Monet AI

Monet AI - Comprehensive AI content generation API for AI agents. Video generation (Sora, Veo, Doubao Seedance, Wan, Hailuo, Kling), image generation (GPT-4o, Nano Banana, Seedream, Flux, Imagen, Ideogram), and music generation (MiniMax Music). Build intelligent workflows with multi-model AI generation capabilities.

# Monet AI Skill

Comprehensive AI content generation API designed for AI agents. Monet AI provides unified access to state-of-the-art AI generation models for video (Sora, Veo, Doubao Seedance, Wan, Hailuo, Kling), image (GPT-4o, Nano Banana, Seedream, Flux, Imagen, Ideogram), and music (MiniMax Music) generation. Build intelligent workflows that combine multiple AI capabilities for automated content creation pipelines.

## When to Use

Use this skill when:

- **Video Generation**: Create AI-generated videos from text prompts using state-of-the-art models
  - Sora: OpenAI's video generation model for high-quality, realistic videos
  - Veo: Google's video generation model
  - Doubao Seedance: ByteDance's AI video model with audio-visual sync
  - Wan: Alibaba's video generation model with excellent localization support
  - Hailuo: Fast video generation with good quality-speed balance
  - Kling: Kuaishou's video generation model
- **Image Generation**: Generate images from text descriptions with various artistic styles
  - GPT-4o: OpenAI's multimodal model for image generation
  - Nano Banana: Google's image model with ultra-high character consistency
  - Seedream: ByteDance's intelligent visual reasoning model
  - Wan: Alibaba's visual model for high-quality and expressive image generation
  - Flux: High-quality photorealistic and artistic image generation
  - Imagen: Google's text-to-image model
  - Ideogram: Specialized in text rendering and precise composition
- **Music Generation**: Create original music and audio from text descriptions
  - MiniMax Music: AI music generation with support for custom lyrics and text-to-music conversion
- **AI Agent Integration**: Build intelligent workflows that combine multiple AI generation capabilities for automated content creation pipelines

## Getting API Key

1. Visit https://monet.vision to register an account
2. After login, go to https://monet.vision/skills/keys to create an API Key
3. Configure the API Key in environment variables or code

If you don't have an API Key, ask your owner to apply at monet.vision.

## Quick Start

### Create a Video Generation Task

```bash
curl -X POST https://monet.vision/api/v1/tasks/async \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MONET_API_KEY" \
  -d '{
    "type": "video",
    "input": {
      "model": "sora-2",
      "prompt": "A cat running in the park",
      "duration": 5,
      "aspect_ratio": "16:9"
    },
    "idempotency_key": "unique-key-123"
  }'
```

> ⚠️ **Important**: `idempotency_key` is **required**. Use a unique value (e.g., UUID) to prevent duplicate task creation if the request is retried.

Response:

```json
{
  "id": "task_abc123",
  "status": "pending",
  "type": "video",
  "created_at": "2026-02-27T10:00:00Z"
}
```

### Get Task Status and Result

Task processing is asynchronous. You need to poll the task status until it becomes `success` or `failed`. **Recommended polling interval: 5 seconds**.

```bash
curl https://monet.vision/api/v1/tasks/task_abc123 \
  -H "Authorization: Bearer $MONET_API_KEY"
```

Response when completed:

```json
{
  "id": "task_abc123",
  "status": "success",
  "type": "video",
  "outputs": [
    {
      "model": "sora-2",
      "status": "success",
      "progress": 100,
      "url": "https://files.monet.vision/..."
    }
  ],
  "created_at": "2026-02-27T10:00:00Z",
  "updated_at": "2026-02-27T10:01:30Z"
}
```

**Example: Poll until completion**

```typescript
const TASK_ID = "task_abc123";
const MONET_API_KEY = process.env.MONET_API_KEY;

async function pollTask() {
  while (true) {
    const response = await fetch(
      `https://monet.vision/api/v1/tasks/${TASK_ID}`,
      {
        headers: {
          Authorization: `Bearer ${MONET_API_KEY}`,
        },
      },
    );

    const data = await response.json();
    const status = data.status;

    if (status === "success") {
      console.log("Task completed successfully!");
      console.log(JSON.stringify(data, null, 2));
      break;
    } else if (status === "failed") {
      console.log("Task failed!");
      console.log(JSON.stringify(data, null, 2));
      break;
    } else {
      console.log(`Task status: ${status}, waiting...`);
      await new Promise((resolve) => setTimeout(resolve, 5000)); // Wait 5 seconds
    }
  }
}

pollTask();
```

