agentleFS
montezuma-pmontezuma-p/harken/.claude/skills/transcribe-audio/SKILL.md

transcribe-audio

Skill12 starsChanged 3 months agoApache-2.0View on GitHub

Use when a task requires reading, transcribing, or extracting content from audio or voice — WhatsApp PTT/voice notes (.opus/.ogg), meeting recordings, .mp3/.m4a/.wav/.mp4 files, or audio attachments inside a WhatsApp chat-export zip.

7 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions7 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 7

    1. barefootford/buttercut★ 625same name
    2. zedxter/utility-belt★ 4same name
    3. caiopizzol/skills★ 3same name
    4. valtterimelkko/agent-workflow-skills★ 2same name
    5. andfrancot-alt/claude-skills★ 0same name
    6. jwkchung/claude-skills★ 0same name
    7. umakhanpro/vocalingo-mcp★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never loop over files one harken invocation each: pass them all in one invocation (the model loads once per run, and per-file runs reload …

    line 45
  2. Very specific:

    If the harken MCP server is connected (claude mcp add harken -- harken mcp), prefer its tools — transcribe_file and …

    line 47

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Transcribe Audio (harken, local-only)

Transcribe audio with harken, a local whisper.cpp CLI (single static binary). Audio never leaves the machine — do not send audio to cloud transcription APIs, and do not write inline whisper one-liners (they reload the model per file; harken loads it once per batch).

Invocation: use harken ... if the command is on PATH. If it is missing, install it with the one-liner (no Python, no runtime deps):

curl --proto '=https' --tlsv1.2 -LsSf \
  https://github.com/montezuma-p/harken/releases/latest/download/harken-installer.sh | sh
# Batch: files, dirs, or globs (model loads once per run)
harken ~/Downloads/audios/*.opus --out /path/to/transcripts

# WhatsApp export zip: no manual unzip needed; dates inclusive
# (quote paths with spaces using $HOME — a quoted ~ does not expand)
harken whatsapp "$HOME/Downloads/WhatsApp Chat - X.zip" \
  --from 2026-07-13 --to 2026-07-14 --out /path/to/out --merge
  • Outputs: per-file .txt + manifest.jsonl (source, text, duration) in --out. Existing outputs are skipped; --force redoes them.
  • --merge writes _chat.transcribed.txt — the chat with each voice note's transcript inlined (>> [transcript] ...).
  • Defaults: --lang pt, --model small, CPU (safe everywhere, no GPU required).
  • --lang auto for non-Portuguese audio; --model medium when accuracy matters more than speed; --model small-q5_1 for a 60% smaller download; --format json|srt|md for timestamps (md is the readable one: one [hh:mm:ss] line per segment).
  • First ever run downloads the ggml model (~466 MB for small) to ~/.cache/harken/models; after that it works fully offline. harken warm (or harken warm --model medium) pre-downloads without transcribing — useful right after installing.
  • Never loop over files one harken invocation each: pass them all in one invocation (the model loads once per run, and per-file runs reload it).
  • If the harken MCP server is connected (claude mcp add harken -- harken mcp), prefer its tools — transcribe_file and transcribe_whatsapp_export — over the shell invocations above; the CLI remains the fallback. Its transcribe_status tool reports the model cache state without transcribing anything — whether the first call would download, or is already waiting on a startup download in flight.
  • Full docs: README.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.