@felores/kie-ai-mcp-server 1.2.2 → 1.7.1

package/README.md

@@ -1,34 +1,96 @@
 # Kie.ai MCP Server
 
-An MCP (Model Context Protocol) server that provides access to Kie.ai's AI APIs including Nano Banana image generation/editing and Veo3 video generation.
-
-## Features
-
-- **Nano Banana Image Generation**: Text-to-image generation using Google's Gemini 2.5 Flash Image Preview
-- **Nano Banana Image Editing**: Natural language image editing with up to 10 input images
-- **Nano Banana Image Upscaling**: Upscale images 1-4x with optional face enhancement
-- **Veo3 Video Generation**: Professional-quality video generation with text-to-video and image-to-video capabilities
-- **1080p Video Upgrade**: Get high-definition versions of Veo3 videos
-- **Suno Music Generation**: AI-powered music creation with multiple models (V3_5, V4, V4_5, V4_5PLUS, V5)
-- **Task Management**: SQLite-based task tracking with status polling
-- **Smart Endpoint Routing**: Automatic detection of task types for status checking
-- **Error Handling**: Comprehensive error handling and validation
-
-## Prerequisites
-
-- Node.js 18+ 
-- Kie.ai API key from https://kie.ai/api-key
-
-## Installation
-
-### From NPM
-
+**Access multiple AI models with one API. Generate videos, images, music, and audio.**
+
+Access the world's best AI models through a single, developer-friendly API. Generate stunning videos, images, music, and audio at **lower cost than Fal.ai** with 99.9% uptime and 24/7 support.
+
+## Why Choose Kie.ai MCP Server?
+
+| Feature | Kie.ai | Fal.ai | Replicate.com |
+|---------|--------|--------|---------------|
+| **Pricing** | Lower | Higher | Higher |
+| **Models** | All-in-one API | Limited | Separate APIs |
+| **Uptime** | 99.9% | Lower | 99.5% |
+| **Support** | 24/7 | Limited | Business hours |
+| **API Keys** | One key | Multiple keys | Multiple keys |
+| **Free Trial** | Yes | Limited | Limited |
+
+### 🚀 **All AI Models in One API**
+- **Google Veo 3**: Cinematic video generation with synchronized audio and 1080p output
+- **Runway Aleph**: Advanced video editing with object removal and style transfer
+- **Suno V5**: Professional music generation with realistic vocals up to 8 minutes
+- **Nano Banana**: Lightning-fast image generation and editing
+- **ElevenLabs**: Studio-quality text-to-speech and sound effects
+- **ByteDance Seedance**: High-quality video with text-to-video and image-to-video
+
+### 💰 **Affordable Pricing**
+Pay-as-you-go credit system means you only pay for what you use. Good for startups and enterprises looking to reduce AI costs.
+
+### ⚡ **Fast & Reliable**
+- **99.9% uptime**
+- **25.2s average response time**
+- Low latency for applications
+- High concurrency support
+
+### 🔒 **Secure**
+Your data is protected with encryption. We prioritize privacy and do not expose your information.
+
+## What You Can Build
+
+### 🎬 **Video Generation**
+Generate videos from text or images. Use for:
+- Social media content
+- Marketing materials  
+- Product demonstrations
+- Creative projects
+
+### 🎨 **Image Generation**
+Create images, edit existing ones, and upscale with AI. Use for:
+- Content creation
+- Product photography
+- Artistic projects
+- Design mockups
+
+### 🎵 **Music Generation**
+Generate music tracks with vocals. Use for:
+- Background music for videos
+- Podcast intros/outros
+- Game soundtracks
+- Commercial projects
+
+### 🎤 **Audio Generation**
+Voiceovers and sound effects. Use for:
+- Narration and voiceovers
+- Podcast production
+- Game audio
+- Accessibility features
+
+## Key Features
+
+- **🎯 One API Key**: Access all models with one credential
+- **🔄 Task Management**: Built-in SQLite database for tracking generations
+- **📱 Smart Routing**: Automatic endpoint detection and status monitoring
+- **🛡️ Error Handling**: Validation and error recovery
+- **⚙️ Flexible Parameters**: Control outputs with parameters
+- **📊 Persistent Storage**: Tasks survive server restarts
+- **🎛️ Quality Control**: Choose between speed (lite) and quality (pro) modes
+- **🌐 Multilingual Support**: Text-to-speech in multiple languages
+
+## Quick Start
+
+### 🎯 Get Your Free API Key
+1. Visit [Kie.ai API Key](https://kie.ai/api-key) to get your free API key
+2. **Try any model for free** in the AI Playground before committing
+3. Choose the flexible pricing plan that fits your needs
+
+### 📦 Installation
+
+#### Option 1: Install from NPM (Recommended)
 ```bash
 npm install -g @felores/kie-ai-mcp-server
 ```
 
