Skip to main content
skill CX Codex

transcribe · badlogic — Claude Code skill: local audio transcription on macOS

The transcribe skill for Claude Code transcribes speech locally on Apple Silicon Macs. It handles wav directly and converts other formats via ffmpeg.

MIT 851 installs ★ 2,663 updated 2026-06-06

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add badlogic/pi-skills --skill transcribe -a claude-code
Open on GitHub

What transcribe does

The skill runs parakeet-cpp-transcribe and prints plain text with timestamps to stdout. Output is split into 15-second chunks: [00:00-00:15] transcript text, then the next block.

On first launch it fetches the arm64 macOS binary from a badlogic/pibot GitHub release into the extension's bin folder. The GGUF model downloads itself when missing.

Non-WAV audio needs ffmpeg — install it with brew install ffmpeg. Without it only wav files work. Model and GGML logs go to stderr; add 2>/dev/null to keep the output clean.

What it helps with

  • turn voice memos into searchable text
  • get a transcript with per-second timestamps
  • transcribe audio without sending files to a cloud API
  • handle mp3 and other formats via ffmpeg

Example prompts for the agent

  • Transcribe meeting.wav with the transcribe skill
  • Run transcribe on interview.mp3 and show me the text
  • Give me a timestamped transcript of voice-memo.m4a

How to install transcribe

1Skills CLI (Vercel)

npx skills add badlogic/pi-skills --skill transcribe -a claude-code

2Manually: put the files in place

~/.claude/skills/transcribe/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/transcribe/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about transcribe

How do I install transcribe in Claude Code?

Run npx skills add badlogic/pi-skills --skill transcribe -a claude-code, then open ~/.claude/skills/transcribe/SKILL.md.

What does the transcribe skill do?

It turns audio into text locally on Apple Silicon macOS. The result is timestamped, split into 15-second blocks.

What do I need before using it?

You need curl, tar, and ffmpeg for non-WAV formats. The binary and model download automatically on first run.

Source text

SKILL.md · MIT
---
name: transcribe
description: Local speech-to-text transcription on Apple Silicon macOS. Supports wav directly and other audio formats via ffmpeg.
---

# Transcribe

Local speech-to-text using `parakeet-cpp-transcribe` on Apple Silicon macOS.

## Usage

```bash
{baseDir}/transcribe.sh <audio-file>
```

The first run downloads the macOS arm64 binary from the latest `badlogic/pibot` GitHub release into the extension's ignored `bin` directory:

```text
{extensionDir}/bin/parakeet-cpp-transcribe
```

(`{extensionDir}` is the parent directory of this skill's `{baseDir}`.) The binary downloads its GGUF model automatically if missing.

## Output

Plain text timestamped in 15 second chunks is written to stdout:

```text
[00:00-00:15] transcript text
[00:15-00:30] more transcript text
```

Model/GGML diagnostic logs are written to stderr. Redirect stderr to hide them:

```bash
{baseDir}/transcribe.sh <audio-file> 2>/dev/null
```

## Requirements

- Apple Silicon macOS only
- `curl` and `tar`
- `ffmpeg` for non-WAV input: `brew install ffmpeg`

© badlogic · MIT · badlogic/pi-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

transcribe by other authors comes first.

transcribe openai Transcribes audio recordings into text and identifies speakers using OpenAI models. Helpful when processing interviews and team meetings. CX Codex +1 272installs transcribe EditAtlas This Claude Code skill transcribes speech in video or audio and timestamps each word. It also creates subtitles and flags possible cuts for editing. CX Codex +1 ★ 52repo stars mcp-transcribe transcribe-app Connects AI assistants to the Transcribe platform to convert audio and video into text. Handles both local files and remote links directly in chat. CX Codex +1 ★ 8repo stars asr-transcribe-to-text daymade asr-transcribe-to-text is a Claude Code skill that turns audio and video into timestamped text with speaker labels. It can also prepare audio for speech recognition without transcribing it. CX Codex +1 2,300installs stepfun-asr daymade stepfun-asr transcribes Chinese and English speech with StepFun stepaudio-3-asr-max in a single call, no chunking. Triggers on 阶跃 ASR or speech recognition prompts. CX Codex +1 645installs youtube-transcribe marks97 youtube-transcribe turns YouTube videos into structured digests using ElevenLabs Scribe v2, extracts key frames, and synthesizes topics. CX Codex +1 1,700installs elevenlabs-stt 101-skills elevenlabs-stt runs ElevenLabs Scribe speech-to-text models and forced text alignment via the belt command-line tool. CX Codex +1 236installs openai-whisper-api openclaw openai-whisper-api — a skill for Claude Code, Codex, Cursor, and other platforms that sends an audio file to OpenAI /v1/audio/transcriptions over curl and writes back the transcript. CX Codex +1 5,500installs

From the same set8

Project sponsors

Companies that keep this analytics open