Veo 3.1 for AI agents
Google's video model for text- and image-to-video with natively synced audio. Called through Vaaya, billed per call — no Google account.
from ~5¢/s
Model by Google. Called through Vaaya — no Google account or API key.
What it's for
Text- and image-to-video with natively synced audio.
Built by Google. Runs on your Vaaya balance — no Google account or API key.
Request it by name, or describe the video and Vaaya routes to a fitting model.
Returns a video URL, saved to your Media library.
How to ask your agent
Connect Vaaya, then just say it in plain language. For example:
❯Use Vaaya to generate a 4-second establishing shot of a city skyline at dawn with ambient sound.
❯Use Vaaya to run this on Veo 3.1.
What you get back
{
"video": { "url": "https://…/output.mp4", "duration_sec": 5 },
"model": "veo3-1--lite"
}
Pricing
~5–8¢/s of video (720p/1080p, with audio). Billed per call in cents, capped by your max, every call on the ledger. Failed calls are not billed.
Give your agents this.
Connect Vaaya once, then describe the outcome. It picks the right tool, runs it, and pays per call.
npx @vaaya/mcp install