-### From Source
-
+#### Option 2: Install from Source
 ```bash
 # Clone the repository
 git clone https://github.com/felores/kie-ai-mcp-server.git
@@ -41,6 +103,27 @@ npm install
 npm run build
 ```
 
+### ⚙️ Configuration
+
+Create your environment file:
+```bash
+# Required: Your API key from https://kie.ai/api-key
+export KIE_AI_API_KEY="your_api_key_here"
+
+# Optional: Custom settings
+export KIE_AI_BASE_URL="https://api.kie.ai/api/v1"  # Default
+export KIE_AI_TIMEOUT="60000"                        # Default: 60 seconds
+export KIE_AI_DB_PATH="./tasks.db"                   # Default: local database
+export KIE_AI_CALLBACK_URL="https://your-domain.com/webhook"  # For notifications
+```
+
+### 🚀 Start Generating
+You're ready to create amazing AI content! The server will automatically:
+- Track all your generations in a local database
+- Handle task status and completion notifications
+- Route requests to the optimal AI models
+- Provide detailed error messages and guidance
+
 ## Configuration
 
 ### Environment Variables
@@ -88,7 +171,35 @@ Or if installed globally:
 
 ## Available Tools
 
-### 1. `nano_banana_generate`
+### 1. `list_tasks`
+List recent tasks with their status.
+
+**Parameters:**
+- `limit` (integer, optional): Max tasks to return (default: 20, max: 100)
+- `status` (string, optional): Filter by status ("pending", "processing", "completed", "failed")
+
+**Example:**
+```json
+{
+  "limit": 10,
+  "status": "completed"
+}
+```
+
+### 2. `get_task_status`
+Check the status of a generation task.
+
+**Parameters:**
+- `task_id` (string, required): Task ID to check
+
+**Example:**
+```json
+{
+  "task_id": "281e5b0*********************f39b9"
+}
+```
+
+### 3. `nano_banana_generate`
 Generate images using Nano Banana.
 
 **Parameters:**
@@ -105,7 +216,7 @@ Generate images using Nano Banana.
 }
 ```
 
-### 2. `nano_banana_edit`
+### 4. `nano_banana_edit`
 Edit images using natural language prompts.
 
 **Parameters:**
@@ -124,7 +235,7 @@ Edit images using natural language prompts.
 }
 ```
 
-### 3. `nano_banana_upscale`
+### 5. `nano_banana_upscale`
 Upscale images with optional face enhancement.
 
 **Parameters:**
@@ -141,7 +252,7 @@ Upscale images with optional face enhancement.
 }
 ```
 
-### 4. `veo3_generate_video`
+### 6. `veo3_generate_video`
 Generate videos using Veo3.
 
 **Parameters:**
@@ -166,19 +277,6 @@ Generate videos using Veo3.
 }
 ```
 
-### 5. `get_task_status`
-Check the status of a generation task.
-
-**Parameters:**
-- `task_id` (string, required): Task ID to check
-
-### 6. `list_tasks`
-List recent tasks with their status.
-
-**Parameters:**
-- `limit` (integer, optional): Max tasks to return (default: 20, max: 100)
-- `status` (string, optional): Filter by status ("pending", "processing", "completed", "failed")
-
 ### 7. `veo3_get_1080p_video`
 Get 1080P high-definition version of a Veo3 video.
 
@@ -195,7 +293,7 @@ Generate music with AI using Suno models.
 - `prompt` (string, required): Description of desired audio content (max 5000 chars for V4_5+, V5; 3000 for V3_5, V4; 500 chars for non-custom mode)
 - `customMode` (boolean, required): Enable advanced parameter customization
 - `instrumental` (boolean, required): Generate instrumental music (no lyrics)
-- `model` (enum, required): AI model version - "V3_5", "V4", "V4_5", "V4_5PLUS", or "V5"
+- `model` (enum, optional): AI model version - "V3_5", "V4", "V4_5", "V4_5PLUS", or "V5" (default: "V5")
 - `callBackUrl` (string, optional): URL to receive task completion updates (uses KIE_AI_CALLBACK_URL environment variable if not provided)
 - `style` (string, optional): Music style/genre (required in custom mode, max 1000 chars for V4_5+, V5; 200 for V3_5, V4)
 - `title` (string, optional): Track title (required in custom mode, max 80 chars)
@@ -222,6 +320,15 @@ With explicit callback URL:
 
