Transcribes audio files into text with advanced speaker identification and diarization using OpenAI models.
This skill empowers Claude to convert audio and video recordings into highly accurate text, offering specialized features like speaker diarization and known-speaker hints. By leveraging a dedicated Python CLI and OpenAI's transcription models, it automates the extraction of dialogue from meetings, interviews, and presentations. The skill handles complex tasks such as multi-speaker labeling, automatic chunking for long-form content, and offers flexible output formats including plain text and structured JSON. It is an essential tool for developers and researchers who need to integrate high-fidelity speech-to-text processing directly into their automated workflows.
Key Features
010 GitHub stars
02High-speed transcription using gpt-4o-mini-transcribe
03Automatic chunking strategy for long audio files
04Multiple output formats including plain text and diarized JSON
05Known-speaker referencing for accurate identity labeling
06Advanced speaker diarization for multi-person audio
Use Cases
01Processing large batches of audio files for data analysis
02Extracting text content from video recordings for documentation
03Generating labeled transcripts for team meetings and interviews
