media-gen-cli v1.5.0

Full Changelog: v1.4.0...v1.5.0

media-gen-cli v1.4.0

Full Changelog: v1.3.0...v1.4.0

media-gen-cli v1.3.0

Full Changelog: v1.2.0...v1.3.0

media-gen-cli v1.2.0

Full Changelog: v1.1.0...v1.2.0

media-gen-cli v1.1.0

Full Changelog: v1.0.0...v1.1.0

media-gen-cli v1.0.0

Multi-provider media generation CLI for images, video, voice, and audio.

Features

• 12 providers: OpenAI, Google, Azure, ElevenLabs, Deepgram, Fal, Luma, Replicate, Stability, Runway, OpenRouter, Edge TTS (free)
• Commands: image generate/edit, video generate, voice tts/clone/isolate, audio transcribe/translate
• AI agent skill file (SKILL.md) following Agent Skills open standard
• Default provider/model/voice-id via env vars
• Multi-level config: ~/.media-gen/.env -> project .env
• Async video job polling with --wait
• Single bundled JS file (minified, 513KB)
• Structured JSON output for agent integration
• 25 tests passing

Usage

node ./skills/media-generation/scripts/media-gen.mjs --help

Install

Download the zip below, extract the skills/ folder into your project, then run:

node ./skills/media-generation/scripts/media-gen.mjs image generate --prompt 'A red panda' --output ./out.png --json