[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Wan 3.0 Prime Text to Video](https://spiral.ai/integrations/opencode/wan-3-0-prime-text-to-video)

# How to Use Wan 3.0 Prime Text to Video in opencode

Wan 3.0 Prime Text to Video creates scenes from a written description, including timed shots and generated sound. Unlike Wan 3.0 Prime Image to Video, it starts from text alone.

|  |  |
| --- | --- |
| Model | Wan 3.0 Prime Text to Video |
| Available through | fal |
| Category | Video |
| Price | `resolution`: 480p $0.0884, 720p $0.182, 1080p (default) $0.364 per second. Billed on `duration`, default 5. |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Wan 3.0 Prime Text to Video in opencode

- Use Wan 3.0 Prime Text to Video to make a silent five-second background for our garden website: morning light through leaves, a slow forward camera move, no lettering. Read the design brief for the palette; output 1080p in 16:9.
- Read our game's scene brief, then use Wan 3.0 Prime Text to Video for a 10-second 720p preview. From 0-5 seconds, show a lantern-lit harbor; from 5-10 seconds, follow a courier stepping onto a boat. Include water and footsteps.
- Estimate, then generate a 5-second 9:16 clip with Wan 3.0 Prime Text to Video: a paper boat drifting down a rainy street. Save the result in ./assets.
- Make a 10-second product teaser with Wan 3.0 Prime Text to Video for a smartwatch, slow orbit shot, studio lighting.
- Generate three 5-second b-roll clips of a busy coffee shop with Wan 3.0 Prime Text to Video and list what each cost.

## How to set up Wan 3.0 Prime 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 Wan 3.0 Prime 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": "alibaba/wan-3.0-prime/text-to-video",
    "input": {
      "prompt": "A red panda walking through a bamboo forest at sunrise"
    }
  }'
```

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

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

## Wan 3.0 Prime Text to Video tools and prices

- [Wan 3.0 Prime Text to Video](https://spiral.ai/tools/fal/alibaba/wan-3.0-prime/text-to-video) (fal): `resolution`: 480p $0.0884, 720p $0.182, 1080p (default) $0.364 per second. Billed on `duration`, default 5.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| resolution | 480p, 720p, 1080p | 1080p | Output video resolution tier. |
| aspect_ratio | adaptive, 16:9, 4:3, 1:1, 3:4, 9:16 | adaptive | Output aspect ratio, or adaptive selection. |
| duration | 2 to 30 | 5 | Output duration in seconds. Set to null for smart duration, which lets the model pick a length from the prompt and reference media. |
| audio |  | true | Include generated audio. |
| enable_prompt_expansion |  | true | Enable intelligent prompt rewriting. Disabling it can save roughly 20-60 seconds of latency but is likely to degrade generation quality. |
| enable_thinking |  | false | Enable enhanced reasoning before generation. |

## What can you do with Wan 3.0 Prime Text to Video in opencode?

Create video assets for a site, app, or game while working in the project. A coding agent can turn the creative brief into shot directions and place the resulting clips where the project needs them.

### Short product ads

Create a 10-second product scene with a clear reveal, one camera move, and a closing hold. Add exact product names and offer text during editing.

### Storyboard previews

Preview a short sequence with numbered shots and timestamps. Use the result to judge pacing, framing, and transitions before production.

### Atmospheric background footage

Make a slow shot of a workshop, garden, or imagined landscape for a website or presentation. Request silence when the footage will sit behind other audio.

### Dialogue scene drafts

Try a brief exchange or a single spoken line with a specified setting and soundscape. Review the delivery and audio before using the clip.

### Game scene concepts

Explore an environment, character entrance, or short story beat. Keep each clip focused on a few visible actions so the team can assess the direction.

### Travel campaign concepts

Plan a short destination sequence around light, scenery, and a deliberate camera path. Treat imagined locations as concept footage.

## Overview

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

## Wan 3.0 Prime Text to Video in other agents

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

## More opencode guides

- [Wan 3.0 Prime Reference to Video](https://spiral.ai/integrations/opencode/wan-3-0-prime-reference-to-video)
- [Wan 3.0 Reference to Video](https://spiral.ai/integrations/opencode/wan-3-0-reference-to-video)
- [Wan 3.0 Prime Image to Video](https://spiral.ai/integrations/opencode/wan-3-0-prime-image-to-video)
- [Wan 3.0 Text to Video](https://spiral.ai/integrations/opencode/wan-3-0-text-to-video)
- [Wan 3.0 Image to Video](https://spiral.ai/integrations/opencode/wan-3-0-image-to-video)
- [WaveSpeed Video Background Remover](https://spiral.ai/integrations/opencode/wavespeed-video-background-remover)

## Questions about Wan 3.0 Prime Text to Video in opencode

**Can opencode use Wan 3.0 Prime Text to Video?**

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

**How much does Wan 3.0 Prime Text to Video cost in opencode?**

`resolution`: 480p $0.0884, 720p $0.182, 1080p (default) $0.364 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 Wan 3.0 Prime Text to Video in opencode?**

No. Spiral runs Wan 3.0 Prime 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 Wan 3.0 Prime Text to Video in opencode?**

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

**Does opencode wait while Wan 3.0 Prime Text to Video runs?**

Wan 3.0 Prime 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 Wan 3.0 Prime videos be?**

A single output can run up to 30 seconds, at up to 1080p and 30 fps. Give each action enough time instead of filling the clip with rapid instructions.

**Can Wan 3.0 Prime generate sound?**

Yes. It can generate dialogue, background music, and sound effects with the picture; describe the speech and sounds you want in the prompt.

**Which prompt languages does Wan 3.0 Prime support?**

Alibaba documents Chinese and English prompts. Use either language to describe the scene, actions, and camera direction.

**How should I write a multi-shot prompt?**

Number the shots and give each a start and end time. For each shot, describe the subject, setting, action, and camera treatment, then specify dialogue and sound separately.

**What should I check before using the finished video?**

Check generated lettering and listen closely to the audio. Alibaba identifies on-screen text accuracy and audio texture as areas still improving, so plan to add exact titles and correct the sound in an editor.

