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
- After login, go to https://monet.vision/skills/keys to create an API Key
- 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
CODEBLOCK0
⚠️ Important: idempotency_key is required. Use a unique value (e.g., UUID) to prevent duplicate task creation if the request is retried.
Response:
CODEBLOCK1
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.
CODEBLOCK2
Response when completed:
CODEBLOCK3
Example: Poll until completion
CODEBLOCK4
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
CODEBLOCK5
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
CODEBLOCK6
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
CODEBLOCK7
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
CODEBLOCK8
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
CODEBLOCK9
veo-3 - Google Veo 3
High-quality video generation
- - 🎯 Use Cases: Standard high-quality video production
- ⏱️ Duration: 8 seconds
- 📺 Resolution: 1080p, supports negative prompts
CODEBLOCK10
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
CODEBLOCK11
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
CODEBLOCK12
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
CODEBLOCK13
wan-2-2 - Wan 2.2
Excellent image details, strong motion stability
- - 🎯 Use Cases: Video production requiring high stability
- ⏱️ Duration: 5-10 seconds
- 📺 Resolution: 480p-1080p
CODEBLOCK14
Kling
kling-2-6 - Kling 2.6
Cinematic videos and audio
- - 🎯 Use Cases: Cinematic video production
- ⏱️ Duration: 5-10 seconds
- ✨ Features: Strong visual realism, audio generation support
CODEBLOCK15
kling-2-5 - Kling 2.5 Turbo
Smooth motion, stronger consistency
- - 🎯 Use Cases: Video production requiring high consistency
- ⏱️ Duration: 5-10 seconds
- ✨ Features: Supports negative prompts
CODEBLOCK16
kling-v2-1-master - Kling 2.1 Master
Strong visual realism with enhanced features
- - 🎯 Use Cases: Professional-grade high-quality video production
- ⏱️ Duration: 5-10 seconds
- ✨ Features: Strength adjustment support, negative prompts
CODEBLOCK17
kling-v2-1 - Kling 2.1
Strong visual realism
- - 🎯 Use Cases: High-realism video production
- ⏱️ Duration: 5-10 seconds
- ✨ Features: Strength adjustment, negative prompts
CODEBLOCK18
kling-v2 - Kling 2.0
Excellent aesthetics
- - 🎯 Use Cases: Artistic creation and aesthetically-oriented videos
- ⏱️ Duration: 5-10 seconds
- ✨ Features: Strength adjustment, negative prompts
CODEBLOCK19
Hailuo
hailuo-2-3 - Hailuo 2.3
Excellent body movements and physics performance
- - 🎯 Use Cases: Videos requiring realistic physics effects
- ⏱️ Duration: 6-10 seconds
- 📺 Resolution: 768p-1080p, extreme physics simulations
CODEBLOCK20
hailuo-2-3-fast - Hailuo 2.3 Fast
Fast generation speed
- - 🎯 Use Cases: Projects requiring rapid iteration
- ⏱️ Duration: 6-10 seconds
- 📺 Resolution: 768p-1080p
CODEBLOCK21
hailuo-02 - Hailuo 02
Extreme physics simulations
- - 🎯 Use Cases: Scenarios requiring accurate physics simulation
- ⏱️ Duration: 6-10 seconds
- 📺 Resolution: 768p-1080p
CODEBLOCK22
hailuo-01-live2d - Hailuo 01 Live2d
Hailuo Live2D model
- - 🎯 Use Cases: 2D character animation production
- ✨ Features: Suitable for 2D character animation
CODEBLOCK23
hailuo-01 - Hailuo 01
Highest video quality
- - 🎯 Use Cases: Video production requiring ultimate quality
- ✨ Features: Suitable for high-quality needs
CODEBLOCK24
Doubao Seedance
doubao-seedance-1-5-pro - Seedance 1.5 Pro
Pro-grade audio-visual sync
