media

Generate images, videos, and speech from JSON prompts via Bash tools.

Updated Apr 16, 2026
One-click install
npx skills add https://github.com/yethikrishna/humble --skill media-yethikrishna
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: media
Source: https://github.com/yethikrishna/humble/tree/main/core/kortix-master/opencode/skills/GENERAL-KNOWLEDGE-WORKER/media
Command: npx skills add https://github.com/yethikrishna/humble --skill media-yethikrishna

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates media generation and processing from JSON prompts via Bash tools, consolidating image, video, and audio tasks into a single workflow.

Core Features & Use Cases

  • asi-generate-image: Generate images from text prompts with optional img2img references, outputting to a file.
  • asi-generate-video: Create short video clips from prompts, with optional starting frame support.
  • asi-text-to-speech: Convert text prompts to speech audio with configurable voices.
  • asi-transcribe-audio: Transcribe audio/video files to text with optional diarization and timestamps for multi-speaker content.

Quick Start

Run a single media command with a JSON payload to generate images, video, or speech.

Frequently Asked Questions about media

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

FAQPage Schema
How do I automate media generation tasks using Bash and JSON prompts?

You can automate media generation by running Bash commands with per-command JSON payloads. This approach consolidates image, video, and audio tasks into a single content pipeline without leaving the command line.

Can I generate short video clips from a text prompt in the command line?

Yes, you can generate short video clips from text prompts in the command line. The process accepts a JSON payload and supports an optional starting frame image to define the initial visual state of the output.

Does Bash transcription support multi-speaker diarization and timestamps?

Yes, command-line audio and video transcription supports multi-speaker diarization and timestamps. This allows you to accurately separate and identify different speakers when transcribing content directly from Bash.

What do I need to configure for text-to-speech automation in Bash?

Text-to-speech automation requires per-command JSON payloads containing your text and configurable voice options. You must also configure dedicated api_credentials suffixes to authenticate with the underlying audio services.

What are the limitations of running image generation from Bash JSON payloads?

Running image generation from Bash JSON payloads requires external api_credentials to access image services. It is limited to processing text prompts and optional img2img references, outputting the result to a specified file.