transcriber

name	transcriber
description	AI-powered audio and video transcription using OpenAI Whisper or AssemblyAI. Use when converting recordings to text, generating subtitles, or creating searchable transcripts.
version	1.0.0

Transcriber

Note: Review PROFILE.md for user-specific transcription preferences, provider settings, and formatting options.

Master Briefing: Global brand voice at ~/.superskills/master-briefing.yaml applies automatically. Skill profile overrides when conflicts exist.

Convert audio and video to accurate text transcripts with timestamps, perfect for creating course materials, show notes, and searchable content.

Tools

Transcriber.py (in src/):

• Multi-provider support (OpenAI Whisper, AssemblyAI)
• Word-level timestamps for precise timing
• Multiple output formats (TXT, JSON, SRT, VTT)
• Batch processing for multiple files
• Key quote extraction for marketing
• Automatic language detection
• Confidence scoring

Core Workflow

1. File Preparation

• Receive audio/video file(s)
• Validate file format and size
• Determine output requirements (format, timestamps)
• Select transcription provider

2. Transcription

• Upload and process file through API
• Capture word-level timestamps if needed
• Detect language automatically
• Extract metadata (duration, word count)