transcribe

Transcribe audio files to text using the Groq Whisper API.

3|1|Updated Feb 9, 2015
One-click install
npx skills add https://github.com/drafael/dotfiles --skill transcribe-drafael
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: transcribe
Source: https://github.com/drafael/dotfiles/tree/main/.agents/skills/transcribe
Command: npx skills add https://github.com/drafael/dotfiles --skill transcribe-drafael

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill provides a fast and accurate way to convert spoken audio into written text, making audio content searchable and editable.

Core Features & Use Cases

  • Speech-to-Text: Utilizes the Groq Whisper API for high-quality transcription.
  • Wide Format Support: Handles common audio file types like m4a, mp3, wav, ogg, flac, and webm.
  • Use Case: Transcribe meeting recordings, voice notes, or podcast segments into plain text for easy summarization, searching, or documentation.

Quick Start

Use the transcribe skill to convert the audio file 'meeting_recording.mp3' into text.

Frequently Asked Questions about transcribe

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert audio to text from an mp3 or m4a file?

You can transcribe audio files by providing formats like m4a, mp3, or wav to the Skill, which uses the Groq Whisper API to output plain text with punctuation and capitalization.

What audio formats does the Groq Whisper API support for speech to text?

For speech to text conversion, the Skill supports m4a, mp3, wav, ogg, flac, and webm audio file formats, transcribing them into plain text with punctuation.

What is the maximum file size for transcribing audio with Groq?

When performing speech-to-text transcription, the maximum supported audio file size is 25MB. Files larger than this cannot be processed by the Groq Whisper API.

Can I transcribe meeting recordings and voice notes into plain text?

Yes, you can transcribe meeting recordings and voice notes into plain text. The Skill converts spoken audio into written text, making content searchable, editable, and ready for documentation.

Does the transcription output include punctuation and capitalization?

Yes, the speech-to-text output includes punctuation and capitalization. The Groq Whisper API processes the audio and generates formatted plain text delivered to standard output.