- - 🎯 Use Cases: Professional production requiring audio-visual sync
- ⏱️ Duration: 4-12 seconds
- 📺 Resolution: 480p-720p with audio generation support
CODEBLOCK25
doubao-seedance-1-0-pro-fast - Seedance 1.0 Pro Fast
Premium quality & unbeatable efficiency
- - 🎯 Use Cases: Scenarios requiring fast high-quality output
- ⏱️ Duration: 2-12 seconds
- 📺 Resolution: 720p-1080p, ByteDance's next-gen AI video model
CODEBLOCK26
doubao-seedance-1-0-pro - Seedance 1.0 Pro
Stable motion performance
- - 🎯 Use Cases: Video production requiring stable motion
- ⏱️ Duration: 5-10 seconds
- 📺 Resolution: 480p-1080p
CODEBLOCK27
doubao-seedance-1-0-lite - Seedance 1.0 Lite
Precise semantic understanding
- - 🎯 Use Cases: Scenarios requiring precise semantic understanding
- ⏱️ Duration: 5-10 seconds
- 📺 Resolution: 480p-1080p
CODEBLOCK28
Special Features
kling-motion-control - Kling Motion Control
Precision motion control via video references
- - 🎯 Use Cases: Scenarios requiring motion replication from reference videos
- ⏱️ Duration: 3-30 seconds
- 📺 Resolution: 720p/1080p with audio generation support
- 💰 Pricing: 720p: 8 credits/s, 1080p: 15 credits/s
CODEBLOCK29
runway-act-two - Runway Act Two
Runway Next-Generation Motion Capture Model
- - 🎯 Use Cases: Capturing motion from videos and applying to new characters
- ⏱️ Duration: 3-30 seconds
- ✨ Features: Motion transfer support
- 💰 Pricing: 10 credits/second
CODEBLOCK30
wan-animate-mix - Wan Animate Mix (Standard)
Perfect for character replacement scenarios
- - 🎯 Use Cases: Video character replacement
- ⏱️ Duration: 3-30 seconds
- ✨ Features: Replace characters in videos with specified image characters
- 💰 Pricing: 10 credits/second
CODEBLOCK31
wan-animate-mix-pro - Wan Animate Mix Pro (Professional)
High animation fluidity with better results
- - 🎯 Use Cases: Professional-grade video character replacement
- ⏱️ Duration: 3-30 seconds
- ✨ Features: Higher quality character replacement effects
- 💰 Pricing: 20 credits/second
CODEBLOCK32
wan-animate-move - Wan Animate Move (Standard)
Replicate dance and challenging body movements
- - 🎯 Use Cases: Motion capture and transfer
- ⏱️ Duration: 3-30 seconds
- ✨ Features: Apply motion from reference videos to target images
- 💰 Pricing: 10 credits/second
CODEBLOCK33
wan-animate-move-pro - Wan Animate Move Pro (Professional)
High animation fluidity with better results
- - 🎯 Use Cases: Professional-grade motion capture and transfer
- ⏱️ Duration: 3-30 seconds
- ✨ Features: Higher quality motion transfer effects
- 💰 Pricing: 20 credits/second
CODEBLOCK34
Image Generation
GPT (OpenAI)
gpt-4o - GPT 4o
Accurate, realistic output
- - 🎯 Use Cases: High-quality, photorealistic image generation
- ✨ Features: Supports multiple reference images, multiple aspect ratios, customizable style
CODEBLOCK35
gpt-image-1-5 - GPT Image 1.5
True-color precision rendering
- - 🎯 Use Cases: Professional image generation requiring color accuracy
- ✨ Features: Supports up to 10 reference images, adjustable quality
CODEBLOCK36
Nano Banana (Google)
nano-banana-1 - Google Nano Banana
Ultra-high character consistency
- - 🎯 Use Cases: Image series requiring consistent character appearance
- ✨ Features: Supports up to 5 reference images, multiple aspect ratio options
CODEBLOCK37
nano-banana-1-pro - Nano Banana Pro
Google's flagship generation model
- - 🎯 Use Cases: Professional-grade high-quality image generation
- ✨ Features: Supports 1K-4K resolution, up to 14 reference images, ultra-wide 21:9
