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
npx skills add badlogic/pi-skills --skill transcribe -a claude-codeWhat 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.wavwith the transcribe skill - Run transcribe on
interview.mp3and 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-code2Manually: put the files in place
~/.claude/skills/transcribe/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/transcribe/
1Skills CLI (Vercel)
npx skills add badlogic/pi-skills --skill transcribe -a codex2Manually: put the files in place
.agents/skills/transcribe/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add badlogic/pi-skills --skill transcribe -a cursor2Manually: put the files in place
.cursor/skills/transcribe/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install badlogic/pi-skills transcribe2Manually: put the files in place
.github/skills/transcribe/SKILL.md1Skills CLI (Vercel)
npx skills add badlogic/pi-skills --skill transcribe -a gemini-cli2Platform CLI
gemini skills install https://github.com/badlogic/pi-skills --path transcribeManually: put the files in place
.devin/skills/transcribe/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add badlogic/pi-skills --skill transcribe -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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.