[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Wan 2.2 S2V 14B](https://spiral.ai/integrations/instinct/wan-2-2-s2v-14b)

# How to Use Wan 2.2 S2V 14B in Instinct

Wan 2.2 S2V 14B turns a reference image and recorded speech or singing into an animated performance. Use it for expressive presenters and character scenes where prompts direct body movement and camera work.

|  |  |
| --- | --- |
| Model | Wan 2.2 S2V 14B |
| Available through | fal |
| Category | Video |
| Price | Up to $7.80 per run at the default inputs for 60 seconds of input. `resolution`: 480p (default) $7.80, 580p $11.70, 720p $15.60. |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Wan 2.2 S2V 14B in Instinct

- Every weekday, use Wan 2.2 S2V 14B with today's prepared presenter image and five-second announcement recording. Make a 480p half-body shot at 16 frames per second with a steady camera and one small greeting gesture.
- Each Friday, use Wan 2.2 S2V 14B with the selected host image and five-second podcast excerpt. Create a 720p seated speaking shot at 16 frames per second and place it in the weekly review collection.
- When a lesson introduction recording and instructor image are ready, use Wan 2.2 S2V 14B to make a five-second 480p draft at 16 frames per second. Request a half-body view, a static camera, and restrained gestures.
- Each week, use Wan 2.2 S2V 14B with the approved performer image and five-second singing excerpt. Generate a 720p take at 16 frames per second with gentle swaying and a slow camera move closer.
- For each prepared character image and five-second dialogue recording, use Wan 2.2 S2V 14B to create a 480p draft at 16 frames per second. Request a medium shot where the character turns slightly toward someone off camera.

## How to set up Wan 2.2 S2V 14B in Instinct

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

### Use the Spiral skill

1. **Send Instinct 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 Spiral's MCP server

1. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

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

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### 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 2.2 S2V 14B**: 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/wan/v2.2-14b/speech-to-video",
    "input": {
      "prompt": "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard.",
      "image_url": "https://storage.googleapis.com/falserverless/example_inputs/wan_s2v_cat.png",
      "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/wan_s2v_talk.wav"
    }
  }'
```

Then paste one of the prompts above: Instinct finds Wan 2.2 S2V 14B on Spiral, shows the price and runs it.

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

## Wan 2.2 S2V 14B tools and prices

- [Wan-2.2 14B · Speech to Video](https://spiral.ai/tools/fal/fal-ai/wan/v2.2-14b/speech-to-video) (fal): `resolution`: 480p (default) $0.13, 580p $0.195, 720p $0.26 per second.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| negative_prompt |  |  | Negative prompt for video generation. |
| num_frames | 40 to 120 | 80 | Number of frames to generate. Must be between 40 to 120, (must be multiple of 4). |
| frames_per_second | 4 to 60 | 16 | Frames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If `adjust_fps_for_interpolation` is set to false, this value will be used as-is. |
| seed |  | — | Random seed for reproducibility. If None, a random seed is chosen. |
| resolution | 480p, 580p, 720p | 480p | Resolution of the generated video (480p, 580p, or 720p). |
| num_inference_steps | 2 to 40 | 27 | Number of inference steps for sampling. Higher values give better quality but take longer. |

## What can you do with Wan 2.2 S2V 14B in Instinct?

Produce recurring presenter clips from prepared images and short recordings. A scheduled agent can generate consistent shot briefs and organize each batch for review.

### Presenter introductions

Animate a presenter image with a short recorded introduction. Request a half-body shot with a small greeting gesture.

### Singing previews

Pair a performer image with a short vocal excerpt to test the expression, movement, and camera direction for a music video.

### Dialogue scene drafts

Turn a character image and recorded line into a short acted shot. Describe the character's posture and interaction with someone off camera.

### Course introductions

Create a brief instructor welcome from a reference image and narration. Keep the camera steady and request restrained gestures.

### Podcast video excerpts

Give a short spoken excerpt a visual performance using a host image. Direct a seated pose and subtle head movement.

### Camera direction comparisons

Use the same character image and audio to compare a static medium shot with a slow camera move before choosing a scene's direction.

### Full-body performance studies

Animate a full-body reference with speech or singing to explore walking, posture, and gestures within a short shot.

## Overview

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

## Wan 2.2 S2V 14B in other agents

- [Amp](https://spiral.ai/integrations/amp/wan-2-2-s2v-14b)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/wan-2-2-s2v-14b)
- [Claude](https://spiral.ai/integrations/claude-desktop/wan-2-2-s2v-14b)
- [Claude Code](https://spiral.ai/integrations/claude-code/wan-2-2-s2v-14b)
- [Cline](https://spiral.ai/integrations/cline/wan-2-2-s2v-14b)
- [Codex](https://spiral.ai/integrations/codex/wan-2-2-s2v-14b)
- [Cursor](https://spiral.ai/integrations/cursor/wan-2-2-s2v-14b)
- [Devin](https://spiral.ai/integrations/devin/wan-2-2-s2v-14b)
- [dots](https://spiral.ai/integrations/dots/wan-2-2-s2v-14b)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/wan-2-2-s2v-14b)
- [Gemini](https://spiral.ai/integrations/gemini/wan-2-2-s2v-14b)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/wan-2-2-s2v-14b)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/wan-2-2-s2v-14b)
- [goose](https://spiral.ai/integrations/goose/wan-2-2-s2v-14b)
- [Grok](https://spiral.ai/integrations/grok/wan-2-2-s2v-14b)
- [Grok Build](https://spiral.ai/integrations/grok-build/wan-2-2-s2v-14b)
- [Hermes](https://spiral.ai/integrations/hermes/wan-2-2-s2v-14b)
- [Manus](https://spiral.ai/integrations/manus/wan-2-2-s2v-14b)
- [Muse](https://spiral.ai/integrations/muse/wan-2-2-s2v-14b)
- [Muse Code](https://spiral.ai/integrations/muse-code/wan-2-2-s2v-14b)
- [n8n](https://spiral.ai/integrations/n8n/wan-2-2-s2v-14b)
- [Notion](https://spiral.ai/integrations/notion/wan-2-2-s2v-14b)
- [OpenClaw](https://spiral.ai/integrations/openclaw/wan-2-2-s2v-14b)
- [opencode](https://spiral.ai/integrations/opencode/wan-2-2-s2v-14b)
- [Perplexity](https://spiral.ai/integrations/perplexity/wan-2-2-s2v-14b)
- [Raycast](https://spiral.ai/integrations/raycast/wan-2-2-s2v-14b)
- [VS Code](https://spiral.ai/integrations/vscode/wan-2-2-s2v-14b)
- [Windsurf](https://spiral.ai/integrations/windsurf/wan-2-2-s2v-14b)
- [Zapier](https://spiral.ai/integrations/zapier/wan-2-2-s2v-14b)

## More Instinct guides

- [Wan 2.2 FastWan 5B Text to Video](https://spiral.ai/integrations/instinct/wan-2-2-fastwan-5b-text-to-video)
- [Wan 2.5 Image to Video](https://spiral.ai/integrations/instinct/wan-2-5-image-to-video)
- [Wan 2.2 Animate Replace](https://spiral.ai/integrations/instinct/wan-2-2-animate-replace)
- [Wan 2.5 Text to Video](https://spiral.ai/integrations/instinct/wan-2-5-text-to-video)
- [Wan 2.2 Animate Move](https://spiral.ai/integrations/instinct/wan-2-2-animate-move)
- [Wan 2.6 Image to Video](https://spiral.ai/integrations/instinct/wan-2-6-image-to-video)

## Questions about Wan 2.2 S2V 14B in Instinct

**Can Instinct use Wan 2.2 S2V 14B?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Wan 2.2 S2V 14B like any built-in tool.

**How much does Wan 2.2 S2V 14B cost in Instinct?**

Up to $7.80 per run at the default inputs for 60 seconds of input. `resolution`: 480p (default) $7.80, 580p $11.70, 720p $15.60. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.

**Do I need a fal account to use Wan 2.2 S2V 14B in Instinct?**

You need no fal account. Instinct uses one Spiral API key for every tool, and Spiral runs Wan 2.2 S2V 14B on its own fal account.

**How long does it take to set up Wan 2.2 S2V 14B in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while Wan 2.2 S2V 14B runs?**

Wan 2.2 S2V 14B runs in the background. Instinct starts the run, checks on it and gives you the video when it's ready.

**Can Wan 2.2 S2V animate more than a face?**

Yes. It supports half-body and full-body characters, making it useful for presenters, gestures, and acted scenes.

**Can Wan 2.2 S2V animate singing?**

Yes. Singing and performance are documented uses alongside spoken dialogue. Try a short vocal passage with a reference image of the performer.

**What should I put in a Wan 2.2 S2V prompt?**

Describe the visible action: how the character moves, who they interact with, and what the camera does. For example, ask for a seated speaker who leans forward as the camera slowly moves closer.

**How long should a Wan 2.2 S2V shot be?**

Plan short shots: the hosted endpoint accepts 40 to 120 frames. At 16 frames per second, that works out to 2.5 to 7.5 seconds; 80 frames gives a five-second shot.

**Can Wan 2.2 S2V produce 720p video?**

Yes. The maker documents both 480p and 720p generation. Use a short 480p draft to judge the performance before requesting a 720p take.

