[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Kling 3.0 4K Text to Video](https://spiral.ai/integrations/opencode/kling-3-0-4k-text-to-video)

# How to Use Kling 3.0 4K Text to Video in opencode

Create native 4K footage for scenes that need fine detail without a source photo. Unlike Kling 3.0 4K Image to Video, it builds the scene from your written direction.

|  |  |
| --- | --- |
| Model | Kling 3.0 4K Text to Video |
| Available through | fal |
| Category | Video |
| Price | $0.546 per second. Billed on `duration`, default 5. |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Kling 3.0 4K Text to Video in opencode

- Use Kling 3.0 4K Text to Video to create a 10-second setting preview from the game's environment brief. Shot one lasts 5 seconds and establishes the abandoned station; shot two lasts 5 seconds and tracks beside a lone traveler. Keep the traveler's coat and backpack identical.
- Use Kling 3.0 4K Text to Video to make three separate 5-second previews for the landing page's forest scene. Keep the scene description fixed and compare a locked camera, a slow push-in, and a gentle sideways track.
- Use Kling 3.0 4K Text to Video to preview the launch video's opening from the creative brief. Make a 9-second sequence with three 3-second shots: a wide workshop view, a close-up of a rotating wheel, and the maker looking up.
- Estimate, then generate a 5-second 9:16 clip with Kling 3.0 4K Text to Video: a paper boat drifting down a rainy street. Save the result in ./assets.
- Make a 10-second product teaser with Kling 3.0 4K Text to Video for a smartwatch, slow orbit shot, studio lighting.

## How to set up Kling 3.0 4K Text to Video in opencode

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Leave out `--global` to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

```bash
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
```

2. **Sign in**: Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, `/mcps` starts the same sign-in.

```bash
opencode mcp auth spiral
```

3. **Check it**: Spiral shows as connected.

```bash
opencode mcp list
```

### Use the Spiral skill

1. **Send opencode this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Kling 3.0 4K Text to Video**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/kling-video/v3/4k/text-to-video",
    "input": {
      "prompt": "Close-up of glowing fireflies dancing in a dark forest at twilight. Soft bioluminescent particles float through the air. Shallow depth of field, bokeh lights in…"
    }
  }'
```

Then paste one of the prompts above: opencode finds Kling 3.0 4K Text to Video on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/opencode

## Kling 3.0 4K Text to Video tools and prices

- [Kling Video V3 4K · Text to Video](https://spiral.ai/tools/fal/fal-ai/kling-video/v3/4k/text-to-video) (fal): $0.546 per second. Billed on `duration`, default 5.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| prompt |  | — | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. |
| duration | 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | 5 | The duration of the generated video in seconds |
| multi_prompt |  | — | List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations. |
| generate_audio |  | true | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |
| shot_type | customize, intelligent | customize | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. |
| aspect_ratio | 16:9, 9:16, 1:1 | 16:9 | The aspect ratio of the generated video frame |

## What can you do with Kling 3.0 4K Text to Video in opencode?

Create scene previews and moving visual assets for a project's website, game, or launch video. Use the project's brief and artwork to specify subjects, camera movement, and short shot sequences.

### Ad storyboard previews

Preview a short commercial with an opening view, a product detail, and a closing shot. Use the sequence to judge pacing before production.

### Atmospheric B-roll

Create a short establishing shot with a deliberate camera move, changing light, or environmental motion for an edited video.

### Short narrative previews

Stage a brief action with a setup, a reaction, and a payoff. Test the scene's camera coverage and timing before filming or animation.

### Camera treatment tests

Compare a locked camera, a slow push-in, and a tracking shot for the same scene. Change one movement at a time to choose a treatment.

### Original setting concepts

Build a setting from a written brief, such as a rain-soaked station or a city at sunrise. Explore composition and camera direction before commissioning detailed artwork.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All opencode guides](https://spiral.ai/integrations/opencode)

## Kling 3.0 4K Text to Video in other agents

- [Amp](https://spiral.ai/integrations/amp/kling-3-0-4k-text-to-video)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/kling-3-0-4k-text-to-video)
- [Claude](https://spiral.ai/integrations/claude-desktop/kling-3-0-4k-text-to-video)
- [Claude Code](https://spiral.ai/integrations/claude-code/kling-3-0-4k-text-to-video)
- [Cline](https://spiral.ai/integrations/cline/kling-3-0-4k-text-to-video)
- [Codex](https://spiral.ai/integrations/codex/kling-3-0-4k-text-to-video)
- [Cursor](https://spiral.ai/integrations/cursor/kling-3-0-4k-text-to-video)
- [Devin](https://spiral.ai/integrations/devin/kling-3-0-4k-text-to-video)
- [dots](https://spiral.ai/integrations/dots/kling-3-0-4k-text-to-video)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/kling-3-0-4k-text-to-video)
- [Gemini](https://spiral.ai/integrations/gemini/kling-3-0-4k-text-to-video)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/kling-3-0-4k-text-to-video)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/kling-3-0-4k-text-to-video)
- [goose](https://spiral.ai/integrations/goose/kling-3-0-4k-text-to-video)
- [Grok](https://spiral.ai/integrations/grok/kling-3-0-4k-text-to-video)
- [Grok Build](https://spiral.ai/integrations/grok-build/kling-3-0-4k-text-to-video)
- [Hermes](https://spiral.ai/integrations/hermes/kling-3-0-4k-text-to-video)
- [Instinct](https://spiral.ai/integrations/instinct/kling-3-0-4k-text-to-video)
- [Manus](https://spiral.ai/integrations/manus/kling-3-0-4k-text-to-video)
- [Muse](https://spiral.ai/integrations/muse/kling-3-0-4k-text-to-video)
- [Muse Code](https://spiral.ai/integrations/muse-code/kling-3-0-4k-text-to-video)
- [n8n](https://spiral.ai/integrations/n8n/kling-3-0-4k-text-to-video)
- [Notion](https://spiral.ai/integrations/notion/kling-3-0-4k-text-to-video)
- [OpenClaw](https://spiral.ai/integrations/openclaw/kling-3-0-4k-text-to-video)
- [Perplexity](https://spiral.ai/integrations/perplexity/kling-3-0-4k-text-to-video)
- [Raycast](https://spiral.ai/integrations/raycast/kling-3-0-4k-text-to-video)
- [VS Code](https://spiral.ai/integrations/vscode/kling-3-0-4k-text-to-video)
- [Windsurf](https://spiral.ai/integrations/windsurf/kling-3-0-4k-text-to-video)
- [Zapier](https://spiral.ai/integrations/zapier/kling-3-0-4k-text-to-video)

## More opencode guides

- [Kling 3.0 4K Image to Video](https://spiral.ai/integrations/opencode/kling-3-0-4k-image-to-video)
- [Kling 3.0 Pro Image to Video](https://spiral.ai/integrations/opencode/kling-3-0-pro-image-to-video)
- [Kling 2.6 Pro Text to Video](https://spiral.ai/integrations/opencode/kling-2-6-pro-text-to-video)
- [Kling 3.0 Pro Motion Control](https://spiral.ai/integrations/opencode/kling-3-0-pro-motion-control)
- [Kling 2.6 Pro Image to Video](https://spiral.ai/integrations/opencode/kling-2-6-pro-image-to-video)
- [Kling 3.0 Pro Text to Video](https://spiral.ai/integrations/opencode/kling-3-0-pro-text-to-video)

## Questions about Kling 3.0 4K Text to Video in opencode

**Can opencode use Kling 3.0 4K Text to Video?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Kling 3.0 4K Text to Video like any built-in tool.

**How much does Kling 3.0 4K Text to Video cost in opencode?**

$0.546 per second. Billed on `duration`, default 5. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.

**Do I need a fal account to use Kling 3.0 4K Text to Video in opencode?**

No. Spiral runs Kling 3.0 4K Text to Video on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Kling 3.0 4K Text to Video in opencode?**

About two minutes: add the server, then sign in, then check it.

**Does opencode wait while Kling 3.0 4K Text to Video runs?**

Kling 3.0 4K Text to Video runs in the background. opencode starts the run, checks on it and gives you the video when it's ready.

**How long can a Kling 3.0 video be?**

A generation can run from 3 to 15 seconds. Plan a longer story as separate clips with clear beginnings and endings.

**Can Kling 3.0 make a scene with several shots?**

Yes, Kling 3.0 supports up to six shots in one output. Give each shot a clear purpose and keep the complete sequence within 15 seconds.

**How should I describe a character across several shots?**

Define the character at the start, then reuse the same description. Keep identifying details such as clothing and appearance consistent when the camera angle changes.

**Does Kling 3.0 understand camera movement?**

Yes. Describe the camera's behavior directly, such as tracking beside a walking subject or shifting focus from a foreground object to a person behind it.

**Why might Kling 3.0 ignore a requested cut?**

Automatic shot planning can keep a scene in one shot when it considers that treatment more suitable. Use an explicit storyboard when the sequence depends on particular cuts.

