---
title: Use Kling in WorkBuddy via RunAPI — MCP Video Guide | RunAPI
description: Generate video with Kling 3.0 in WorkBuddy over MCP. Add RunAPI as an MCP server and the workbench agent handles text-to-video, sound, and 1080p output.
url: https://runapi.ai/workbuddy-kling.md
canonical: https://runapi.ai/workbuddy-kling
locale: en
site: RunAPI
image: https://runapi.ai/assets/opengraph-bfaaa0f0.png
alternates:
  en: https://runapi.ai/workbuddy-kling
  zh-CN: https://runapi.ai/zh-CN/workbuddy-kling
  es: https://runapi.ai/es/workbuddy-kling
  ja: https://runapi.ai/ja/workbuddy-kling
  de: https://runapi.ai/de/workbuddy-kling
  fr: https://runapi.ai/fr/workbuddy-kling
  pt-BR: https://runapi.ai/pt-BR/workbuddy-kling
  ko: https://runapi.ai/ko/workbuddy-kling
  it: https://runapi.ai/it/workbuddy-kling
  nl: https://runapi.ai/nl/workbuddy-kling
  pl: https://runapi.ai/pl/workbuddy-kling
  tr: https://runapi.ai/tr/workbuddy-kling
  zh-TW: https://runapi.ai/zh-TW/workbuddy-kling
  zh-HK: https://runapi.ai/zh-HK/workbuddy-kling
  ar: https://runapi.ai/ar/workbuddy-kling
  x-default: https://runapi.ai/workbuddy-kling
model: kling
---

> HTML version: https://runapi.ai/workbuddy-kling
> Site index for agents: https://runapi.ai/llms.txt


# Use Kling in WorkBuddy.

Kling 3.0 by Kuaishou generates video from text or images at up to 1080p with native audio, multi-shot scenes, and 3–15 second durations. WorkBuddy speaks MCP natively — add RunAPI as an MCP server once and the workbench agent can send a Kling prompt, wait on the async task, and hand back the finished video URL.

- [Get API Key](https://runapi.ai/login)
- [Read the docs](https://runapi.ai/docs/guides)

one MCP server · text to video + image to video · per-second billing

### Prompt

```text
Use the runapi MCP server to generate a video with Kling 3.0.

Requirements:
- Use model "kling-3.0".
- Prompt: a drone shot pulling back from a mountain lake at sunrise, mist
  rising off the water, cinematic lighting.
- Set duration_seconds to 5, aspect_ratio to "16:9", and
  output_resolution to "1080p".
- Enable native audio with enable_sound: true.
- The task is async. Wait for it to complete, then report the video URL
  and the cost.

```

### MCP config

```bash
{
  "mcpServers": {
    "runapi": {
      "url": "https://runapi.ai/mcp",
      "transport": "streamable_http",
      "headers": {
        "Authorization": "Bearer $RUNAPI_API_KEY"
      }
    }
  }
}

```

### Result

```json
{
  "task_id": "tsk_abc123",
  "status": "completed",
  "model": "kling-3.0",
  "output": {
    "video_url": "https://media.runapi.ai/tasks/tsk_abc123/output.mp4",
    "duration_seconds": 5,
    "resolution": "1080p"
  }
}

```

## Use Kling in WorkBuddy in three steps

1. **Add RunAPI as an MCP server** - Register an MCP server named runapi in WorkBuddy pointing at https://runapi.ai/mcp over streamable HTTP, with the Authorization header reading your key from RUNAPI_API_KEY. One server covers Kling alongside every other RunAPI model. `url: https://runapi.ai/mcp
transport: streamable_http
auth: Bearer $RUNAPI_API_KEY
`
2. **Prompt the workbench agent** - Ask WorkBuddy to generate a video with Kling 3.0. Include the scene description, duration_seconds (3–15), aspect_ratio, and optionally enable_sound for native audio. For image-driven generation, attach a first frame image URL and the agent uses the image_to_video tool instead. `Use the runapi MCP server to generate a 5-second Kling 3.0 clip: ...`
3. **Let the agent run the tool and collect the result** - WorkBuddy calls the Kling tool through the runapi MCP server and receives a task_id immediately. The agent polls the async task until it completes — typically 30–120 seconds depending on duration and resolution — then reports the video URL back in the workbench. `runapi.text_to_video -> task_id: tsk_abc123 -> status: completed`

