transcribe

Original：🇺🇸 English

Translated

1 scriptsChecked / no sensitive code detected

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

2installs

Added on2026-02-17

NPX Install

npx skill4agent add badlogic/pi-skills transcribe

Speech-to-text using Groq Whisper API.

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:

Ask if they have a Groq API key
If not, have them sign up at https://console.groq.com/ and create an API key
Have them add to their shell profile (~/.zshrc or ~/.bashrc):
bash
```
export GROQ_API_KEY="<their-api-key>"
```
Then run
```
source ~/.zshrc
```
(or restart terminal)

bash

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

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