# Ltx 2.3 Fast Text To Video 

> AI model for generating video content

## Overview

- **Model ID**: `ltx-2-3-fast-t2v`
- **Category**: video
- **Provider**: ltx
- **Source Type**: Closed Source Model
- **Status**: model_ready
- **Screenshot**: `https://assets.modelslab.ai/generations/7029a6fb-cda3-4a62-a5e3-69f379676c39.webp`

## API Information

This model can be used via our HTTP API. See the API documentation and usage examples below.

### Endpoint

- **URL**: `https://modelslab.com/api/v7/video-fusion/text-to-video`
- **Method**: POST

### Parameters

- **`prompt`** (required): Text prompt describing the desired video content
  - Type: textarea

- **`resolution`** (optional): Output video resolution: Supported resolutions include 1920×1080, 2560×1440, and 3840×2160.
  - Type: select (options: FHD, 2K, 4K)

- **`duration`** (required): Video duration (in seconds): Supported durations depend on the model and include 6s, 8s, and 10s.
  - Type: select (options: 6s, 8s, 10s)

- **`generate_audio`** (optional): Generate audio for the video. When true, the generated video will include AI-generated audio matching the scene. When false, only silent video is generated.
  - Type: toggle

- **`fps`** (optional): **Frame rate (frames per second):** Supported frame rates depend on the model and resolution, with available options **25 FPS** and **50 FPS**. This parameter is optional and defaults to **25 FPS**.
  - Type: select (options: 25, 50)

## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://modelslab.com/api/v7/video-fusion/text-to-video \
  --header "Content-Type: application/json" \
  --data '{
    "key": "YOUR_API_KEY",
    "model_id": "ltx-2-3-fast-t2v",
    "prompt": "Two young men arguing in a dimly lit alley at night, tension rising before a sudden realistic fist fight begins, natural human movements, punches and dodges, camera shaking slightly like handheld footage, cinematic lighting, gritty atmosphere, slow motion impact moments, ultra realistic, 4k, dramatic scene",
    "resolution": "1920x1080",
    "duration": "6",
    "generate_audio": false,
    "fps": "25"
  }'
```

### Python

```python
import requests

response = requests.post(
    "https://modelslab.com/api/v7/video-fusion/text-to-video",
    headers={
        "Content-Type": "application/json"
    },
    json={
        "key": "YOUR_API_KEY",
        "model_id": "ltx-2-3-fast-t2v",
        "prompt": "Two young men arguing in a dimly lit alley at night, tension rising before a sudden realistic fist fight begins, natural human movements, punches and dodges, camera shaking slightly like handheld footage, cinematic lighting, gritty atmosphere, slow motion impact moments, ultra realistic, 4k, dramatic scene",
        "resolution": "1920x1080",
        "duration": "6",
        "generate_audio": False,
        "fps": "25"
    }
)

print(response.json())
```

### JavaScript

```javascript
fetch("https://modelslab.com/api/v7/video-fusion/text-to-video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "key": "YOUR_API_KEY",
    "model_id": "ltx-2-3-fast-t2v",
    "prompt": "Two young men arguing in a dimly lit alley at night, tension rising before a sudden realistic fist fight begins, natural human movements, punches and dodges, camera shaking slightly like handheld footage, cinematic lighting, gritty atmosphere, slow motion impact moments, ultra realistic, 4k, dramatic scene",
    "resolution": "1920x1080",
    "duration": "6",
    "generate_audio": false,
    "fps": "25"
  })
})
.then(response => response.json())
.then(data => console.log(data));
```

## Integration Options

### CLI

Install: `curl -fsSL https://modelslab.sh/install.sh | sh` or `brew install modelslab/tap/modelslab`

```bash
modelslab auth login                                    # Authenticate
modelslab models search "ltx-2-3-fast-t2v"                       # Find this model
modelslab models detail --id ltx-2-3-fast-t2v                    # Get model details
modelslab generate image --prompt "..." --model ltx-2-3-fast-t2v  # Generate with model
modelslab config set generation.default_model ltx-2-3-fast-t2v   # Set as default
```

- Website: https://modelslab.sh
- GitHub: https://github.com/ModelsLab/modelslab-cli

### MCP Servers (Model Context Protocol)

For Claude Code, Cursor, VS Code, Windsurf, and any MCP-compatible agent.

- Generation: `https://modelslab.com/mcp/v7` (API key auth, 23 tools)
- Agent Control Plane: `https://modelslab.com/mcp/agents` (Bearer token auth, 10 tools)

Claude Code config (`~/.claude/settings.json`):

```json
{
  "mcpServers": {
    "modelslab-v7": {
      "url": "https://modelslab.com/mcp/v7",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
```

- Documentation: https://docs.modelslab.com/mcp-web-api/overview

### Agent Skills

Install skill files directly into AI coding agents:

```bash
npx skills add modelslab/skills --all                          # All skills
npx skills add modelslab/skills --skill image-generation       # Specific skill
npx skills add modelslab/skills --all -a claude-code -a cursor # Target agents
```

- GitHub: https://github.com/ModelsLab/skills
- Documentation: https://docs.modelslab.com/agent-skills

### SDKs

- Python: `pip install modelslab`
- TypeScript: `npm install modelslab`
- PHP: `composer require modelslab/modelslab`
- Go: `go get github.com/modelslab/modelslab-go`
- Dart: `dart pub add modelslab`

## Links

- [Model Playground](https://modelslab.com/models/ltx-23-fast-text-to-video/ltx-2-3-fast-t2v)
- [API Documentation](https://docs.modelslab.com)
- [ModelsLab Platform](https://modelslab.com)