veo-video — Claude Code skill: generate videos with Google Veo
veo-video — a skill for Claude Code, Codex, Cursor and other platforms that generates videos via Google Veo API. Triggered by a prompt, animates still images, blends references, and upscales to 1080p.
Apache-2.0 241 installs ★ 17 updated 2026-10-25
npx skills add AceDataCloud/Skills --skill veo-video -a claude-codeWhat veo-video does
Supports Veo 3 and Veo 3.1 models with native audio: veo3, veo3-fast, veo31, veo31-fast and veo31-fast-ingredients. Four modes: text-to-video, image-to-video (animating stills), ingredients-to-video (blending two or three references) and upscaling to 1080p.
Async: requests return a task ID, results arrive later via polling the /veo/tasks endpoint. Resolutions range from 720p to 4k and GIF. Aspect ratios 16:9 and 9:16 work only with image-to-video. Requires ACEDATACLOUD_API_TOKEN in .env. Ingredients mode needs at least one image; text-only prompts are ignored.
For automation, use the mcp-veo MCP server (pip install mcp-veo or hosted at https://veo.mcp.acedata.cloud/mcp). The translation: true flag translates the prompt to English before sending it to Veo.
What it helps with
- generate a video from a text description
- animate a still image into video
- blend multiple reference images into one video
- upscale an existing video to 1080p
- add native audio to generated footage
Example prompts for the agent
- Generate a video: whale breaching at sunset, model
veo3, 1080p - Animate
landscape.jpg: gentle wind and cloud movement,veo31-fast, 16:9 - Upscale video ID
abc123to 1080p withveo3
How to install veo-video
1Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill veo-video -a claude-code2Manually: put the files in place
~/.claude/skills/veo-video/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/veo-video/
1Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill veo-video -a codex2Manually: put the files in place
.agents/skills/veo-video/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill veo-video -a cursor2Manually: put the files in place
.cursor/skills/veo-video/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install AceDataCloud/Skills skills/veo-video2Manually: put the files in place
.github/skills/veo-video/SKILL.md1Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill veo-video -a gemini-cli2Platform CLI
gemini skills install https://github.com/AceDataCloud/Skills --path skills/veo-videoManually: put the files in place
.devin/skills/veo-video/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill veo-video -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about veo-video
How do I install veo-video in Claude Code?
Run npx skills add AceDataCloud/Skills --skill veo-video -a claude-code, the skill ends up in ~/.claude/skills/veo-video/SKILL.md.
What does veo-video do?
Generates videos via Google Veo API: from text, from an image with a prompt, from multiple references, or upscales an existing video to 1080p. Supports Veo 3 and 3.1 models with native audio.
Which Veo models are available?
veo3, veo3-fast, veo31, veo31-fast and veo31-fast-ingredients. All generate audio. The ingredients variant works only with images; text-only prompts are ignored.
Source text
SKILL.md · Apache-2.0
---
name: veo-video
description: Generate AI videos with Google Veo via AceDataCloud API. Use when creating videos from text descriptions, animating still images into video, blending reference images into video, or upscaling existing videos to 1080p. Supports Veo 3 and Veo 3.1 models including fast and ingredient variants.
license: Apache-2.0
metadata:
author: acedatacloud
version: "1.0"
compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-veo for tool-use.
---
# Veo Video Generation
Generate AI videos through AceDataCloud's Google Veo API.
> **Setup:** See [authentication](../_shared/authentication.md) for token setup.
## Quick Start
```bash
curl -X POST https://api.acedata.cloud/veo/videos \
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"action": "text2video", "prompt": "a whale breaching in slow motion at golden hour", "model": "veo3", "callback_url": "https://api.acedata.cloud/health"}'
```
> **Async:** See [async task polling](../_shared/async-tasks.md). Poll via `POST /veo/tasks` with `{"id": "..."}`.
This returns a task ID immediately. Poll for the result:
```bash
curl -X POST https://api.acedata.cloud/veo/tasks \
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"id": "<task_id from above>"}'
```
## Models
| Model | Audio | Best For |
|-------|-------|----------|
| `veo3` | Yes (native) | Full audiovisual generation |
| `veo3-fast` | Yes (native) | Faster audiovisual generation |
| `veo31` | Yes (native) | Veo 3.1, highest quality |
| `veo31-fast` | Yes (native) | Veo 3.1 fast variant |
| `veo31-fast-ingredients` | Yes (native) | Veo 3.1 fast, ingredient mode |
## Workflows
### 1. Text-to-Video
```json
POST /veo/videos
{
"action": "text2video",
"prompt": "cinematic aerial shot of the Northern Lights over Iceland",
"model": "veo3",
"resolution": "1080p"
}
```
### 2. Image-to-Video
Animate still images into video.
```json
POST /veo/videos
{
"action": "image2video",
"prompt": "the scene gently comes to life with wind and subtle motion",
"image_urls": ["https://example.com/landscape.jpg"],
"model": "veo31-fast",
"aspect_ratio": "16:9"
}
```
### 3. Ingredients-to-Video (Multi-Image Blend)
Blend 1–3 reference images into a video (only `veo31-fast-ingredients`).
```json
POST /veo/videos
{
"action": "ingredients2video",
"image_urls": [
"https://example.com/img1.jpg",
"https://example.com/img2.jpg"
],
"model": "veo31-fast-ingredients"
}
```
### 4. Upscale to 1080p
Convert a previously generated video to full 1080p resolution.
```json
POST /veo/videos
{
"action": "get1080p",
"video_id": "your-video-id",
"model": "veo3"
}
```
## Parameters
| Parameter | Values | Description |
|-----------|--------|-------------|
| `action` | `"text2video"`, `"image2video"`, `"ingredients2video"`, `"get1080p"` | Generation mode |
| `model` | see Models table | Model to use |
| `resolution` | `"4k"`, `"1080p"`, `"gif"` | Output resolution (default: 720p) |
| `aspect_ratio` | `"16:9"`, `"9:16"` | Aspect ratio — only valid for `image2video` |
| `image_urls` | array of strings | Reference image URLs — for `image2video` (up to 2) or `ingredients2video` (up to 3) |
| `video_id` | string | Video to upscale — only for `get1080p` |
| `translation` | `true` / `false` | Auto-translate prompt to English (default: false) |
## Gotchas
- Veo 3 and 3.1 models generate **native audio**
- The `get1080p` action uses `video_id` (from a prior generation), not a URL
- `aspect_ratio` is **only valid** for the `image2video` action
- `image_urls` accepts an array — up to 2 images for `image2video`, up to 3 for `ingredients2video`
- `veo31-fast-ingredients` **requires** image input — it cannot do text-only generation
- Documented `aspect_ratio` values are only `"16:9"` and `"9:16"`
- `translation: true` auto-translates Chinese or other non-English prompts before sending to Veo
- Task polling uses `id` (not `task_id`) in the `/veo/tasks` request body
- Task states use `"succeeded"` (not "completed") — check for this value when polling
> **MCP:** `pip install mcp-veo` | Hosted: `https://veo.mcp.acedata.cloud/mcp` | See [all MCP servers](../_shared/mcp-servers.md)
© acedatacloud · Apache-2.0 · AceDataCloud/Skills