AU

Transcribes audio files locally to generate summaries and extract action items.

Install

mkdir -p .claude/skills/audio-transcription && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16329" && unzip -o skill.zip -d .claude/skills/audio-transcription && rm skill.zip

Installs to .claude/skills/audio-transcription

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Transcribe inbound audio clips to text using local Whisper (faster-whisper). Use when the user sends voice notes/audio files and asks what was said, asks for transcript/summary/action items, or asks to process audio privately on-host. Default model is small.en for better English accuracy on constrained hosts.
310 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Beginner

Key capabilities

  • Transcribe audio clips to text using local Whisper models
  • Generate a short summary (2-4 bullets) from the transcript
  • Extract action items or questions from the transcribed audio
  • Process audio privately on-host
  • Use `small.en` model by default for English accuracy on constrained hosts
  • Offer `base.en` model as a fallback for lower-resource environments

How it works

The skill executes a Python script that uses the local Whisper (faster-whisper) library to transcribe an input audio file, then processes the transcript to generate a summary and extract action items.

Inputs & outputs

You give it
Audio file path
You get back
Transcript, short summary, and extracted action items

When to use audio-transcription

  • Transcribing meeting voice notes
  • Processing audio files locally
  • Extracting tasks from voice memos

About this skill

Audio Transcription (Local, small.en)

Use local transcription by default with small.en.

Default command

python3 skills/audio-transcription/scripts/transcribe_local.py \
  --input "<audio-path>" \
  --model small.en

Fast/lower-resource fallback

python3 skills/audio-transcription/scripts/transcribe_local.py \
  --input "<audio-path>" \
  --model base.en

What to return to user

  1. Transcript (verbatim best-effort)
  2. Short summary (2-4 bullets)
  3. Action items/questions extracted from transcript
  4. If confidence seems low, say so clearly

Notes

  • First run downloads model weights (~500MB for small.en).
  • Keep transcripts concise in chat; offer full dump on request.
  • Treat audio content as sensitive by default; do not share externally.

When not to use it

  • When the user wants to process audio using an external service
  • When the user does not want a local, on-host transcription
  • When the user does not want a summary or action items from the audio

Limitations

  • First run downloads model weights (~500MB for `small.en`)
  • Transcripts should be kept concise in chat, with full dump offered on request
  • Audio content is treated as sensitive and not shared externally

How it compares

This skill performs audio transcription and summarization locally on the host, ensuring data privacy and avoiding external API calls, unlike cloud-based transcription services.

Compared to similar skills

audio-transcription side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
audio-transcription (this skill)05moReviewBeginner
diary03moReviewAdvanced
granola-local-dev-loop11moReviewIntermediate
video-downloader1017moReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry