[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [H3 Max Text to Video](https://spiral.ai/integrations/instinct/h3-max-text-to-video)

# How to Use H3 Max Text to Video in Instinct

Create a short scene from a written shot brief, including camera direction and sound. Unlike H3 Max Image to Video, it starts from text alone.

|  |  |
| --- | --- |
| Model | H3 Max Text to Video |
| Available through | fal |
| Category | Video |
| Price | $0.104 per second at 768p ($0.065 at 480p, $0.208 at 1080p). |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with H3 Max Text to Video in Instinct

- For each new seasonal scene brief, use H3 Max Text to Video to create a six-second video at 768p. Show one clear action, a slow camera movement, and the ambient sounds of the setting.
- Each Monday, use H3 Max Text to Video to create three five-second videos at 768p from that week's campaign brief. Give each a different camera movement, keep the product action the same, and describe the sound in every prompt.
- Every Monday at 9am: estimate, then generate a 5-second 9:16 clip with H3 Max Text to Video: a paper boat drifting down a rainy street.
- Make a 10-second product teaser with H3 Max Text to Video for a smartwatch, slow orbit shot, studio lighting.
- Generate three 5-second b-roll clips of a busy coffee shop with H3 Max Text to Video and list what each cost.

## How to set up H3 Max Text to Video 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 H3 Max 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": "minimax/h3-max/text-to-video",
    "input": {
      "prompt": "A white kitten chases a butterfly across a sunlit garden. Gentle camera tracking, natural movement, soft afternoon light filtering through the leaves.",
      "prompt_expansion_mode": "balanced"
    }
  }'
```

Then paste one of the prompts above: Instinct finds H3 Max Text to Video on Spiral, shows the price and runs it.

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

## H3 Max Text to Video tools and prices

- [MiniMax H3 Max Text to Video](https://spiral.ai/tools/fal/minimax/h3-max/text-to-video) (fal): $0.104 per second at 768p ($0.065 at 480p, $0.208 at 1080p).

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| duration | 0.92 to 15 | 5 | Video length in seconds. The output can run up to about 0.7 s longer than requested. Use at least 2 s with target_audio_url. |
| resolution | 480P, 768P, 1080P | 768P | The native generation resolution, or 1080P latent refinement from a native 768P source. |
| seed |  | — | Random seed. A random seed is selected when omitted. |
| target_audio_url |  | — | Optional URL of an audio clip at least 2 seconds long (maximum 15 MB) to pin to the generated soundtrack. Longer clips are trimmed to the generated video's length, keeping the beginning. The original audio replaces the output soundtrack, padded with silence if shorter than the video, without changing playback speed. Exceptionally high sample rates may be resampled to 96 kHz. Accepts an HTTP(S) URL or a base64 data URI. |
| aspect_ratio | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | 16:9 | The aspect ratio of the generated video. |

## What can you do with H3 Max Text to Video in Instinct?

Produce recurring batches of short video concepts from incoming creative briefs. An always-on agent can keep each batch consistent in shot length and visual direction while changing a single creative choice per take.

### Product ad concepts

Plan a short product reveal around one visible action, such as a bottle turning or a box opening. Describe it from scratch or guide the shot with product imagery.

### Storyboard shot studies

Test how a scene reads with a static camera, a slow push forward, or a tracking shot. Keep the action consistent so you can compare the camera choices.

### Animated explainer scenes

Make a short visual explanation of one event, such as water flowing through a filter. Specify the illustration style, action sequence, and accompanying sounds.

### Atmospheric establishing shots

Create a brief setting for a story or presentation, such as a bakery before opening. Pair the camera movement with concrete sounds: shutters, footsteps, and trays.

## Overview

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

## H3 Max Text to Video in other agents

- [Amp](https://spiral.ai/integrations/amp/h3-max-text-to-video)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/h3-max-text-to-video)
