How to Use Wan 3.0 Text to Video in Codex
Wan 3.0 Text to Video creates scenes from written descriptions, including stories with multiple shots and generated sound. Unlike Wan 3.0 Image to Video, it starts without a supplied opening image.
Prompts to try with Wan 3.0 Text to Video in Codex
Copy an example into Codex, or ask in your own words.
Read the creative brief in this project and use Wan 3.0 Text to Video to make a 15-second concept at 720p. Write three consecutive five-second shots, each with one action, a camera direction, and ambient sound.
Read the campaign brief and use Wan 3.0 Text to Video to create a ten-second 1080p rain-soaked street scene. Request one continuous tracking shot, footsteps and rain, no dialogue, and no visible lettering.
Estimate, then generate a 5-second 9:16 clip with Wan 3.0 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 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 Text to Video and list what each cost.
How to set up Wan 3.0 Text to Video in Codex
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
codex mcp add spiral --url https://api.spiral.ai/mcp
- Sign in
Codex opens the browser: sign in to Spiral and click Authorize. No API key. codex mcp list then shows Spiral.
codex mcp login spiral
Use the Spiral skill
- Send Codex this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Wan 3.0 Text to Video
One request; the result comes back by polling or a webhook.
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/text-to-video", "input": { "prompt": "A red panda walking through a bamboo forest at sunrise" } }'
Then paste one of the prompts above: Codex finds Wan 3.0 Text to Video on Spiral, shows the price and runs it.
Wan 3.0 Text to Video providers and prices
Spiral runs Wan 3.0 Text to Video through fal. Open a card for today's price, with every fee included.
resolution: 480p $0.065, 720p $0.13, 1080p (default) $0.26 per second. Billed on duration, default 5.
Settings you can ask for
Wan 3.0 Text to Video works from your prompt. Ask Codex for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Resolution | 480p, 720p, or 1080p | 1080p | Output video resolution tier. |
| Aspect ratio | adaptive, 16:9, 4:3, 1:1, 3:4, or 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 | on or off | on | Include generated audio. |
| Enable prompt expansion | on or off | on | Enable intelligent prompt rewriting. Disabling it can save roughly 20-60 seconds of latency but is likely to degrade generation quality. |
| Enable thinking | on or off | off | Enable enhanced reasoning before generation. |
| Seed | 0 to 2147483647 |
Every API field of Wan 3.0 Text to Video is on its tool page: open its card above.
What can you do with Wan 3.0 Text to Video in Codex?
Turn project creative briefs and visual assets into short video concepts with Wan 3.0. A coding agent can prepare shot descriptions from project files and help review generated clips for text and audio problems.
Product storyboards
Explore a short product story with an establishing shot, a detail shot, and a closing scene. Describe the concept in text, animate a product still, or use references to guide its appearance.
Destination video concepts
Build a short destination sequence around a landscape, a street scene, or local food. Use a written scene description or supplied imagery, then specify the camera movement and ambient sound.
Animated short scenes
Create a brief animated scene with a clear action and reaction. Start with a written character description, an illustrated opening frame, or character references.
Atmospheric cutaways
Generate supporting footage such as rain on a window, steam above coffee, or wind moving through grass. Specify a simple action, a deliberate camera move, and the sounds the scene needs.
More on Wan 3.0 Text to Video and Codex
Overview
Wan 3.0 Text to Video in other agents
Questions about Wan 3.0 Text to Video in Codex
Can Codex use Wan 3.0 Text to Video?
Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Wan 3.0 Text to Video like any built-in tool.
How much does Wan 3.0 Text to Video cost in Codex?
`resolution`: 480p $0.065, 720p $0.13, 1080p (default) $0.26 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 Codex plan is separate.
Do I need a fal account to use Wan 3.0 Text to Video in Codex?
No. Spiral runs Wan 3.0 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 Text to Video in Codex?
About two minutes: add the hosted server, then sign in.
Does Codex wait while Wan 3.0 Text to Video runs?
Wan 3.0 Text to Video runs in the background. Codex starts the run, checks on it and gives you the video when it's ready.
How long can a Wan 3.0 video be?
Wan 3.0 can generate up to 30 seconds in one pass. When you supply a video reference, Alibaba documents a combined limit of 30 seconds for the input video and generated output.
What resolution and frame rate does Wan 3.0 produce?
Wan 3.0 supports 480p, 720p, and 1080p output. Alibaba documents an output frame rate of 30 fps.
Can Wan 3.0 generate sound with the video?
Yes. Wan 3.0 can generate dialogue, background music, and sound effects alongside the visuals.
How should I write a Wan 3.0 prompt?
Describe the subject, setting, action, camera movement, and sound. For several shots, give each shot a number and time range; for an uninterrupted take, explicitly request one continuous shot.
What should I check before using a Wan 3.0 video?
Check any visible text and listen closely to the audio. Alibaba identifies on-screen text accuracy and audio texture as areas that still need improvement.
Start using Wan 3.0 Text to Video in Codex
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Codex:
set up https://spiral.ai/SKILL.md


