whisper

Transcribe speech from audio and video files to text using Whisper APIs.

Updated Jun 19, 2026
One-click install
npx skills add https://github.com/MuhammadUA/Axe --skill whisper-muhammadua
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/MuhammadUA/Axe/tree/main/.kortix/opencode/skills/GENERAL-KNOWLEDGE-WORKER/whisper
Command: npx skills add https://github.com/MuhammadUA/Axe --skill whisper-muhammadua

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Manually listening to audio or video files to extract spoken content is time-consuming and inefficient, especially for voice messages, meeting recordings, or any media with speech that needs to be converted to readable text.

Core Features & Use Cases

  • Multi-format Support: Transcribes all common audio and video formats including mp3, mp4, wav, ogg, flac, and more.
  • Fast, Reliable Processing: Uses Groq Whisper for near-instant transcription, with OpenAI Whisper as a fallback for reliability.
  • Customizable Output: Supports optional language specification, timestamp inclusion, and prompt hints to improve transcription accuracy for specific use cases like meeting notes or voice message replies.

Quick Start

Use the whisper skill to transcribe the audio file 'weekly-team-meeting.mp3' from your workspace to get a full text transcript.

Frequently Asked Questions about whisper

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

FAQPage Schema
How do I transcribe an audio file to text from my workspace?

To transcribe audio file to text, you use the transcription skill by specifying the target media file name to generate an accurate text output of the spoken content.

Can I transcribe video files like mp4 to text, or does it only support audio?

Yes, you can transcribe video files to text. The transcription process supports common media formats including mp4, mp3, wav, ogg, and flac for extracting speech content.

Do I need an API key to convert voice messages to text?

Yes, converting voice messages to text requires API key authentication. The process uses Groq Whisper APIs for near-instant transcription with OpenAI Whisper as a fallback.

Can I include timestamps when transcribing meeting recordings?

Yes, you can include timestamps when transcribing meeting recordings. The transcription process offers optional timestamp inclusion and language specification for accurate text output.

What is the best way to transcribe speech for meeting notes and voice message replies?

The best way to transcribe speech for meeting notes is using a dedicated transcription skill that supports prompt hints to improve accuracy for specific use cases like voice message replies.

Are there limitations when using Groq for speech-to-text conversion?

Groq provides near-instant speech-to-text conversion but relies on API key authentication. The system uses OpenAI Whisper as a fallback to ensure reliable transcription if Groq encounters issues.