
Rewrote sync_microsoft_skills.py (v4) to use each SKILL.md's frontmatter 'name' field as the flat directory name under skills/, replacing the nested skills/official/microsoft/<lang>/<category>/<service>/ hierarchy. This fixes CI failures caused by the indexing, validation, and catalog scripts expecting skills/<id>/SKILL.md (depth 1). Changes: - Rewrite scripts/sync_microsoft_skills.py for flat output with collision detection - Update scripts/tests/inspect_microsoft_repo.py for flat name mapping - Update scripts/tests/test_comprehensive_coverage.py for name uniqueness checks - Delete skills/official/ nested directory - Add 129 Microsoft skills as flat directories (e.g. skills/azure-mgmt-botservice-dotnet/) - Move attribution files to docs/ (LICENSE-MICROSOFT, microsoft-skills-attribution.json) - Rebuild skills_index.json, CATALOG.md, README.md (845 total skills)
70 lines
1.7 KiB
Markdown
70 lines
1.7 KiB
Markdown
---
|
|
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.
|
|
Triggers: "transcription", "speech to text", "Azure AI Transcription", "TranscriptionClient".
|
|
package: azure-ai-transcription
|
|
---
|
|
|
|
# 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
|