flatkey-cli-media-generation

Generate images, videos, audio, and text via the Flatkey CLI with JSON output.

4|Updated May 16, 2026
One-click install
npx skills add https://github.com/reason-machines/devtools-skills --skill flatkey-cli-media-generation-reason-machines
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: flatkey-cli-media-generation
Source: https://github.com/reason-machines/devtools-skills/tree/main/skills/flatkey-cli-media-generation
Command: npx skills add https://github.com/reason-machines/devtools-skills --skill flatkey-cli-media-generation-reason-machines

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @flatkey-ai/cli.

What problem does it solve? It removes the friction of juggling separate APIs and SDKs for each media type by providing one terminal-first CLI with a unified API key, credit balance, and machine-readable JSON output for image, video, audio, and text generation. ## Core Features & Use Cases - Multi-modal generation: Create images, videos (with reference images or first/last frames), text-to-speech, sound effects, music, and text from a single CLI. - Agent-friendly workflows: --json mode, --dry-run validation, model and voice discovery commands, and environment-variable authentication for programmatic use. - Use Case: An automation agent checks credit balance with flatkey credits --json, discovers available video models, then batch-generates product videos from uploaded reference images, saving each result locally with cost metadata. ## Quick Start Ask the agent to generate an image with the Flatkey CLI using a prompt like "minimalist product shot on white background" and save it to a local file with JSON output.

Frequently Asked Questions about flatkey-cli-media-generation

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

FAQPage Schema
How do I generate an image with the Flatkey CLI?▼

Run flatkey image generate with a --prompt, a --model such as gpt-image-2, and -o to save the file locally. Add --json for machine-readable output containing the media URL, local path, cost, and model used.

How to create a video from a reference image using Flatkey?▼

First upload the local image with flatkey image upload --file ./ref.png --json to get a temporary signed URL, then pass that URL via --image to flatkey video generate along with a prompt, model, ratio, and resolution.

Does Flatkey CLI support text-to-speech in multiple languages?▼

Yes, audio generation supports multilingual TTS through the eleven_multilingual_v2 model. List available voices with flatkey audio voices --json, then pass a voice_id and prompt to flatkey audio generate.

Can I validate a Flatkey request without spending credits?▼

Yes, add the --dry-run flag to any generation command to return the request payload without executing it. You can also check your balance beforehand with flatkey credits --json.

Why does Flatkey video generation fail with a local image path?▼

The video command requires a hosted URL, not a local file path. Upload the image first with flatkey image upload to obtain a temporary signed URL, then use that URL as the --image value.