media

Generate images, videos, speech, and transcriptions via harness CLI commands.

28|2|Updated Feb 5, 2026
One-click install
npx skills add https://github.com/labs21-dev/agents-stack --skill media-labs21-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: media
Source: https://github.com/labs21-dev/agents-stack/tree/main/skills-optional/media
Command: npx skills add https://github.com/labs21-dev/agents-stack --skill media-labs21-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Media tasks like generating images, videos, and transcribing audio can be fragmented across tools. This skill unifies media workflows by exposing harness CLI commands for image and video generation, speech synthesis, and transcription.

Core Features & Use Cases

  • asi-generate-image: Generate images from prompts for visuals, thumbnails, or concept art.
  • asi-generate-video: Create short video clips from prompts for social media or product demos.
  • asi-text-to-speech: Convert text to speech using Gemini and ElevenLabs voices for narrations and voiceovers.
  • asi-transcribe-audio: Transcribe audio/video with optional diarization and timestamps for captions and meeting notes.
  • Use Case: Produce a promotional short with a generated image, narrated voiceover, and synchronized captions.

Quick Start

Generate an image from a detailed prompt using asi-generate-image, then optionally create a short video and attach a speech narration with asi-text-to-speech.

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 videos from text prompts using a CLI?

You can generate images and videos from text prompts by running harness CLI commands like asi-generate-image and asi-generate-video, streamlining visual creation for product demos and social media.

Can I convert text to speech using Gemini and ElevenLabs voices for voiceovers?

Yes, the asi-text-to-speech command converts text to speech using Gemini and ElevenLabs voices, producing high-quality audio narrations and voiceovers for marketing or training materials.

How do I transcribe audio with diarization and timestamps for meeting notes?

Audio transcription with diarization and timestamps is handled by the asi-transcribe-audio command, which processes audio and video files to generate captions and structured meeting notes.

What's the best way to combine image generation, speech synthesis, and transcription into one workflow?

The best way to combine these media tasks is using the unified harness CLI media suite, which sequentially chains image generation, text-to-speech, and audio transcription commands to produce promotional shorts with synchronized captions.

Does the media generation suite require any external dependencies or components?

No external dependencies or components are required to run the media generation suite, as the skill operates independently using the built-in harness CLI commands for all transcription and generation tasks.