---
title: "ai-media"
description: "Use this plugin for image, video, speech, and transcription workflows for generated media."
canonical: https://agentpluginsdirectory.com/plugins/ai-media
last-updated: 2026-09-12
---

# ai-media
Use this plugin for image, video, speech, and transcription workflows for generated media.
- Slug: ai-media
- Publisher: OpenAI
- Repository: https://github.com/mjcramerz/codex-home
- Manifest: home/marketplaces/codex-home/plugins/cache/codex-home/ai-media/local/plugin.json
- Version: 1.1.0
- Category (editorial): other
- Skills: 4 (imagegen, sora, speech, transcribe)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-08-11
- Repository last pushed: 2026-09-12
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/ai-media
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- imagegen: Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OP…
- sora: Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI's video API using the bundled CLI (`scripts/sora.py`), including requests like "generate AI video," "Sora," "video remix," "download video/thumbnail/spritesheet," and batch video generation; requires `…
- speech: Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out…
- transcribe: Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.