---
title: "通过 RunAPI 在龙虾 (OpenClaw) 中使用 Veo 3 — 视频 API 指南"
url: "https://runapi.ai/zh-CN/openclaw-veo-3.md"
canonical: "https://runapi.ai/zh-CN/openclaw-veo-3"
locale: "zh-CN"
model: "veo-3"
---

# 在 OpenClaw 中使用 Veo 3。

Veo 3 是 Google DeepMind 的视频生成模型，可生成最长 8 秒、1080p 的片段，并带有原生音频——与视频同步生成的对白、环境声和音乐。OpenClaw agent 通过与聊天相同的 RunAPI 密钥和端点调用它，无需安装额外技能。

## API example

```bash
curl -X POST https://runapi.ai/api/v1/veo_3_1/text_to_video \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo-3.1",
    "prompt": "A woman walks through a bustling Tokyo street at night, neon signs reflecting on wet pavement. She speaks into her phone: I just arrived. Ambient city noise, distant car horns, light rain.",
    "duration_seconds": 8,
    "aspect_ratio": "16:9"
  }'

```

### Response

```json
{
  "task_id": "tsk_abc123",
  "status": "pending",
  "model": "veo-3.1"
}

```

## How it works

1. **Configure RunAPI** — Set the RUNAPI_API_KEY environment variable. If you already configured RunAPI as an OpenClaw provider for chat, the same key works for video generation — no additional setup or provider accounts.
2. **Call Veo 3 text_to_video** — Send a POST to the text_to_video endpoint with model set to veo-3.1. Include a prompt with scene descriptions and audio cues (dialogue, ambient sounds). Set duration_seconds to 4, 6, or 8 and aspect_ratio to 16:9 or 9:16.
3. **Poll for the result** — The endpoint returns a task_id immediately. Poll the task status endpoint until the status changes to completed, then retrieve the output video URL. The video includes synchronized audio generated from your prompt.

## Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `model` | `string` | Required. veo-3.1 (standard quality) or veo-3.1-fast (lower cost, faster generation). |
| `prompt` | `string` | Required. Scene description including visual action, camera movement, and audio cues for dialogue or ambient sound. |
| `duration_seconds` | `integer` | Optional. Video length in seconds. Accepted values: 4, 6, 8. Defaults to 8. |
| `aspect_ratio` | `string` | Optional. Output aspect ratio. Accepted values: 16:9, 9:16, auto. |
| `input_mode` | `string` | Optional. Generation mode. text (default), first_and_last_frames (keyframe-guided), or reference (style reference). |
| `first_frame_image_url` | `string` | Optional. URL of the first frame image. Used when input_mode is first_and_last_frames. |
| `last_frame_image_url` | `string` | Optional. URL of the last frame image. Used when input_mode is first_and_last_frames. |
| `reference_image_urls` | `array` | Optional. URLs of style reference images. Used when input_mode is reference. |
| `callback_url` | `string` | Optional. Webhook URL that receives a POST when the task completes. |

## FAQ

### Can I use Veo 3 in OpenClaw?

Yes. OpenClaw agents call the RunAPI Veo 3 text_to_video endpoint directly. Set model to veo-3.1 and send the request with the same RUNAPI_API_KEY you use for chat. No additional skills, plugins, or Google Cloud accounts required.

### Does Veo 3 cost money or is it free?

Veo 3 is a paid model on RunAPI. Each generation is billed per task based on duration and quality tier. veo-3.1-fast costs less than veo-3.1. Check the RunAPI pricing page for current rates. No subscription required -- you pay per generation.

### Why is Veo 3 slow compared to other generators?

Veo 3 generates both video and synchronized audio in a single pass, which takes more processing time. Generation typically takes 60 to 180 seconds. Use veo-3.1-fast for quicker turnaround when iterating on drafts.

### Can I extend or upscale a Veo 3 video after generation?

Yes. RunAPI exposes extend_video and upscale_video endpoints for Veo 3. Pass the source_task_id from the original generation to extend the clip, or upscale to 1080p or 4K resolution. Both are async and billed separately.

### What is the maximum video duration and resolution?

Veo 3 generates clips of 4, 6, or 8 seconds at up to 1080p base resolution. You can upscale completed videos to 4K using the upscale_video endpoint. Aspect ratio options are 16:9, 9:16, and auto.


## Links

- [OpenClaw 配置指南 →](https://runapi.ai/zh-CN/openclaw)
- [RunAPI 上的 Veo 3 →](https://runapi.ai/zh-CN/models/veo-3)
- [Model catalog](https://runapi.ai/zh-CN/models)
- [API docs](https://runapi.ai/zh-CN/docs)