## Kling text_to_video parameters

| Parameter | Type | Description |
| --- | --- | --- |
| `model` | `string` | Required. kling-3.0 for the latest version. |
| `prompt` | `string` | Video description. Required for single-shot and automatic multi-shot mode. The custom multi-shot mode uses a prompt for each shot in multi_prompt. |
| `duration_seconds` | `integer` | Video length. Kling 3.0 supports 3–15 seconds. Older versions accept 5 or 10. |
| `aspect_ratio` | `string` | Output aspect ratio: 16:9, 9:16, or 1:1. |
| `output_resolution` | `string` | Resolution: 720p, 1080p, or 4k. Higher resolution costs more per second. |
| `enable_sound` | `boolean` | Generate native audio alongside video. Increases per-second cost. |

## What is Kling on WorkBuddy?

Kling 3.0 by Kuaishou is known for cinematic-quality video with strong cloth simulation, fluid dynamics, and motion physics. It generates clips from text or images at up to 1080p with native audio and multi-shot scenes. WorkBuddy reaches it through the runapi MCP server — the workbench agent calls Kling as a standard tool with the single key in RUNAPI_API_KEY, and RunAPI handles the async task lifecycle underneath.

## Kling use cases

- **B-roll and establishing shots** - Ask WorkBuddy for scene-length B-roll footage on tight deadlines — nature shots, travel content, and environment footage where Kling's motion physics and cinematic lighting stand out.
- **Product lifestyle content** - Create product videos for food, fashion, or lifestyle brands from a single image or text prompt, with natural camera movement and realistic material rendering.
- **Social media shorts** - Produce short clips for TikTok, Reels, or YouTube Shorts with cinematic framing. Set duration_seconds to 5 or 10 for platform-ready lengths.

## Kling + WorkBuddy questions

### Can I use Kling in WorkBuddy?

Yes. WorkBuddy speaks MCP natively. Add RunAPI as an MCP server with your RUNAPI_API_KEY and the workbench agent can call the Kling text_to_video and image_to_video tools directly — no plugins or separate video service accounts.

### How does Kling per-second billing work on RunAPI?

Kling charges per second of generated video. The rate depends on output_resolution and whether enable_sound is on. A 5-second 720p clip without sound is the cheapest option; 1080p with sound costs roughly twice as much per second. Check the RunAPI pricing page for exact rates.

### What happens when a Kling generation fails — do I lose credits?

No. RunAPI only bills for completed generations. If the task fails or times out, the reserved credits are rolled back to your account balance, and WorkBuddy simply reports the failed status.

### Can Kling generate videos with sound?

Yes. Ask WorkBuddy to enable sound, which sets enable_sound to true in the tool call. Kling 3.0 generates synchronized audio matching the video content. Sound generation increases the per-second cost — at 720p, sound adds about 3 cents per second.

### Can I control camera motion in Kling videos?

Kling 3.0 has a separate motion_control tool for applying motion presets to a source image with a reference video, exposed through the same runapi MCP server. The text_to_video tool relies on prompt descriptions for camera direction.


- [WorkBuddy setup guide →](https://runapi.ai/workbuddy.md) - Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy.
- [Kling models →](https://runapi.ai/models/kling.md) - See all Kling variants, pricing tiers, and API docs.

## Try Kling in WorkBuddy today.

Get a free RunAPI key, add the MCP server to WorkBuddy, and start generating video with Kling 3.0.

[Browse models →](https://runapi.ai/models.md)

---

## More from RunAPI

- [Home](https://runapi.ai/.md)
### Product
- [Model Catalog](https://runapi.ai/models.md)
- [Pricing](https://runapi.ai/pricing.md)
- [Providers](https://runapi.ai/models#all-models)
### Developers
- [Documentation](https://runapi.ai/docs/guides)
- [SDKs](https://runapi.ai/sdk.md)
- [CLI](https://runapi.ai/cli.md)
- [MCP Server](https://runapi.ai/mcp.md)
- [x402](https://runapi.ai/x402.md)
### Guides
- [Claude Code vs Cursor](https://runapi.ai/claude-code-vs-cursor.md)
- [Cursor API Setup](https://runapi.ai/cursor-api-setup.md)
- [RunAPI vs OpenRouter](https://runapi.ai/openrouter-alternative.md)
### Company
- [Enterprise](https://runapi.ai/contact.md)
- [Contact](https://runapi.ai/contact.md)
### Legal
- [Terms](https://runapi.ai/terms.md)
- [Privacy](https://runapi.ai/privacy.md)
- [Site index for agents](https://runapi.ai/llms.txt)

