mcpField
T
transcribe-audio

transcribe-audio

github.com/barefootfordCreative & media61491 installsUpdated 5w ago
Repository

About transcribe-audio

A ButterCut skill for transcribing video audio with WhisperX into JSON transcripts with word-level timing. In the library workflow, transcription runs through a shared mechanical job; a separate step can refine transcripts using library context.

Key features

  1. 01WhisperX audio transcription
  2. 02Word-level timing in JSON
  3. 03Configurable language and model
  4. 04Separate context-based refinement

Use cases

  1. 01Create timed transcripts for video clips
  2. 02Prepare transcripts for footage analysis
  3. 03Refine names using library context

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/barefootford/buttercut --skill transcribe-audio

After installing, type/transcribe-audioin Claude Code to confirm it loaded.

Bundled filesagent_prompt.mdrefine_instructions.md

Details

From the project README

Skill: Transcribe Audio (parent brief)

Note: In the library pipeline, transcription runs mechanically via ruby lib/buttercut/process_footage.rb transcripts <library> (using TranscribeJob), not by dispatching this sub-agent — so footage analysis comes out identical across models. The WhisperX command lives in exactly one place, lib/buttercut/transcribe_job.rb, which also runs standalone: ruby lib/buttercut/transcribe_job.rb <video_path> <output_dir> <language_code> <whisper_model>. refine_instructions.md remains the playbook for the separate (judgment) refinement step that analyze-video Step 3 dispatches.

Transcribes video audio using WhisperX and produces a clean JSON transcript with word-level timing.

SKILL.md is the parent's dispatch brief. The sub-agent's working prompt lives in agent_prompt.md — inline its contents when launching the Task agent. Don't pass SKILL.md.

Parallelism

Launch at most 2 in parallel. WhisperX is already multithreaded internally (~4 CPU threads via CTranslate2); 2 processes is the throughput-vs-RAM sweet spot on a 16GB machine.

Inputs to gather and pass inline

The parent reads library.yaml and settings.yaml and passes these values inline in each agent's prompt:

  • video_path — absolute path to the video file
  • transcript_output_dir — where to write the transcript JSON (e.g. libraries/<library>/transcripts)
  • language_code — ISO 639-1 code (e.g. en, es) — parent maps from library.yaml's language name
  • whisper_model — model size from settings.yaml (e.g. small, medium, turbo)
  • transcript_refinement — boolean from library.yaml. If true, also pass:
    • user_context (may be empty string)
    • footage_summary (may be empty string)

After the agent returns, update library.yaml with transcript: <filename>.json.

Next step

Once all videos have audio transcripts, dispatch analyze-video for visual descriptions.

Dependencies

WhisperX must be installed. Use the setup skill to verify.

Comments

Markdown supported