 Using environment variable (KIE_AI_CALLBACK_URL):
 ```json
+{
+  "prompt": "A relaxing electronic music track",
+  "customMode": false,
+  "instrumental": false
+}
+```
+
+Using explicit model (overrides default V5):
+```json
 {
   "prompt": "A relaxing electronic music track",
   "customMode": false,
@@ -230,7 +337,325 @@ Using environment variable (KIE_AI_CALLBACK_URL):
 }
 ```
 
-**Note**: In custom mode, `style` and `title` are required. If `instrumental` is false, `prompt` is used as exact lyrics. The `callBackUrl` is optional and will use the `KIE_AI_CALLBACK_URL` environment variable if not provided.
+**Note**: In custom mode, `style` and `title` are required. If `instrumental` is false, `prompt` is used as exact lyrics. The `callBackUrl` is optional and will use the `KIE_AI_CALLBACK_URL` environment variable if not provided. The `model` parameter defaults to "V5" but can be explicitly set to any available version.
+
+### 9. `elevenlabs_tts`
+Generate speech from text using ElevenLabs TTS models (Turbo 2.5 by default, with optional Multilingual v2 support).
+
+**Parameters:**
+- `text` (string, required): The text to convert to speech (max 5000 characters)
+- `model` (enum, optional): TTS model to use - "turbo" (faster, default) or "multilingual" (supports context)
+- `voice` (enum, optional): Voice to use - "Rachel", "Aria", "Roger", "Sarah", "Laura", "Charlie", "George", "Callum", "River", "Liam", "Charlotte", "Alice", "Matilda", "Will", "Jessica", "Eric", "Chris", "Brian", "Daniel", "Lily", "Bill" (default: "Rachel")
+- `stability` (number, optional): Voice stability (0-1, step 0.01, default: 0.5)
+- `similarity_boost` (number, optional): Similarity boost (0-1, step 0.01, default: 0.75)
+- `style` (number, optional): Style exaggeration (0-1, step 0.01, default: 0)
+- `speed` (number, optional): Speech speed (0.7-1.2, step 0.01, default: 1.0)
+- `timestamps` (boolean, optional): Whether to return timestamps for each word (default: false)
+- `previous_text` (string, optional): Text that came before current request (multilingual model only, max 5000 chars)
+- `next_text` (string, optional): Text that comes after current request (multilingual model only, max 5000 chars)
+- `language_code` (string, optional): ISO 639-1 language code for language enforcement (turbo model only, max 500 chars)
+- `callBackUrl` (string, optional): URL to receive task completion updates (uses KIE_AI_CALLBACK_URL environment variable if not provided)
+
+**Examples:**
+
+Basic TTS generation (uses Turbo model by default):
+```json
+{
+  "text": "Hello, this is a test of the ElevenLabs text-to-speech system.",
+  "voice": "Rachel"
+}
+```
+
+Fast generation with language enforcement (Turbo model):
+```json
+{
+  "text": "Bonjour, comment allez-vous?",
+  "voice": "Rachel",
+  "model": "turbo",
+  "language_code": "fr"
+}
+```
+
+Advanced voice controls with context (Multilingual model):
+```json
+{
+  "text": "This is the second part of our conversation.",
+  "voice": "Roger",
+  "model": "multilingual",
+  "stability": 0.8,
+  "similarity_boost": 0.9,
+  "previous_text": "This is the first part of our conversation.",
+  "next_text": "This is the third part of our conversation."
+}
+```
+
+**Model Comparison:**
+- **Turbo 2.5** (default): Faster generation (15-60 seconds), supports language enforcement with `language_code`
+- **Multilingual v2**: Supports context with `previous_text`/`next_text`, generation takes 30-120 seconds
+
+**Note**: The `callBackUrl` is optional and will use the `KIE_AI_CALLBACK_URL` environment variable if not provided. Choose Turbo model for speed and language enforcement, or Multilingual model for context-aware speech generation.
+
+### 10. `elevenlabs_ttsfx`
