Introduction
Generate media and text, and make typed judgments from the terminal.
Generate anything from your terminal. Create text, images, video, and audio, and make typed decisions with composable commands. ai-cli uses the Vercel AI SDK and AI Gateway to connect to hundreds of models.
What it does
Image generation
Create images from text or existing images.
Video generation
Generate video from text or images.
Text generation
Generate text from prompts with any language model.
Audio generation
Generate speech or transcribe audio files and streams.
Multi-model comparison
Run the same prompt across multiple models in parallel.
Decisions
Use AI SDK evaluation models with typed questions and JSON results.
Stdin piping
Pipe any content in and out for composable workflows.
Inline preview
See generated images, video frames, and speech playback directly in your terminal.
Quick start
Commands
image
Generate images from a prompt.
video
Generate video from text or start/end frames.
text
Generate text from a prompt.
audio
Generate speech or transcribe audio.
decide
Make decisions with named typed questions against shared stdin.
models
List available models from the gateway.
mcp
Run every command as a typed tool over a stdio MCP server.
ai-cli works the same for people and agents. Progress goes to stderr, results go to files or stdout, and --json returns metadata that scripts can parse.