Verified:GitHub

media

Generate images, videos, and speech, and transcribe audio via CLI commands.

Updated Jun 19, 2026

Search Tags:#image generation #text-to-speech #content creation #audio transcription #video generation #media generation #cli commands

Ready to run

npx skills add https://github.com/MuhammadUA/Axe --skill media-muhammadua

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: media
Source: https://github.com/MuhammadUA/Axe/tree/main/.kortix/opencode/skills/GENERAL-KNOWLEDGE-WORKER/media
Command: npx skills add https://github.com/MuhammadUA/Axe --skill media-muhammadua

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the need to juggle multiple disconnected tools for media creation and transcription by providing a single, consistent set of CLI commands for all common media tasks.

Core Features & Use Cases

Image Generation: Create custom photos, illustrations, and artistic graphics from text prompts, with support for img2img, aspect ratio control, and multiple model options.
Video Generation: Produce short video clips from text descriptions, with options for starting frames, duration control, and multiple video models.
Audio Processing: Convert text to natural speech with customizable voices and transcribe audio/video files with speaker diarization and timestamp support.
Use Case: Content creators can use this Skill to generate a social media graphic, produce a short promotional video clip, create a matching voiceover, and transcribe a customer interview all from the same unified command set.

Quick Start

Use the media skill to generate a 16:9 image of a mountain sunset and save it with the filename sunset.

Frequently Asked Questions about media

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

FAQPage Schema

How do I generate images and video from text using a single CLI tool?▼

You can generate images and video from text using unified CLI commands that support aspect ratio control, starting frames, duration adjustment, and multiple model options for content creation.

Can I convert text to speech and transcribe audio with speaker diarization via command line?▼

Yes, text-to-speech conversion and audio transcription with speaker diarization and timestamp support can both be executed via CLI commands for audio processing workflows.

What is the best way to consolidate fragmented media generation and transcription workflows?▼

Using a unified CLI command set eliminates the need for multiple disconnected tools by providing consistent media creation and transcription operations for visual, video, and audio assets.

Does CLI media generation support aspect ratio control and video duration adjustment?▼

CLI media generation supports configurable operations including aspect ratio control for images, video duration adjustment, starting frame specification, and voice selection for text-to-speech output.

How do I transcribe a customer interview audio file with timestamps using command line?▼

Audio transcription via CLI commands processes existing media files into structured text with speaker diarization and timestamp support, converting audio or video files directly from the command line.

Can I use img2img generation and specify custom filenames when creating images via CLI?▼

Image generation via CLI supports img2img workflows, text prompt inputs, aspect ratio control, multiple model options, and custom filename specification for saving generated visual assets.