azure-ai-transcription-py

Transcribe Azure Blob Storage audio with speaker attribution and timestamps.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/davidrrowley/CortexYouV3 --skill azure-ai-transcription-py-davidrrowley
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: azure-ai-transcription-py
Source: https://github.com/davidrrowley/CortexYouV3/tree/main/.agents/skills/azure-ai-transcription-py
Command: npx skills add https://github.com/davidrrowley/CortexYouV3 --skill azure-ai-transcription-py-davidrrowley

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Converts audio into reliable, timestamped text and speaker-attributed transcripts so teams can index, search, subtitle, and analyze recorded meetings and calls without manual transcription.

Core Features & Use Cases

  • Batch transcription for long recordings stored in Azure Blob Storage with job status checks and result retrieval.
  • Real-time streaming for live captioning and low-latency transcription consumption.
  • Diarization and timings to identify speakers, produce phrase- and word-level timestamps, and generate subtitles or meeting summaries.
  • Python SDK integration with environment-variable driven subscription key authentication and guidance for resource cleanup and error handling.
  • Use Case: Transcribe a multi-speaker meeting, attribute text to speakers, and export SRT subtitles with accurate timing.

Quick Start

Set TRANSCRIPTION_ENDPOINT and TRANSCRIPTION_KEY, then call begin_transcription with locale and content_urls for batch jobs or begin_stream_transcription for live streams.

Frequently Asked Questions about azure-ai-transcription-py

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe audio files into timestamped text with Python?

You can transcribe audio files into timestamped text using Python by calling begin_transcription with locale and content_urls for batch jobs, or begin_stream_transcription for live streams.

Can I identify speakers in meeting recordings using Azure speech-to-text?

Yes, Azure speech-to-text supports diarization to identify speakers in meeting recordings, producing speaker-attributed transcripts with phrase- and word-level timestamps for accurate subtitle generation.

Does this batch transcription approach work with audio stored in Azure Blob Storage?

Batch transcription works with audio stored in Azure Blob Storage by submitting content URLs to the transcription job and polling job status checks until results are retrieved.

What do I need to set up before authenticating Azure speech-to-text in Python?

You need to set the TRANSCRIPTION_ENDPOINT and TRANSCRIPTION_KEY environment variables for subscription key authentication before initializing the Python SDK client.

How do I generate SRT subtitles from a multi-speaker recording?

You generate SRT subtitles by transcribing the recording with diarization enabled, extracting phrase- and word-level timestamps, and exporting the timed text with speaker attribution.

What are the limitations of streaming transcription for real-time audio processing?

Streaming transcription requires proper stream and client cleanup to maintain robust workflows, and you must handle low-latency consumption and error handling carefully to avoid resource leaks.