## Supported Models

### Video Generation

#### Sora (OpenAI)

**sora-2** - Sora 2

_OpenAI latest video generation model_

- 🎯 **Use Cases**: Video projects requiring OpenAI's latest technology
- ⏱️ **Duration**: 10-15 seconds
- 🎵 **Features**: Audio generation support, reference image support

```typescript
{
  model: "sora-2",
  prompt: string,                // Required
  images?: string[],             // Optional: Reference images
  duration?: 10 | 15,           // Optional, default: 10
  aspect_ratio?: "16:9" | "9:16"
}
```

**sora-2-pro** - Sora 2 Pro

_Perfect quality for cinematic scenes_

- 🎯 **Use Cases**: Professional film, advertising, and high-end production
- ⏱️ **Duration**: 15-25 seconds
- 🎵 **Features**: Audio generation support, reference image support

```typescript
{
  model: "sora-2-pro",
  prompt: string,
  images?: string[],
  duration?: 15 | 25,           // Optional, default: 15
  aspect_ratio?: "16:9" | "9:16"
}
```

#### Veo (Google)

**veo-3-1-fast** - Google Veo 3.1 Fast

_Ultra-fast video generation_

- 🎯 **Use Cases**: Video projects requiring fast generation
- ⏱️ **Duration**: 8 seconds
- 📺 **Resolution**: 1080p with audio generation support

```typescript
{
  model: "veo-3-1-fast",
  prompt: string,
  images?: string[],             // Reference images
  aspect_ratio?: "16:9" | "9:16"
}
```

**veo-3-1** - Google Veo 3.1

_Advanced AI video with sound_

- 🎯 **Use Cases**: Professional-grade video production
- ⏱️ **Duration**: 8 seconds
- 📺 **Resolution**: 1080p with audio generation support

```typescript
{
  model: "veo-3-1",
  prompt: string,
  images?: string[],
  aspect_ratio?: "16:9" | "9:16"
}
```

**veo-3-fast** - Google Veo 3 Fast

_30% faster than standard Veo 3_

- 🎯 **Use Cases**: Video projects requiring rapid iteration
- ⏱️ **Duration**: 8 seconds
- 📺 **Resolution**: 1080p, supports negative prompts

```typescript
{
  model: "veo-3-fast",
  prompt: string,
  images?: string[],
  negative_prompt?: string       // Specify unwanted content
}
```

**veo-3** - Google Veo 3

_High-quality video generation_

- 🎯 **Use Cases**: Standard high-quality video production
- ⏱️ **Duration**: 8 seconds
- 📺 **Resolution**: 1080p, supports negative prompts

```typescript
{
  model: "veo-3",
  prompt: string,
  images?: string[],
  negative_prompt?: string
}
```

#### Wan

**wan-2-6** - Wan 2.6

_Multi-shot and automatic audio_

- 🎯 **Use Cases**: Video production requiring multi-shot switching
- ⏱️ **Duration**: 5-15 seconds
- 📺 **Resolution**: 720p-1080p with audio generation support

```typescript
{
  model: "wan-2-6",
  prompt: string,
  images?: string[],
  duration?: 5 | 10 | 15,
  resolution?: "720p" | "1080p",
  aspect_ratio?: "16:9" | "9:16" | "4:3" | "3:4" | "1:1",
  shot_type?: "single" | "multi"  // Single/multi-shot switching
}
```

**wan-2-5** - Wan 2.5

_Supports automatic audio generation_

- 🎯 **Use Cases**: Quickly generating videos with audio
- ⏱️ **Duration**: 5-10 seconds
- 📺 **Resolution**: 480p-1080p with audio support

```typescript
{
  model: "wan-2-5",
  prompt: string,
  images?: string[],
  duration?: 5 | 10,
  resolution?: "480p" | "720p" | "1080p",
  aspect_ratio?: "16:9" | "9:16" | "4:3" | "3:4" | "1:1"
}
```

**wan-2-2-flash** - Wan 2.2 Flash

_Instruction understanding, controllable camera movement_

- 🎯 **Use Cases**: Scenarios requiring precise camera movement control
- ⏱️ **Duration**: 5-10 seconds
- 📺 **Resolution**: 480p-1080p

```typescript
{
  model: "wan-2-2-flash",
  prompt: string,
  images?: string[],
  duration?: 5 | 10,
  resolution?: "480p" | "720p" | "1080p",
  negative_prompt?: string
}
```

**wan-2-2**