跳到正文
TakoAPI
返回技能列表

azure-ai-transcription-py

由 thegovind 提供

DevOps & Cloud
1.7k下载量由 clawskills.sh 提供
1星标
1浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Azure AI Transcription SDK for Python.

描述

该技能的功能

Python client library for Microsoft Azure's speech-to-text service. Supports batch transcription of audio files stored in blob storage and real-time streaming transcription with per-event text output. Speaker diarization and timestamp capture are available in both modes.

Combines batch and real-time transcription with built-in diarization in a single client, removing the need to stitch together separate Azure services or third-party speaker separation tools.

何时使用

  • Transcribing recorded meeting audio with speaker labels
  • Generating subtitle files from video recordings
  • Real-time captioning of live audio streams
  • Processing large call center recordings stored in blob storage
  • Converting interview audio to searchable text

示例工作流

输入

User asks: Transcribe this meeting recording and label each speaker

智能体
  1. 1

    Initialize TranscriptionClient with TRANSCRIPTION_ENDPOINT and TRANSCRIPTION_KEY

  2. 2

    Call begin_transcription with the audio file URL, locale set to en-US, and diarization_enabled=True

  3. 3

    Poll the returned job handle until result is available

  4. 4

    Read result.status and iterate over transcribed segments with speaker labels

输出

Full text transcript with each segment attributed to a distinct speaker

前置要求

  • Azure account with a Cognitive Services resource
  • TRANSCRIPTION_ENDPOINT environment variable (Azure Cognitive Services endpoint URL)
  • TRANSCRIPTION_KEY environment variable (Azure subscription key)

安装

clawhub install thegovind/azure-ai-transcription-py

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接