- [Claude](https://spiral.ai/integrations/claude-desktop/h3-max-text-to-video)
- [Claude Code](https://spiral.ai/integrations/claude-code/h3-max-text-to-video)
- [Cline](https://spiral.ai/integrations/cline/h3-max-text-to-video)
- [Codex](https://spiral.ai/integrations/codex/h3-max-text-to-video)
- [Cursor](https://spiral.ai/integrations/cursor/h3-max-text-to-video)
- [Devin](https://spiral.ai/integrations/devin/h3-max-text-to-video)
- [dots](https://spiral.ai/integrations/dots/h3-max-text-to-video)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/h3-max-text-to-video)
- [Gemini](https://spiral.ai/integrations/gemini/h3-max-text-to-video)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/h3-max-text-to-video)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/h3-max-text-to-video)
- [goose](https://spiral.ai/integrations/goose/h3-max-text-to-video)
- [Grok](https://spiral.ai/integrations/grok/h3-max-text-to-video)
- [Grok Build](https://spiral.ai/integrations/grok-build/h3-max-text-to-video)
- [Hermes](https://spiral.ai/integrations/hermes/h3-max-text-to-video)
- [Manus](https://spiral.ai/integrations/manus/h3-max-text-to-video)
- [Muse](https://spiral.ai/integrations/muse/h3-max-text-to-video)
- [Muse Code](https://spiral.ai/integrations/muse-code/h3-max-text-to-video)
- [n8n](https://spiral.ai/integrations/n8n/h3-max-text-to-video)
- [Notion](https://spiral.ai/integrations/notion/h3-max-text-to-video)
- [OpenClaw](https://spiral.ai/integrations/openclaw/h3-max-text-to-video)
- [opencode](https://spiral.ai/integrations/opencode/h3-max-text-to-video)
- [Perplexity](https://spiral.ai/integrations/perplexity/h3-max-text-to-video)
- [Raycast](https://spiral.ai/integrations/raycast/h3-max-text-to-video)
- [VS Code](https://spiral.ai/integrations/vscode/h3-max-text-to-video)
- [Windsurf](https://spiral.ai/integrations/windsurf/h3-max-text-to-video)
- [Zapier](https://spiral.ai/integrations/zapier/h3-max-text-to-video)

## More Instinct guides

- [H3 Max Relight](https://spiral.ai/integrations/instinct/h3-max-relight)
- [H3 Max Turbo Extend Video](https://spiral.ai/integrations/instinct/h3-max-turbo-extend-video)
- [H3 Max Reframe Video](https://spiral.ai/integrations/instinct/h3-max-reframe-video)
- [H3 Max Turbo Image to Video](https://spiral.ai/integrations/instinct/h3-max-turbo-image-to-video)
- [H3 Max Reference to Video](https://spiral.ai/integrations/instinct/h3-max-reference-to-video)
- [H3 Max Turbo Reference to Video](https://spiral.ai/integrations/instinct/h3-max-turbo-reference-to-video)

## Questions about H3 Max Text to Video in Instinct

**Can Instinct use H3 Max Text to Video?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run H3 Max Text to Video like any built-in tool.

**How much does H3 Max Text to Video cost in Instinct?**

$0.104 per second at 768p ($0.065 at 480p, $0.208 at 1080p). 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 H3 Max Text to Video in Instinct?**

You need no fal account. Instinct uses one Spiral API key for every tool, and Spiral runs H3 Max Text to Video on its own fal account.

**How long does it take to set up H3 Max Text to Video in Instinct?**

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

**Does Instinct wait while H3 Max Text to Video runs?**

H3 Max Text to Video runs in the background. Instinct starts the run, checks on it and gives you the video when it's ready.

**What is H3 Max good for?**

H3 Max suits short scenes with specific actions, camera direction, and sound. Its post-training focused on following the brief and improving visual quality.

**Does H3 Max generate sound with the video?**

Yes. Describe the ambience, physical sounds, and music you want alongside the action so the audio has a clear brief.

**Is H3 Max's 1080p output native?**

The documented 1080p process refines a native 768p source. Choose it when you need the larger output, while recognizing how it is produced.

**Will a requested five-second clip be exactly five seconds?**

The output can run about 0.7 seconds longer than requested. If the clip must fit an exact edit, check its actual duration and trim it.

**What should I put in an H3 Max prompt?**

Describe the opening composition, what changes on screen, how the camera moves, and what the viewer hears. Use observable actions such as a lid opening or a camera moving toward a label.

