Skip to content
Agentmart
Submit a tool

whisper-audio-transcriber

Transcribe local audio to plain text with whisper-cpp; default language is Italian.

Skill by mameli

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/mameli-whisper-audio-transcriber

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Transcribe local audio to plain text with whisper-cpp; default language is Italian.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Shell scripts

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/whisper-audio-transcriber

What's inside

Skill name
whisper-audio-transcriber
Description
Transcribe local audio to plain text with whisper-cpp; default language is Italian.
License
MIT
Instructions
15 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (3)

  • SKILL.md
  • openai.yaml · agents/
  • transcribe_audio.sh · scripts/

SKILL.md (first lines)

# Local audio transcription

Run `zsh scripts/transcribe_audio.sh "audio-path"` from this skill directory. Default to Italian; use `--language en` when the user specifies English. Respect another supported language when explicitly requested.

The helper requires `ffmpeg`, `whisper-cli` and a local GGML model. It uses `$WHISPER_MODEL_PATH` when present; `--model "model-path"` overrides it.

The helper creates `YYYY-MM-DD_HH-MM_file-name/` beside the source, containing a copy of the original, a mono 16 kHz PCM WAV and `*_transcript.txt`. Keep generated files there even for WAV input. Preserve the source.

Verify successful completion and a usable transcript, then return the transcript and output-folder links. Produce subtitles only when requested.

## Local configuration

Run the helper with `zsh` or directly via its shebang, not `bash`. Model precedence is `--model`, then `WHISPER_MODEL_PATH`, then a model in `WHISPER_MODEL_DIR` (default `$HOME/.local/share/whisper/models`). Prefer `ggml-medium.bin`, then an available `ggml-*.bin`. Do not assume a particular user home or model installation.

From mameli/skills, MIT.

More from mameli/skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 14, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from mameli

Cite this page

whisper-audio-transcriber skill. Agent Mart. https://agentmart.dev/skills/mameli-whisper-audio-transcriber (last updated 2026-10-24)