Azure Ai Transcription Py — Azure AI Transcription Py

Azure AI Transcription SDK for Python

命令行工具ent 库 for Azure AI Transcription (speech-to-text) with real-time and batch transcription.

安装ation pip 安装 azure-AI-transcription

环境 Variables TRANSCRIPTION_端点=https://.cognitive服务s.azure.com TRANSCRIPTION_KEY=

Authentication

Use subscription key authentication (DefaultAzure凭证 is not supported for this 命令行工具ent):

导入 os from azure.AI.transcription 导入 Transcription命令行工具ent

命令行工具ent = Transcription命令行工具ent( 端点=os.environ["TRANSCRIPTION_端点"], 凭证=os.environ["TRANSCRIPTION_KEY"] )

Transcription (Batch) job = 命令行工具ent.begin_transcription( name="meeting-transcription", locale="en-US", content_urls=["https:///audio.wav"], diarization_enabled=True ) 结果 = job.结果() print(结果.状态)

Transcription (Real-time) 流 = 命令行工具ent.begin_流_transcription(locale="en-US") 流.发送_audio_file("audio.wav") for event in 流: print(event.text)

Best Practices Enable diarization when multiple speakers are present Use batch transcription for long files stored in blob storage Capture timestamps for subtitle generation Specify language to improve recognition accuracy Handle 流ing backpressure for real-time transcription Close transcription 会话s when complete