google-veo
Direct production with Google DeepMind's Veo video-generation family across the Gemini Developer API and Google Cloud Gemini Enterprise Agent Platform (formerly Vertex AI). Use for Veo route and model selection, text/image/reference/first-last-frame/extension workflows, native-audio prompting, camera direction, async API operation, troubleshooting, QA, and responsible commercial content production.
Profile →npx skills add calesthio/generative-media-skills --skill google-veo --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Treat a Veo request as a shot-production job, not as a generic text completion. Lock the access route, model, input mode, shot contract, and delivery constraints before generating.
How it works
- Distinguishes Veo workflows for two routes: Gemini Developer API and Gemini Enterprise Agent Platform / Vertex publisher-model route.
- For the Developer API, uses current model IDs veo-3.1-generate-preview, veo-3.1-fast-generate-preview, and vea-3.1-lite-generate-preview; submits REST to POST https://generativelanguage.googleapis.com/v1beta/models/{MODEL}:predictLongRunning with x-goog-api-key, polls via GET https://generativelanguage.googleapis.com/v1beta/{operationName}, and downloads result from the provided URI within the retention window. Handles 720p/1080p/4K where applicable; clip lengths are 4, 6, or 8 seconds depending on inputs and extensions. Generated files remain on Google’s server for two days. Extension adds seven seconds and can be repeated up to 20 times within limits.
- For the Enterprise route, uses stable IDs veo-3.1-generate-001 and veo-3.1-fast-generate-001 (Lite-001 is Preview); avoids copying preview IDs into Cloud route. Submits REST to POST https://us-central1-aiplatform.googleapis.com/v1/projects/{PROJECT}/locations/us-central1/publishers/google/models/{MODEL}:predictLongRunning, polls via POST ...:fetchPredictOperation with body {"operationName":"..."}, outputs can be inline or as storageUri.
- Chooses among Standard, Fast, or Lite depending on needs: Standard supports text-to-video, image-to-video, first/last-frame, extension, and asset references; Lite has limitations on reference images in Developer API, and differences across Enterprise vs Developer API.
- Provides guidance on selecting Veo variants (Standard, Fast, Lite) based on final shot quality, storyboard speed, and cost considerations, and notes pricing inputs as a dated snapshot.
When to use it
- Use when a Veo production objective benefits from Veo-specific controls (first/last-frame, extension, asset references, or native audio) and when choosing between Developer API and Enterprise routes.
- Use different generation modes (Text to video, First-frame image to video, First and last frames, Asset reference images, Extension) according to the production need described in the prompts.
What it can touch
- Tools specified for this skill include claude-code, codex, copilot, cursor.
Caveats
- Documented facts are current as of 2026-07-09 and should be rechecked for lifecycle, quotas, pricing, regional availability, and terms before paid production.
- There are documented gaps: audio behavior differs between Developer API and Enterprise routes; Lite/standard capability discrepancies; and potential conflicts between model cards and generic fields requiring preflight checks.
- Some model IDs are deprecated in certain routes; ensure correct route and ID usage for production.
# Produce with Google Veo Treat a Veo request as a shot-production job, not as a generic text completion. Lock the access route, model, input mode, shot contract, and delivery constraints before generating. ## Read evidence labels correctly - **Documented** means a current first-party Google API document, model card, policy, or technical report says it. - **First-party evaluation** means Google me
What does the google-veo skill do?
Direct production with Google DeepMind's Veo video-generation family across the Gemini Developer API and Google Cloud Gemini Enterprise Agent Platform (formerly Vertex AI). Use for Veo route and model selection, text/image/reference/first-last-frame/extension workflows, native-audio prompting, camera direction, async API operation, troubleshooting, QA, and responsible commercial content production.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill google-veo --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.