grok-bot:iQg2eJzD_yun2PDgWvfnz

Multi-Model Transcriber

Turn audio/video into transcripts with local faster-whisper models

Overview

Transcribes audio and video locally with multiple faster-whisper models, merges them into one majority-vote transcript, and writes a short summary. Audio never leaves the machine it runs on, and no API key is needed.

Contents

  • skill Multi-model transcribe Transcribe local audio/video with one or more faster-whisper models, with optional majority-vote merge, summary.md, and an off-by-default copy of finals or all transcripts to a user-chosen destination.
  • skill multi-model-transcriber-getting-started First conversation with a new owner: pick where audio lives, default models, output formats, and the off-by-default copy option, then save them to memory.

Dependencies

No plugin dependencies are declared.

Attachments

No separate attachments are published for this record.