+Generate sound effects from text descriptions using ElevenLabs Sound Effects v2 model.
+
+**Parameters:**
+- `text` (string, required): Description of the sound effect to generate (max 5000 chars)
+- `loop` (boolean, optional): Whether to create a sound effect that loops smoothly (default: false)
+- `duration_seconds` (number, optional): Duration in seconds (0.5-22, step 0.1). If not specified, optimal duration will be determined from prompt
+- `prompt_influence` (number, optional): How closely to follow the prompt (0-1, step 0.01, default: 0.3). Higher values mean less variation
+- `output_format` (string, optional): Audio output format (default: "mp3_44100_192")
+  - MP3 options: `mp3_22050_32`, `mp3_44100_32`, `mp3_44100_64`, `mp3_44100_96`, `mp3_44100_128`, `mp3_44100_192`
+  - PCM options: `pcm_8000`, `pcm_16000`, `pcm_22050`, `pcm_24000`, `pcm_44100`, `pcm_48000`
+  - Telephony: `ulaw_8000`, `alaw_8000`
+  - Opus: `opus_48000_32`, `opus_48000_64`, `opus_48000_96`, `opus_48000_128`, `opus_48000_192`
+- `callBackUrl` (string, optional): URL for task completion notifications
+
+**Examples:**
+
+Basic sound effect:
+```json
+{
+  "text": "Rain falling on a tin roof"
+}
+```
+
+Advanced sound effect with custom duration:
+```json
+{
+  "text": "Epic thunderstorm with heavy rain and distant thunder",
+  "duration_seconds": 15.0,
+  "prompt_influence": 0.8,
+  "output_format": "mp3_44100_192"
+}
+```
+
+Looping ambient sound:
+```json
+{
+  "text": "Gentle ocean waves lapping at the shore",
+  "loop": true,
+  "duration_seconds": 10.0
+}
+```
+
+**Key Features:**
+- **High-Quality Audio**: Professional-grade sound effect generation
+- **Flexible Duration**: Control exact length from 0.5 to 22 seconds
+- **Loop Support**: Create seamless looping sound effects
+- **Multiple Formats**: Support for MP3, PCM, Opus, and telephony formats
+- **Prompt Control**: Adjust how closely to follow your description
+
+**Note**: The `callBackUrl` is optional and will use the `KIE_AI_CALLBACK_URL` environment variable if not provided. Sound effects generation typically takes 30-90 seconds depending on complexity.
+
+### 12. `bytedance_seedance_video`
+Generate videos using ByteDance Seedance models (unified tool for both text-to-video and image-to-video).
+
+**Parameters:**
+- `prompt` (string, required): Text prompt for video generation (max 10000 chars)
+- `image_url` (string, optional): URL of input image for image-to-video generation (if not provided, uses text-to-video)
+- `quality` (string, optional): Model quality level (default: "lite")
+  - `lite`: Faster generation with good quality
+  - `pro`: Higher quality with longer generation time
+- `aspect_ratio` (string, optional): Video aspect ratio (default: "16:9")
+  - Options: `1:1`, `9:16`, `16:9`, `4:3`, `3:4`, `21:9`, `9:21`
+- `resolution` (string, optional): Video resolution (default: "720p")
+  - `480p`: Faster generation
+  - `720p`: Balanced quality and speed
+  - `1080p`: Highest quality
+- `duration` (string, optional): Video duration in seconds 2-12 (default: "5")
+- `camera_fixed` (boolean, optional): Whether to fix camera position (default: false)
+- `seed` (integer, optional): Random seed for reproducible results (default: -1 for random)
+- `enable_safety_checker` (boolean, optional): Enable content safety checking (default: true)
+- `end_image_url` (string, optional): URL of ending image (image-to-video only)
+- `callBackUrl` (string, optional): URL for task completion notifications
+
+**Examples:**
+
+Text-to-video (lite quality):
+```json
+{
+  "prompt": "A serene sailing boat gently sways in the harbor at dawn, surrounded by soft Impressionist hues of pink and orange",
+  "quality": "lite",
+  "aspect_ratio": "16:9",
+  "duration": "5"
+}
+```
+