CODEBLOCK38
nano-banana-2 - Nano Banana 2
Google Gemini latest model
- - 🎯 Use Cases: Latest technology for high-quality image generation
- ✨ Features: Supports 1K-4K resolution, up to 14 reference images, ultra-wide 8:1 ratio
CODEBLOCK39
Wan
wan-i-2-6 - Wan 2.6
High-quality and expressive
- - 🎯 Use Cases: Creative image generation requiring high expressiveness
- ✨ Features: Supports up to 4 reference images, ultra-wide 21:9
CODEBLOCK40
wan-2-5 - Wan 2.5
Fast, creative image generation
- - 🎯 Use Cases: Quick creation and iteration
- ✨ Features: Supports up to 2 reference images, ultra-wide 21:9
CODEBLOCK41
Seedream (ByteDance)
seedream-5-0 - Seedream 5.0 Lite
Intelligent visual reasoning
- - 🎯 Use Cases: Complex scenarios requiring intelligent understanding and reasoning
- ✨ Features: 2K-3K resolution, up to 14 reference images, ultra-wide 21:9
CODEBLOCK42
seedream-4-5 - Seedream 4.5
ByteDance's 4K image model
- - 🎯 Use Cases: High-resolution professional image generation
- ✨ Features: 2K-4K resolution, up to 14 reference images, ultra-wide 21:9
CODEBLOCK43
seedream-4-0 - Seedream 4.0
Support images with cohesive styles
- - 🎯 Use Cases: Image series requiring consistent style
- ✨ Features: Supports up to 10 reference images
CODEBLOCK44
Flux (Black Forest Labs)
flux-2-dev - Flux.2 Dev
Photorealistic output
- - 🎯 Use Cases: Image generation requiring high photorealism
- ✨ Features: Model by Black Forest Labs, multiple aspect ratio options
CODEBLOCK45
flux-kontext-pro - Flux Kontext Pro
Perfect for editing, compositing
- - 🎯 Use Cases: Professional image editing and compositing work
- ✨ Features: Supports reference images, customizable style
CODEBLOCK46
flux-kontext-max - Flux Kontext Max
Excellent for prompt accuracy
- - 🎯 Use Cases: Scenarios requiring precise control of generation results
- ✨ Features: Supports reference images, customizable style
CODEBLOCK47
flux-1-schnell - Flux Schnell
Suitable for simple basic scenes
- - 🎯 Use Cases: Quick prototyping and simple scenarios
- ✨ Features: Fast generation speed
CODEBLOCK48
Imagen (Google)
imagen-3-0 - Imagen 3.0
Fast, high-quality results
- - 🎯 Use Cases: Fast high-quality image generation
- ✨ Features: Google's advanced image model, customizable style
CODEBLOCK49
imagen-4-0 - Imagen 4.0
Google's latest generation model
- - 🎯 Use Cases: High-quality images requiring latest technology
- ✨ Features: Higher quality and precision, customizable style
CODEBLOCK50
Ideogram
ideogram-v2 - Ideogram V2
Highly recommended for text editing
- - 🎯 Use Cases: Scenarios requiring text in images
- ✨ Features: Excellent text rendering performance
CODEBLOCK51
ideogram-v3 - Ideogram V3
Outstanding design capabilities
- - 🎯 Use Cases: First choice for designers and creative professionals
- ✨ Features: Better text rendering and typography
CODEBLOCK52
Stability AI
stability-1-0 - Stability 1.0
Perfect for generating detailed images
- - 🎯 Use Cases: Image generation requiring fine control and high detail
- ✨ Features: Supports negative prompts, customizable style
CODEBLOCK53
Music Generation
minimax-music - MiniMax Music
AI music generation from text with custom lyrics support
- - 🎯 Provider: MiniMax
- ✨ Features: Text-to-music conversion, supports custom lyrics
- 🎵 Use Cases: Music creation from text descriptions or lyrics
CODEBLOCK54
API Reference
Create Task (Async)
POST /api/v1/tasks/async - Create an async task. Returns immediately with task ID.
