Can this skill help with subtitle generation?

Yes, by enabling timestamp capture features, the skill helps generate the precise timing data required for SRT or VTT subtitle files.

Can I identify different speakers in a recording?

Yes, the skill includes best practices for enabling speaker diarization to distinguish between multiple participants in a single audio file.

Does this skill support real-time audio streaming?

Yes, it provides implementation patterns for using the TranscriptionClient to handle real-time audio streams with built-in backpressure management.

How should I handle very large audio files?

For long files stored in blob storage, the skill recommends using the batch transcription method (begin_transcription) rather than streaming.

What authentication method is required for this SDK?

This specific client requires subscription key authentication using an endpoint and key; DefaultAzureCredential is not currently supported for this library.

Azure AI Transcription for Python

Name: Azure AI Transcription for Python
Author: microsoft

bymicrosoft

•

1,777

•

데이터 과학 및 ML

Implements high-accuracy speech-to-text capabilities including real-time streaming and batch processing with speaker diarization.

This skill equips Claude with the expertise to integrate and utilize the Azure AI Transcription SDK for Python, providing standardized patterns for converting spoken audio into text. It covers both real-time streaming for live applications and batch processing for large-scale audio files stored in cloud storage. By offering guidance on complex tasks like multi-speaker diarization, timestamp generation, and session management, this skill helps developers build robust voice-enabled applications while ensuring efficient handling of audio backpressure and authentication.

주요 기능

01Support for global locales and language identification

02Automated session and backpressure management for streaming

031,777 GitHub stars

04Precise timestamp generation for subtitling and indexing

05Real-time and batch speech-to-text transcription

06Multi-speaker diarization for meeting transcripts

사용 사례

01Processing large audio archives for searchable text databases

02Generating automated meeting minutes with speaker labels

03Building real-time captioning systems for live broadcasts

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add microsoft/skills azure-ai-transcription-py

For use in Claude.ai and ChatGPT

주요 기능

01Support for global locales and language identification

02Automated session and backpressure management for streaming

031,777 GitHub stars

04Precise timestamp generation for subtitling and indexing

05Real-time and batch speech-to-text transcription

06Multi-speaker diarization for meeting transcripts

사용 사례

01Processing large audio archives for searchable text databases

02Generating automated meeting minutes with speaker labels

03Building real-time captioning systems for live broadcasts

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add microsoft/skills azure-ai-transcription-py

For use in Claude.ai and ChatGPT