Habilidades Azure AI Transcription SDK for Python
📦

Azure AI Transcription SDK for Python

Seguro

Transcribe Audio with Azure AI

Need accurate speech-to-text transcription for audio files or real-time streams. This skill provides Python SDK integration for Azure AI Transcription with batch processing and streaming support.

Soporta: Claude Codex Code(CC)
🥉 73 Bronce
1

Descargar el ZIP de la skill

2

Subir en Claude

Ve a Configuración → Capacidades → Skills → Subir skill

3

Activa y empieza a usar

Pruébalo

Usando "Azure AI Transcription SDK for Python". Transcribe audio file at https://storage.example.com/meeting.wav

Resultado esperado:

The transcription job is submitted. Job ID: abc123. Status: InProgress. Once complete, the result will include text segments with timestamps and speaker labels if diarization is enabled.

Usando "Azure AI Transcription SDK for Python". Set up real-time transcription for English audio

Resultado esperado:

Streaming transcription session initialized. Locale: en-US. The stream will output transcribed text events as audio is processed.

Auditoría de seguridad

Seguro
v1 • 2/24/2026

This is a prompt-only documentation skill containing only informational content about the Azure AI Transcription SDK. No executable code, scripts, or network calls are present. The skill provides usage examples for batch and real-time transcription. Risk score is 0/100.

0
Archivos escaneados
0
Líneas analizadas
0
hallazgos
1
Auditorías totales
No se encontraron problemas de seguridad
Auditado por: claude

Puntuación de calidad

38
Arquitectura
100
Mantenibilidad
87
Contenido
50
Comunidad
100
Seguridad
83
Cumplimiento de la especificación

Lo que puedes crear

Meeting Transcription

Transcribe recorded meetings or conference calls with speaker identification

Media Content Subtitles

Generate timestamped subtitles for video content from audio tracks

Call Center Analytics

Convert customer call recordings to text for analysis and quality assurance

Prueba estos prompts

Basic Batch Transcription 
Use the Azure AI Transcription skill to transcribe the audio file at URL https://example.com/meeting.wav with diarization enabled.
Multi-File Transcription 
Use the Azure AI Transcription skill to transcribe multiple audio files from these URLs: [list URLs]. Enable diarization and use en-US locale.
Real-time Stream Transcription 
Use the Azure AI Transcription skill to set up real-time transcription for a live audio stream. Configure for English locale.
Subtitle Generation 
Use the Azure AI Transcription skill to transcribe video audio and generate SRT subtitle file with timestamps. The video is at https://example.com/presentation.mp4.

Mejores prácticas

  • Enable diarization when transcribing multi-speaker audio to identify each speaker
  • Use batch transcription for files over 1 minute to optimize costs and reliability
  • Specify the locale parameter to improve transcription accuracy for known languages

Evitar

  • Using DefaultAzureCredential - this client only supports subscription key authentication
  • Processing audio without checking transcription job status before retrieving results
  • Not handling transcription session cleanup for real-time streams

Preguntas frecuentes

What authentication methods are supported?
This SDK supports only subscription key authentication via TRANSCRIPTION_KEY environment variable. DefaultAzureCredential is not supported.
Can I transcribe local audio files directly?
For batch transcription, audio files must be accessible via HTTPS URLs. Consider uploading to Azure Blob Storage first. Real-time transcription can accept local audio files.
What is speaker diarization?
Diarization identifies and labels different speakers in the audio. Enable with diarization_enabled=True to get speaker labels in the transcription output.
How are timestamps provided?
Transcription results include offset timestamps for each word or segment, enabling subtitle generation and synchronized audio-text applications.
What audio formats are supported?
Azure AI Transcription supports common audio formats including WAV, MP3, and FLAC. Check Azure documentation for the full list of supported formats.
Can I use this for multilingual transcription?
Yes, specify the locale parameter when starting transcription. Supported locales include en-US, en-GB, es-ES, fr-FR, de-DE, and many others.

Detalles del desarrollador

Autor

sickn33

Licencia

MIT

Repositorio

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/azure-ai-transcription-py

Ref.

main

Estructura de archivos

📄 SKILL.md