whisper

Name: whisper
Availability: InStock
Author: aimentor606

Transcribe audio and video files into text with timestamps and language hints.

Updated Apr 8, 2026

Search Tags:#video #transcription #whisper #audio #openai #groq #speech-to-text

Ready to run

npx skills add https://github.com/aimentor606/aether --skill whisper-aimentor606

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/aimentor606/aether/tree/main/core/kortix-master/opencode/skills/GENERAL-KNOWLEDGE-WORKER/whisper
Command: npx skills add https://github.com/aimentor606/aether --skill whisper-aimentor606

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Transcribing spoken content from audio and video files is time-consuming and interrupts workflows; this Skill converts media into searchable, editable text so agents or humans can quickly understand and act on spoken content.

Core Features & Use Cases

Provider prioritization and fallback: Uses Groq Whisper for fast, near-instant transcription with OpenAI as a reliable fallback.
Flexible input and output: CLI-friendly tool that accepts common media formats, supports language hints, and can emit timestamps and JSON output for downstream processing.
Use Cases: Transcribe voice messages from chat apps, generate meeting notes from recordings, or caption videos for accessibility and indexing.

Quick Start

Transcribe the file /workspace/meeting.mp4 to text with timestamps using the whisper skill.

Frequently Asked Questions about whisper

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

FAQPage Schema

How do I transcribe an mp4 video file to text with timestamps?▼

To transcribe audio files like mp3 or wav, this speech-to-text tool processes the media and converts spoken content into searchable text. It requires a GROQ_API_KEY or OPENAI_API_KEY for provider access to handle the transcription.

Do I need a Groq API key to convert voice messages to text?▼

Yes, you need a GROQ_API_KEY or OPENAI_API_KEY to convert voice messages to text. The tool prioritizes Groq Whisper for near-instant transcription speed, but automatically implements OpenAI as a reliable fallback provider if Groq access fails.

What audio and video formats are supported for speech-to-text conversion?▼

Supported audio and video formats for speech-to-text conversion include mp3, mp4, ogg, and wav. This allows you to directly transcribe various media files, such as meeting recordings and video notes, without needing prior format conversion.

Can I get JSON output from transcribed meeting recordings for downstream processing?▼

Yes, you can get JSON output from transcribed meeting recordings. The tool emits JSON output alongside timestamps and language hints, enabling agents or humans to quickly parse and act on the spoken content in downstream automated workflows.

Is there a fast way to generate captions for video accessibility?▼

Generating captions for video accessibility is fast using Groq Whisper, which provides near-instant transcription. This speech-to-text process converts video notes into accurate text transcripts that can be used for captioning and indexing content.