# Transcribe

Local speech-to-text transcription on Apple Silicon macOS.

- Repository: https://github.com/badlogic/pi-skills (2648 stars)
- Category: Media
- License: MIT
- Last updated: 2026-06-06
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add badlogic/pi-skills --skill transcribe -g -a claude-code -y`
Codex: `npx skills add badlogic/pi-skills --skill transcribe -g -a codex -y`
Cursor: `npx skills add badlogic/pi-skills --skill transcribe -g -a cursor -y`
Gemini CLI: `npx skills add badlogic/pi-skills --skill transcribe -g -a gemini-cli -y`

## Description

Local speech-to-text transcription on Apple Silicon macOS. Supports wav directly and other audio formats via ffmpeg.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# 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`