theam/claude-open-marketplace/transcribe

Claude Code and agent skill by theam/claude-open-marketplace

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Transcribe audio files with speaker diarization using local ML models. Works in both Claude Code and Cowork mode.

Install

npx vskill@latest install theam/claude-open-marketplace/transcribe

SKILL.md

Transcribe Audio

Transcribe an audio file locally with speaker diarization. All processing happens on your machine — no data leaves your device.

How to use

Run the CLI transcription tool via Bash. The plugin directory is:

PLUGIN_DIR=$(dirname "$(dirname "$(which transcribe_cli.py 2>/dev/null || echo "")")")

Use the following command pattern:

bash
uv run --directory {PLUGIN_DIR} python transcribe_cli.py "{audio_file}" [options]

Where {PLUGIN_DIR} is the absolute path to the transcription plugin directory (the directory containing transcribe_cli.py). To find it, look for the transcription plugin in the installed plugins — it will be under plugins/transcription/ in the monkey-tools plugin directory.

Arguments
ArgumentDescription
audio_file(required) Path to the audio file (.m4a, .mp3, .wav, .flac, .ogg, .aac, .mp4)
--language LANGLanguage code (e.g., en, es). Auto-detected if omitted.
--skip-diarizationSkip speaker identification for faster processing.
--num-speakers NExact number of speakers if known.
--min-speakers NMinimum expected number of speakers.
--max-speakers NMaximum expected number of speakers.
--model REPOMLX model override (e.g., mlx-community/whisper-large-v3-turbo for speed).
--export FORMATOutput format: txt (default), json, or srt.
Examples

Basic transcription:

bash
uv run --directory /path/to/plugins/transcription python transcribe_cli.py "/path/to/audio.m4a"

With language hint and JSON export:

bash
uv run --directory /path/to/plugins/transcription python transcribe_cli.py "/path/to/audio.m4a" --language es --export json

Fast mode (skip diarization):

bash
uv run --directory /path/to/plugins/transcription python transcribe_cli.py "/path/to/audio.m4a" --skip-diarization

Notes

  • First run installs ML dependencies (~2GB). This is cached for subsequent uses.
  • Apple Silicon: Automatically uses MLX for ~5x real-time transcription speed.
  • Output: Summary stats go to stderr. Clean transcript goes to stdout.
  • The transcript text is printed to stdout — capture it or read it directly from the Bash output.

Platform Notes

  • Claude Code (macOS/Apple Silicon): Full support. Uses MLX GPU acceleration. Deps auto-install via uv or pip.
  • Claude Code (Linux/Intel Mac): CPU-only mode (no MLX). Slower but functional.
  • Cowork: CPU-only. Requires Python 3.11+ in the VM. Network restrictions may prevent auto-install of ML deps — pre-install with uv pip install -e ".[ml]" if needed.
  • Pre-install deps to avoid first-run delay: uv pip install -e ".[ml-apple]" (Apple Silicon) or uv pip install -e ".[ml]" (other platforms).

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/theam/claude-open-marketplace/transcribe/badge)](https://verified-skill.com/skills/theam/claude-open-marketplace/transcribe)

Something wrong with this skill or its page? Tell us.