flatkey-ai/flatkey-cli

What it solves

Flatkey CLI provides a unified interface for generating multimodal AI content—including images, videos, audio (TTS, SFX, music), and text—using a single API key and credit balance. It eliminates the need to manage multiple subscriptions and accounts across different AI providers, specifically targeting media teams and AI agents that require programmatic, cost-effective, and fast iteration without the long queues often found in creator-focused suites.

How it works

The CLI acts as a programmable router to various high-end AI models (such as Seedance, ElevenLabs, and GPT/Claude/Gemini models). Users can trigger generation requests via terminal commands, specify models, and save outputs directly to local files. It includes a dedicated "Agent Protocol" with a --json mode for machine-readable output, making it easy to integrate into AI agent frameworks like Cursor or Claude Code.

Who it’s for

• Media teams building repeatable generation pipelines.
• AI agent developers who need a reliable, programmable way to generate media assets.
• Content creators who prefer a terminal-based workflow for batch testing and prompt iteration.

Highlights

• Unified Modalities: Single CLI for image, video, text, and audio (including speech, sound effects, and music).
• Agent-Friendly: Dedicated JSON output mode, --dry-run for credit-saving testing, and predictable stdout/stderr.
• Comprehensive Video Tools: Supports reference images, first/last frames, and a video copy feature that uses Depth Anything V2 for motion reference.
• Cross-Platform: Distributed as an npm package for macOS, Linux, and Windows.