Contact: contact@runapi.ai

## Structured data

```json
[
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "WebSite",
    "name": "RunAPI",
    "url": "https://runapi.ai/",
    "potentialAction": {
      "@type": "SearchAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://runapi.ai/models?q={search_term_string}"
      },
      "query-input": "required name=search_term_string"
    }
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "Organization",
    "name": "RunAPI",
    "url": "https://runapi.ai/",
    "logo": {
      "@type": "ImageObject",
      "url": "https://runapi.ai/icon.svg"
    },
    "sameAs": [
      "https://github.com/runapi-ai"
    ]
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "SoftwareApplication",
    "name": "RunAPI Kling for WorkBuddy",
    "applicationCategory": "DeveloperApplication",
    "description": "Generate video with Kling 3.0 in WorkBuddy over MCP. Add RunAPI as an MCP server and the workbench agent handles text-to-video, sound, and 1080p output.",
    "url": "https://runapi.ai/workbuddy-kling"
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "FAQPage",
    "mainEntity": [
      {
        "@type": "Question",
        "name": "Can I use Kling in WorkBuddy?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Yes. WorkBuddy speaks MCP natively. Add RunAPI as an MCP server with your RUNAPI_API_KEY and the workbench agent can call the Kling text_to_video and image_to_video tools directly — no plugins or separate video service accounts."
        }
      },
      {
        "@type": "Question",
        "name": "How does Kling per-second billing work on RunAPI?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Kling charges per second of generated video. The rate depends on output_resolution and whether enable_sound is on. A 5-second 720p clip without sound is the cheapest option; 1080p with sound costs roughly twice as much per second. Check the RunAPI pricing page for exact rates."
        }
      },
      {
        "@type": "Question",
        "name": "What happens when a Kling generation fails — do I lose credits?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "No. RunAPI only bills for completed generations. If the task fails or times out, the reserved credits are rolled back to your account balance, and WorkBuddy simply reports the failed status."
        }
      },
      {
        "@type": "Question",
        "name": "Can Kling generate videos with sound?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Yes. Ask WorkBuddy to enable sound, which sets enable_sound to true in the tool call. Kling 3.0 generates synchronized audio matching the video content. Sound generation increases the per-second cost — at 720p, sound adds about 3 cents per second."
        }
      },
      {
        "@type": "Question",
        "name": "Can I control camera motion in Kling videos?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Kling 3.0 has a separate motion_control tool for applying motion presets to a source image with a reference video, exposed through the same runapi MCP server. The text_to_video tool relies on prompt descriptions for camera direction."
        }
      }
    ]
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "HowTo",
    "name": "How to use Kling in WorkBuddy via RunAPI",
    "description": "Add RunAPI as an MCP server in WorkBuddy, prompt the workbench agent, and let it call the Kling text_to_video or image_to_video tool for the generated video.",
    "step": [
      {
        "@type": "HowToStep",
        "position": 1,
        "name": "Add RunAPI as an MCP server",
        "text": "Register an MCP server named runapi in WorkBuddy pointing at https://runapi.ai/mcp over streamable HTTP, with the Authorization header reading your key from RUNAPI_API_KEY. One server covers Kling alongside every other RunAPI model.",
        "url": "https://runapi.ai/workbuddy-kling#how-step-1"
      },
      {
        "@type": "HowToStep",
        "position": 2,
        "name": "Prompt the workbench agent",
        "text": "Ask WorkBuddy to generate a video with Kling 3.0. Include the scene description, duration_seconds (3–15), aspect_ratio, and optionally enable_sound for native audio. For image-driven generation, attach a first frame image URL and the agent uses the image_to_video tool instead.",
        "url": "https://runapi.ai/workbuddy-kling#how-step-2"
      },
      {
        "@type": "HowToStep",
        "position": 3,
        "name": "Let the agent run the tool and collect the result",
        "text": "WorkBuddy calls the Kling tool through the runapi MCP server and receives a task_id immediately. The agent polls the async task until it completes — typically 30–120 seconds depending on duration and resolution — then reports the video URL back in the workbench.",
        "url": "https://runapi.ai/workbuddy-kling#how-step-3"
      }
    ]
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "BreadcrumbList",
    "itemListElement": [
      {
        "@type": "ListItem",
        "position": 1,
        "name": "Home",
        "item": "https://runapi.ai/"
      },
      {
        "@type": "ListItem",
        "position": 2,
        "name": "RunAPI Kling for WorkBuddy",
        "item": "https://runapi.ai/workbuddy-kling"
      }
    ]
  }
]
```