+Image-to-video (pro quality):
+```json
+{
+  "prompt": "A golden retriever dashing through shallow surf at the beach, splashes frozen in time",
+  "image_url": "https://example.com/golden-retriever.jpg",
+  "quality": "pro",
+  "resolution": "1080p",
+  "duration": "6",
+  "camera_fixed": false
+}
+```
+
+Video with specific ending frame:
+```json
+{
+  "prompt": "A traveler crosses an endless desert toward a glowing archway",
+  "image_url": "https://example.com/desert-traveler.jpg",
+  "end_image_url": "https://example.com/archway.jpg",
+  "quality": "pro",
+  "duration": "8"
+}
+```
+
+**Key Features:**
+- **Unified Interface**: Single tool for both text-to-video and image-to-video
+- **Smart Mode Detection**: Automatically detects mode based on presence of `image_url`
+- **Quality Options**: Lite for speed, Pro for quality
+- **Flexible Aspect Ratios**: Support for vertical, horizontal, and square formats
+- **Camera Control**: Option to fix camera position for stable shots
+- **Reproducible Results**: Seed control for consistent output
+- **Safety Features**: Built-in content safety checking
+
+**Note**: The `callBackUrl` is optional and will use the `KIE_AI_CALLBACK_URL` environment variable if not provided. Video generation typically takes 2-5 minutes depending on quality and complexity.
+
+### 13. `runway_aleph_video`
+Transform videos using Runway Aleph video-to-video generation with AI-powered editing.
+
+**Parameters:**
+- `prompt` (string, required): Text prompt describing desired video transformation (max 1000 chars)
+- `videoUrl` (string, required): URL of the input video to transform
+- `waterMark` (string, optional): Watermark text to add to the video (max 100 chars, default: "")
+- `uploadCn` (boolean, optional): Whether to upload to China servers (default: false)
+- `aspectRatio` (enum, optional): Output video aspect ratio (default: "16:9")
+  - Options: `16:9`, `9:16`, `4:3`, `3:4`, `1:1`, `21:9`
+- `seed` (integer, optional): Random seed for reproducible results (1-999999)
+- `referenceImage` (string, optional): URL of reference image for style guidance
+- `callBackUrl` (string, optional): URL for task completion notifications
+
+**Examples:**
+
+Basic video transformation:
+```json
+{
+  "prompt": "Transform this video into a cinematic anime style with vibrant colors",
+  "videoUrl": "https://example.com/input-video.mp4",
+  "aspectRatio": "16:9"
+}
+```
+
+Advanced transformation with reference image:
+```json
+{
+  "prompt": "Apply the artistic style of the reference image to this video",
+  "videoUrl": "https://example.com/cooking-video.mp4",
+  "referenceImage": "https://example.com/van-gogh-painting.jpg",
+  "seed": 123456,
+  "waterMark": "My Channel"
+}
+```
+
+Vertical video for social media:
+```json
+{
+  "prompt": "Convert to a dreamy, ethereal style with soft lighting",
+  "videoUrl": "https://example.com/landscape-video.mp4",
+  "aspectRatio": "9:16",
+  "uploadCn": false
+}
+```
+
+**Key Features:**
+- **Video-to-Video Transformation**: Transform existing videos with AI-powered editing
+- **Style Transfer**: Apply artistic styles from text prompts or reference images
+- **Aspect Ratio Control**: Convert between horizontal, vertical, and square formats
+- **Reproducible Results**: Seed control for consistent transformations
+- **Watermark Support**: Add custom watermarks to transformed videos
+- **Reference Guidance**: Use reference images to guide the transformation style
+
+**Note**: The `callBackUrl` is optional and will use the `KIE_AI_CALLBACK_URL` environment variable if not provided. Video-to-video transformation typically takes 3-8 minutes depending on complexity and length.
+
+### 14. `wan_video`
+Generate videos using Alibaba Wan 2.5 models (unified tool for both text-to-video and image-to-video).
