Model
Veo 3.1
for AI agents
Veo 3.1 is the current video generation model exposed through AnyCap. It is a good fit when an agent needs to turn a text brief into a video draft without branching into a separate integration path. The same CLI can then continue into image generation, video analysis, or other multimodal steps.
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.
When agents should use Veo 3.1
- Generate short product demos from a written concept
- Create motion prototypes during agent-led content workflows
- Turn a text brief into an explainer or teaser draft
- Keep video generation inside the same agent runtime used for image and analysis tasks
Call Veo 3.1 through AnyCap
Generate a video
anycap video generate --model veo3.1 --prompt "a cinematic flyover of a futuristic city at dawn"
List available video models
anycap video models
Workflow placement
In an agent workflow, Veo 3.1 is usually the generation step that follows planning and precedes review. A coding or automation agent may draft the concept, call Veo 3.1 for the video output, then route the result into review, asset packaging, or documentation.
Upstream
Context engineering, prompt preparation, story framing, and asset selection.
Downstream
Review, editing notes, video analysis, and distribution inside the rest of the agent stack.