Setup & Installation
npx skills add https://github.com/microsoft/skills --skill azure-ai-transcription-py
https://github.com/microsoft/skills/tree/main/.github/plugins/azure-sdk-python/skills/azure-ai-transcription-py
View on GitHubWhat This Skill Does
Azure AI Transcription SDK for Python wraps the Azure Cognitive Services speech-to-text API. It supports both real-time streaming and batch transcription, with options for speaker diarization and timestamps.
Instead of polling the Azure REST API directly and managing job state yourself, the SDK handles batch job polling and streaming session lifecycle with a few method calls.
When to use it
- Transcribing recorded meeting audio with speaker labels
- Generating subtitles from video files stored in Azure Blob Storage
- Converting customer call recordings to searchable text
- Running real-time captions for a live audio stream
- Batch processing a folder of interview recordings overnight