+
+**Parameters:**
+- `prompt` (string, required): Text prompt for video generation (max 800 chars)
+- `image_url` (string, optional): URL of input image for image-to-video generation (if not provided, uses text-to-video)
+- `aspect_ratio` (string, optional): Video aspect ratio for text-to-video (default: "16:9")
+  - Options: `16:9`, `9:16`, `1:1`
+- `resolution` (string, optional): Video resolution (default: "1080p")
+  - `720p`: Faster generation
+  - `1080p`: Higher quality
+- `duration` (string, optional): Video duration for image-to-video (default: "5")
+  - Options: `5`, `10` seconds
+- `negative_prompt` (string, optional): Negative prompt to describe content to avoid (max 500 chars, default: "")
+- `enable_prompt_expansion` (boolean, optional): Enable prompt rewriting using LLM (default: true)
+- `seed` (integer, optional): Random seed for reproducible results
+- `callBackUrl` (string, optional): URL for task completion notifications
+
+**Examples:**
+
+Text-to-video generation:
+```json
+{
+  "prompt": "A dimly lit jazz bar at night, wooden tables glowing under warm pendant lights. Patrons sip drinks and chat quietly while a three-piece band performs on stage. The saxophone player stands under a spotlight, gleaming instrument reflecting the light. No dialogue. Ambient audio: smooth live jazz music with saxophone and piano, clinking glasses, low murmur of audience conversations.",
+  "aspect_ratio": "16:9",
+  "resolution": "1080p",
+  "enable_prompt_expansion": true,
+  "seed": 42
+}
+```
+
+Image-to-video generation:
+```json
+{
+  "prompt": "The same woman from the reference image looks directly into the camera, takes a breath, then smiles brightly and speaks with enthusiasm: 'Have you heard? Alibaba Wan 2.5 API is now available on Kie.ai!'",
+  "image_url": "https://example.com/portrait.jpg",
+  "duration": "5",
+  "resolution": "1080p",
+  "negative_prompt": "blurry, low quality",
+  "seed": 123
+}
+```
+
+**Key Features:**
+- **Unified Interface**: Single tool for both text-to-video and image-to-video
+- **Smart Mode Detection**: Automatically detects mode based on presence of `image_url`
+- **Prompt Expansion**: LLM-powered prompt rewriting for better results with short prompts
+- **Flexible Resolutions**: 720p for speed, 1080p for quality
+- **Aspect Ratio Control**: Support for horizontal, vertical, and square formats (text-to-video)
+- **Duration Control**: 5 or 10 second options for image-to-video
+- **Negative Prompts**: Fine-tune results by specifying what to avoid
+- **Reproducible Results**: Seed control for consistent output
+
+**Note**: The `callBackUrl` is optional and will use the `KIE_AI_CALLBACK_URL` environment variable if not provided. Video generation typically takes 2-6 minutes depending on resolution and complexity.
+
+## Why Developers Choose Kie.ai Over Alternatives
+
+### 💸 **Better Value Than Fal.ai**
+- **Lower costs** for the same premium AI models
+- **Pay-as-you-go pricing** - no monthly commitments
+- **Free trial** to test before you buy
+
+### 🛠️ **Developer Experience**
+- **Single API key** for all models
+- **Documentation** with examples
+- **Simple integration** - get started in minutes
+- **24/7 support** from technical team
+
+### 🚀 **Performance**
+- **99.9% uptime**
+- **Fast response times** (25.2s average)
+- **High concurrency** for production workloads
+- **Reliable results**
+
+### 🔒 **Security**
+- **Encryption** for your data
+- **GDPR compliant** data handling
+- **Private prompts and results**
+- **Regular security updates**
+
+### 🎯 **Platform**
+- **Latest AI models** as they're released
+- **Backward compatible** API
+- **Feature updates** based on feedback
+- **Active development**
 