Request:
CODEBLOCK55
⚠️ Important: idempotency_key is required. Use a unique value (e.g., UUID) to prevent duplicate task creation if the request is retried.
Response:
CODEBLOCK56
Create Task (Streaming)
POST /api/v1/tasks/sync - Create a task with SSE streaming. Waits for completion and streams progress.
Request:
CODEBLOCK57
Get Task
GET /api/v1/tasks/{taskId} - Get task status and result.
Request:
CODEBLOCK58
Response:
CODEBLOCK59
List Tasks
GET /api/v1/tasks/list - List tasks with pagination.
Request:
CODEBLOCK60
Response:
CODEBLOCK61
Upload File
POST /api/v1/files - Upload a file to get an online access URL.
📁 File Storage: Uploaded files are stored for 24 hours and will be automatically deleted after expiration.
Request:
CODEBLOCK62
Use Cases:
- - Upload reference images for video/image generation tasks
- Upload video files for video processing
- Upload audio files for music tasks
- Get temporary online URLs for file sharing
Response:
CODEBLOCK63
Configuration
Environment Variables
CODEBLOCK64
Authentication
All API requests require authentication via the Authorization header:
CODEBLOCK65
Monet AI 技能
专为AI代理设计的综合性AI内容生成API。Monet AI提供对最先进AI生成模型的统一访问,涵盖视频(Sora、Veo、豆包Seedance、万相、海螺、可灵)、图像(GPT-4o、Nano Banana、Seedream、Flux、Imagen、Ideogram)和音乐(MiniMax Music)生成。构建结合多种AI能力的智能工作流,实现自动化内容创作管线。
使用场景
在以下情况使用此技能:
- - 视频生成:使用最先进模型从文本提示创建AI生成视频
- Sora:OpenAI的视频生成模型,用于高质量、逼真的视频
- Veo:Google的视频生成模型
- 豆包Seedance:字节跳动的AI视频模型,支持音视频同步
- 万相:阿里巴巴的视频生成模型,本地化支持出色
- 海螺:快速视频生成,质量与速度平衡良好
- 可灵:快手的视频生成模型
- - 图像生成:从文本描述生成具有各种艺术风格的图像
- GPT-4o:OpenAI的多模态图像生成模型
- Nano Banana:Google的图像模型,角色一致性极高
- Seedream:字节跳动的智能视觉推理模型
- 万相:阿里巴巴的视觉模型,用于高质量和富有表现力的图像生成
- Flux:高质量逼真和艺术图像生成
- Imagen:Google的文本到图像模型
- Ideogram:专注于文本渲染和精确构图
- MiniMax Music:AI音乐生成,支持自定义歌词和文本到音乐转换
- - AI代理集成:构建结合多种AI生成能力的智能工作流,实现自动化内容创作管线
获取API密钥
- 1. 访问 https://monet.vision 注册账号
- 登录后,前往 https://monet.vision/skills/keys 创建API密钥
- 在环境变量或代码中配置API密钥
如果没有API密钥,请让所有者前往monet.vision申请。
快速开始
创建视频生成任务
bash
curl -X POST https://monet.vision/api/v1/tasks/async \
-H Content-Type: application/json \
-H Authorization: Bearer $MONETAPIKEY \
-d {
type: video,
input: {
model: sora-2,
prompt: 一只在公园里奔跑的猫,
duration: 5,
aspect_ratio: 16:9
},
idempotency_key: unique-key-123
}
⚠️ 重要:idempotency_key 是必需的。使用唯一值(如UUID)防止请求重试时重复创建任务。
响应:
json
{
id: task_abc123,
status: pending,
type: video,
created_at: 2026-02-27T10:00:00Z
}
获取任务状态和结果
任务处理是异步的。需要轮询任务状态,直到变为 success 或 failed。推荐轮询间隔:5秒。
bash
curl https://monet.vision/api/v1/tasks/task_abc123 \
-H Authorization: Bearer $MONETAPIKEY
完成时的响应:
json
{
id: task_abc123,
status: success,
type: video,
outputs: [
{
model: sora-2,
status: success,
progress: 100,
url: https://files.monet.vision/...
