🎯

transcribe

🎯Skill

from badlogic/pi-skills

VibeIndex|
What it does

Converts audio files to text using Groq Whisper API, supporting multiple formats like m4a, mp3, and wav.

πŸ“¦

Part of

badlogic/pi-skills(8 items)

transcribe

Installation

git cloneClone repository
git clone https://github.com/badlogic/pi-skills ~/.pi/agent/skills/pi-skills
git cloneClone repository
git clone https://github.com/badlogic/pi-skills .pi/skills/pi-skills
git cloneClone repository
git clone https://github.com/badlogic/pi-skills ~/.codex/skills/pi-skills
git cloneClone repository
git clone https://github.com/badlogic/pi-skills ~/.config/amp/tools/pi-skills
git cloneClone repository
git clone https://github.com/badlogic/pi-skills ~/.factory/skills/pi-skills

+ 6 more commands

πŸ“– Extracted from docs: badlogic/pi-skills
7Installs
-
AddedFeb 4, 2026

Skill Details

SKILL.md

Speech-to-text transcription using Groq Whisper API. Supports m4a, mp3, wav, ogg, flac, webm.

Overview

# Transcribe

Speech-to-text using Groq Whisper API.

Setup

The script needs GROQ_API_KEY environment variable. Check if already set:

```bash

echo $GROQ_API_KEY

```

If not set, guide the user through setup:

  1. Ask if they have a Groq API key
  2. If not, have them sign up at https://console.groq.com/ and create an API key
  3. Have them add to their shell profile (~/.zshrc or ~/.bashrc):

```bash

export GROQ_API_KEY=""

```

  1. Then run source ~/.zshrc (or restart terminal)

Usage

```bash

{baseDir}/transcribe.sh

```

Supported Formats

  • m4a, mp3, wav, ogg, flac, webm
  • Max file size: 25MB

Output

Returns plain text transcription with punctuation and proper capitalization to stdout.