 ## API Endpoints
 
@@ -245,6 +670,11 @@ The server interfaces with these Kie.ai API endpoints:
 - **Nano Banana Status**: `GET /api/v1/jobs/recordInfo`
 - **Suno Music Generation**: `POST /api/v1/generate` ✅ **VALIDATED**
 - **Suno Music Status**: `GET /api/v1/generate?taskId=XXX` ✅ **VALIDATED**
+- **ElevenLabs TTS Generation**: `POST /api/v1/jobs/createTask` ✅ **VALIDATED**
+- **ElevenLabs TTS Status**: `GET /api/v1/jobs/recordInfo` ✅ **VALIDATED**
+- **ElevenLabs Sound Effects**: `POST /api/v1/jobs/createTask` ✅ **VALIDATED**
+- **ByteDance Seedance Video**: `POST /api/v1/jobs/createTask` ✅ **VALIDATED**
+- **ByteDance Seedance Status**: `GET /api/v1/jobs/recordInfo` ✅ **VALIDATED**
 
 All endpoints follow official Kie.ai API documentation.
 
@@ -256,7 +686,7 @@ The server uses SQLite to track tasks:
 CREATE TABLE tasks (
   id INTEGER PRIMARY KEY AUTOINCREMENT,
   task_id TEXT UNIQUE NOT NULL,
-  api_type TEXT NOT NULL,  -- 'nano-banana', 'nano-banana-edit', 'veo3', 'suno'
+  api_type TEXT NOT NULL,  -- 'nano-banana', 'nano-banana-edit', 'veo3', 'suno', 'elevenlabs-tts', 'elevenlabs-tts-turbo', 'elevenlabs-sound-effects', 'bytedance-seedance-video'
   status TEXT DEFAULT 'pending',
   created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
   updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
@@ -265,6 +695,142 @@ CREATE TABLE tasks (
 );
 ```
 
+## Database & Task Management
+
+The server includes a built-in SQLite database for persistent task tracking and management.
+
+### **Database Features**
+
+- **🔄 Persistent Storage**: Tasks survive server restarts
+- **📊 Complete History**: Track all generation tasks and their results  
+- **⚡ Smart Caching**: Local database reduces API calls for status checks
+- **🔍 Full Audit Trail**: Complete lifecycle tracking for every task
+- **🎯 Intelligent Routing**: Database provides api_type for correct endpoint selection
+
+### **Task Lifecycle**
+
+```
+1. Task Created → INSERT (status: 'pending')
+2. API Processing → UPDATE (status: 'processing') 
+3. API Complete → UPDATE (status: 'completed', result_url: '...')
+4. API Failed → UPDATE (status: 'failed', error_message: '...')
+```
+
+### **Available Task Management Tools**
+
+#### **1. `list_tasks`**
+List all tasks in the database with optional limit.
+
+```json
+{
+  "limit": 50  // optional, default 100
+}
+```
+
+**Response:**
+```json
+{
+  "tasks": [
+    {
+      "id": 1,
+      "task_id": "281e5b0*********************f39b9",
+      "api_type": "veo3",
+      "status": "completed",
+      "created_at": "2025-01-14T10:30:00.000Z",
+      "updated_at": "2025-01-14T10:35:00.000Z",
+      "result_url": "https://file.aiquickdraw.com/custom-page/akr/video.mp4",
+      "error_message": null
+    }
+  ]
+}
+```
+
+#### **2. `get_task_status`**
+Get detailed status of a specific task, combining local database with live API data.
+
+```json
+{
+  "task_id": "281e5b0*********************f39b9"
+}
+```
+
+**Response:**
+```json
+{
+  "task_id": "281e5b0*********************f39b9",
+  "api_type": "veo3",
+  "status": "completed",
+  "local_status": "completed",
+  "api_status": "success",
+  "created_at": "2025-01-14T10:30:00.000Z",
+  "updated_at": "2025-01-14T10:35:00.000Z",
+  "result_url": "https://file.aiquickdraw.com/custom-page/akr/video.mp4",
+  "api_data": {
+    "state": "success",
+    "resultJson": "{\"resultUrls\":[\"https://file.aiquickdraw.com/custom-page/akr/video.mp4\"]}",
+    "costTime": 180000,
+    "completeTime": 1757584164490
+  }
+}
+```
+
+### **Database Configuration**
+
+#### **Environment Variables**
+```bash
+# Custom database file location (optional)
+KIE_AI_DB_PATH=./custom_tasks.db
+
+# Default: ./tasks.db in current working directory
+```
+
+#### **Database Behavior**
+- **Auto-initialization**: Creates tables and indexes on first run
+- **Indexing**: Optimized queries on `task_id` and `status` fields
+- **Thread-safe**: Uses SQLite serialization for concurrent access
+- **Persistent**: Data survives server restarts
+- **Inspectable**: Can be opened with any SQLite client tool
+
+### **Smart Status Checking**
+
+The `get_task_status` tool uses intelligent routing:
+
+1. **Query Local Database**: Fast lookup of task metadata
+2. **API Status Check**: Calls appropriate endpoint based on `api_type`
+3. **Database Update**: Stores latest status from API response
+4. **Combined Response**: Merges local and API data for complete picture
+
+### **API Type Routing**
+
+The database `api_type` field determines which Kie.ai endpoint to query:
+
+| api_type | Endpoint | Purpose |
+|----------|----------|---------|
+| `veo3` | `/veo/record-info` | Veo3 video generation |
+| `nano-banana` | `/jobs/recordInfo` | Image generation |
+| `nano-banana-edit` | `/jobs/recordInfo` | Image editing |
+| `nano-banana-upscale` | `/jobs/recordInfo` | Image upscaling |
+| `suno` | `/generate/record-info` | Music generation |
+| `elevenlabs-tts` | `/jobs/recordInfo` | Text-to-speech |
+| `elevenlabs-tts-turbo` | `/jobs/recordInfo` | Turbo TTS |
+| `elevenlabs-sound-effects` | `/jobs/recordInfo` | Sound effects |
+| `bytedance-seedance-video` | `/jobs/recordInfo` | Video generation |
+
+### **Task Status Values**
+
+- **`pending`**: Task created, waiting for API processing
+- **`processing`**: API is actively processing the task
+- **`completed`**: Task finished successfully, result available
+- **`failed`**: Task failed, error message available
+
+### **Best Practices**
+
+- **Use `list_tasks`** to get overview of all generation activity
+- **Use `get_task_status`** for detailed progress tracking
+- **Monitor `updated_at`** to see when status last changed
+- **Check `error_message`** for failed tasks to debug issues
+- **Use `result_url`** to access completed generation results
+
 ## Usage Examples
 
 ### Basic Image Generation
@@ -295,6 +861,79 @@ curl -X POST http://localhost:3000/tools/call \
   }'
 ```
 