}
],
created_at: 2026-02-27T10:00:00Z,
updated_at: 2026-02-27T10:01:30Z
}
示例:轮询直到完成
typescript
const TASKID = taskabc123;
const MONETAPIKEY = process.env.MONETAPIKEY;
async function pollTask() {
while (true) {
const response = await fetch(
https://monet.vision/api/v1/tasks/${TASK_ID},
{
headers: {
Authorization: Bearer ${MONETAPIKEY},
},
},
);
const data = await response.json();
const status = data.status;
if (status === success) {
console.log(任务成功完成!);
console.log(JSON.stringify(data, null, 2));
break;
} else if (status === failed) {
console.log(任务失败!);
console.log(JSON.stringify(data, null, 2));
break;
} else {
console.log(任务状态:${status},等待中...);
await new Promise((resolve) => setTimeout(resolve, 5000)); // 等待5秒
}
}
}
pollTask();
支持的模型
视频生成
Sora(OpenAI)
sora-2 - Sora 2
OpenAI最新视频生成模型
- - 🎯 使用场景:需要OpenAI最新技术的视频项目
- ⏱️ 时长:10-15秒
- 🎵 特性:支持音频生成、参考图像
typescript
{
model: sora-2,
prompt: string, // 必需
images?: string[], // 可选:参考图像
duration?: 10 | 15, // 可选,默认:10
aspect_ratio?: 16:9 | 9:16
}
sora-2-pro - Sora 2 Pro
电影级场景的完美画质
- - 🎯 使用场景:专业电影、广告和高端制作
- ⏱️ 时长:15-25秒
- 🎵 特性:支持音频生成、参考图像
typescript
{
model: sora-2-pro,
prompt: string,
images?: string[],
duration?: 15 | 25, // 可选,默认:15
aspect_ratio?: 16:9 | 9:16
}
Veo(Google)
veo-3-1-fast - Google Veo 3.1 Fast
超快速视频生成
- - 🎯 使用场景:需要快速生成的视频项目
- ⏱️ 时长:8秒
- 📺 分辨率:1080p,支持音频生成
typescript
{
model: veo-3-1-fast,
prompt: string,
images?: string[], // 参考图像
aspect_ratio?: 16:9 | 9:16
}
veo-3-1 - Google Veo 3.1
带声音的高级AI视频
- - 🎯 使用场景:专业级视频制作
- ⏱️ 时长:8秒
- 📺 分辨率:1080p,支持音频生成
typescript
{
model: veo-3-1,
prompt: string,
images?: string[],
aspect_ratio?: 16:9 | 9:16
}
veo-3-fast - Google Veo 3 Fast
比标准Veo 3快30%
- - 🎯 使用场景:需要快速迭代的视频项目
- ⏱️ 时长:8秒
- 📺 分辨率:1080p,支持负面提示
typescript
{
model: veo-3-fast,
prompt: string,
images?: string[],
negative_prompt?: string // 指定不想要的内容
}
veo-3 - Google Veo 3
高质量视频生成
- - 🎯 使用场景:标准高质量视频制作
- ⏱️ 时长:8秒
- 📺 分辨率:1080p,支持负面提示
typescript
{
model: veo-3,
prompt: string,
images?: string[],
negative_prompt?: string
}
万相
wan-2-6 - 万相 2.6
多镜头和自动音频
- - 🎯 使用场景:需要多镜头切换的视频制作
- ⏱️ 时长:5-15秒
- 📺 分辨率:720p-1080p,支持音频生成
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