← LeaderboardThe Skill Leaderboard

transcribe

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

Published by badlogic ↗badlogic/pi-skills

Try your first task

transcribe

Start a fresh conversation. Replace the highlighted placeholders.

Use transcribe to transcribe the audio file [audio file] into timestamped plain text in 15-second chunks.

Required inputs

  • [audio file]

User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗

SKILL.md

name: transcribedescription: 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

{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:

{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:

[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:

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

Requirements

  • Apple Silicon macOS only
  • curl and tar
  • ffmpeg for non-WAV input: brew install ffmpeg
transcribe by badlogic · The Skill Leaderboard