+## Real-World Use Cases
+
+### 🎬 **Content Creation Agencies**
+```bash
+# Generate social media video content
+veo3_generate_video: "A trendy coffee shop with latte art, cinematic lighting"
+
+# Create product photography
+nano_banana_generate: "Luxury watch on marble surface, professional product shot"
+
+# Add background music
+suno_generate_music: "Upbeat corporate background music, 2 minutes"
+```
+
+### 🎮 **Game Development Studios**
+```bash
+# Generate game assets
+nano_banana_generate: "Fantasy sword with glowing runes, game asset style"
+
+# Create character voiceovers
+elevenlabs_tts: "Welcome, brave adventurer! Your quest begins now."
+
+# Design sound effects
+elevenlabs_ttsfx: "Magical spell casting with sparkles and energy"
+```
+
+### 📱 **Mobile App Developers**
+```bash
+# Generate app icons and illustrations
+nano_banana_generate: "Modern minimalist app icon for fitness tracker"
+
+# Create tutorial videos
+bytedance_seedance_video: "Screen recording showing app features, clean interface"
+
+# Add narration
+elevenlabs_tts: "Tap here to get started with your new profile"
+```
+
+### 🏢 **Enterprise Applications**
+```bash
+# Generate training materials
+veo3_generate_video: "Professional office environment, employee training scenario"
+
+# Create corporate presentations
+nano_banana_edit: "Add company logo to presentation slide, maintain professional style"
+
+# Produce marketing content
+suno_generate_music: "Corporate background music for promotional video"
+```
+
+### 🎨 **Creative Professionals**
+```bash
+# Artistic projects
+bytedance_seedance_video: "Abstract art coming to life, vibrant colors flowing"
+
+# Photography enhancement
+nano_banana_upscale: "Portrait photo, 4x enhancement with face restoration"
+
+# Audio production
+elevenlabs_sound_effects: "Nature soundscape with birds and gentle wind"
+```
+
+## Success Stories
+
+### 🚀 **Startup Reduces AI Costs**
+*"Switched from multiple AI services to Kie.ai and cut our monthly AI budget from $2,000 to $600. The unified API simplified our codebase."* - CTO, Content Startup
+
+### ⚡ **Agency Speeds Up Delivery**
+*"Our video production timeline went from 2 weeks to 3 days using Veo 3. Clients like the quality and we handle more projects."* - Creative Director, Marketing Agency
+
+### 🎵 **Music Producer Scales Work**
+*"Suno API lets us generate custom background music for client videos in minutes instead of days. It improved our workflow."* - Producer, Video Production Company
+
 ## Error Handling
 
 The server handles these HTTP error codes from Kie.ai:
@@ -368,6 +1007,29 @@ For issues related to:
 - **Kie.ai API**: Contact support@kie.ai or check https://docs.kie.ai/
 - **API Keys**: Visit https://kie.ai/api-key
 
+## 🚀 Start Building with Kie.ai
+
+Developers are using Kie.ai for their AI media generation:
+
+### 🎯 **Get Started**
+1. **Get your free API key** at [kie.ai/api-key](https://kie.ai/api-key)
+2. **Install the MCP server**: `npm install @felores/kie-ai-mcp-server`
+3. **Generate your first AI content** in minutes
+
+### 💡 **Benefits**
+- ✅ **Free trial** - Test models before paying
+- ✅ **Lower pricing** than Fal.ai and Replicate.com
+- ✅ **99.9% uptime**
+- ✅ **24/7 support**
+- ✅ **Simple integration**
+
+### 🌟 **AI Content Generation**
+Kie.ai provides access to advanced AI models at competitive pricing.
+
+**Start your project today.** 🚀
+
+---
+
 ## License
 
 MIT License - see LICENSE file for details.