Capability
Video Generation
AnyCap video generation lets AI agents create videos from text prompts using Veo 3.1 through one CLI interface. Agents can generate video content as part of automated workflows without managing separate API integrations. The capability works across agent products like Claude Code, Cursor, and Codex — one command to generate, consistent output format, same auth flow as every other AnyCap capability.
Early Access
AnyCap is currently in early access. Capabilities shown on this page are available to early access users. Request access on GitHub to get started.
Supported Models
| Model | Status |
|---|---|
| Veo 3.1 | Early Access |
Usage
Text to Video
anycap video generate --model veo3.1 --prompt "a drone shot flying over a mountain range at sunset"
List available models
anycap video models
When Agents Need Video Generation
Demo videos
Generate product demos and walkthroughs as part of automated content pipelines.
Visual storytelling
Create narrative video content from text descriptions within agent workflows.
Social content
Produce short-form video clips for social media as part of content automation.
Prototyping
Rapidly iterate on video concepts without leaving the agent environment.