skills.rest
MoonAxis
MoonAxisOFFICIAL
Explore all skills by this author →
GitHub

azure-ai-transcription-py

Transcribe audio and video to text using Azure AI services via the Python SDK.

Updated Aug 23, 2026
Search Tags:#transcription#audio processing#diarization#python sdk#speech to text#azure ai
One-click install
npx skills add https://github.com/MoonAxis/azure-stack --skill azure-ai-transcription-py
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: azure-ai-transcription-py
Source: https://github.com/MoonAxis/azure-stack/tree/main/skills/azure-ai-transcription-py
Command: npx skills add https://github.com/MoonAxis/azure-stack --skill azure-ai-transcription-py

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the conversion of audio and video content into accurate text transcriptions, making spoken information searchable, editable, and accessible.

Core Features & Use Cases

  • Batch Transcription: Process large audio files stored in cloud storage for offline transcription.
  • Real-time Transcription: Transcribe live audio streams with low latency.
  • Diarization: Identify and label different speakers within the audio.
  • Timestamping: Generate precise timestamps for words and phrases for subtitle creation or analysis.
  • Use Case: Automatically transcribe customer service calls to identify key issues, sentiment, and agent performance, or convert recorded lectures into searchable text documents.

Quick Start

Use the azure-ai-transcription-py skill to transcribe the audio file located at "https://<storage>/audio.wav" with speaker diarization enabled.

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 to text using Azure AI services in Python?▼

To transcribe audio files to text with Azure AI, use the Python SDK to configure batch processing or real-time streaming, authenticating via specific endpoint and key environment variables. The SDK handles audio file submission and returns accurate text transcriptions.

Can I identify different speakers during speech to text transcription?▼

Yes, speaker diarization is supported during speech to text transcription. The Azure AI Python SDK can identify and label different speakers within the audio, generating transcriptions that distinguish who spoke at specific timestamps.

Does Azure speech to text support real-time streaming and batch processing?▼

Azure speech to text supports both real-time streaming for live audio transcription with low latency and batch processing for large audio files stored in cloud storage, providing flexibility for various audio processing workflows.

Do I need Azure Blob Storage to process audio files for transcription?▼

Azure Blob Storage is required for batch transcription to provide content URLs for large audio files stored in the cloud. Real-time streaming transcription processes live audio without needing Blob Storage URLs for file submission.

How do I generate timestamps for words and phrases during audio transcription?▼

Timestamps for words and phrases are generated automatically during audio transcription by configuring the Azure AI Python SDK. The output provides precise timing data for each transcribed element, suitable for subtitle creation or detailed analysis.

Related Skills

Explore More Software Engineering Skills→
Umbral-BotUmbral-Bot

azure-platform

Manage Azure cloud services via Azure CLI and Python SDK.

Official
Advanced
hmzainjamilhmzainjamil
1

Transcription Automation

Convert audio and video recordings into transcripts, subtitles, and meeting notes.

Community
Advanced
partme-aipartme-ai
610

cloud-azure-storage

Manage Azure Storage accounts, blobs, file shares, and queues.

Official
Basic
astoreyaiastoreyai
3

stt-transcription

Transcribe audio from files or microphones using multiple speech-to-text engines.

Community
Advanced