info

Introduction

The VideoGenAPI allows you to generate videos from text descriptions or images using advanced artificial intelligence technology. This RESTful API provides endpoints for video generation, status checking, and user management.

text_fields Text-to-Video

Generate videos from text descriptions using advanced AI models.

image Image-to-Video

Generate videos from an image and descriptive prompt.

smart_toy

Multiple AI Models

Choose from 10 different AI models including 8 free options and 2 premium models. Each model has unique capabilities and specifications.

music_note

AI Audio Enhancement

Add synchronized sound effects to your generated videos automatically! Use the add_audio parameter to enhance your videos with AI-generated audio using Mirelo SFX V1.5. Optional audio_prompt parameter lets you customize the sound effects.

content_copy Copy for AI Chats

Copy this entire documentation in markdown format to share
with AI assistants like ChatGPT, Claude, Cursor, etc.

The API automatically detects the generation mode based on provided parameters. When only the prompt parameter is provided, it uses Text-to-Video mode. When both prompt and image_url parameters are provided, it activates Image-to-Video mode (single image). When reference_image_urls is provided, it uses Image-to-Video mode with multiple images (supported by Veo 3.1 and other models). Use the model parameter to specify which AI model to use for generation.

security

Authentication

All API requests must include your API key in the Authorization header using Bearer token authentication: 

Authorization: Bearer YOUR_API_KEY
vpn_key

Your API Key:

lt_**************
link

Base URL

All API endpoints are relative to the base URL: 

https://videogenapi.com/api/v1/
smart_toy

AI Models

Model Description Resolution Duration Features
Sora 2 Sora 2, developed by OpenAI, is the best model for generating highly realistic videos and audio with precise physical simulations and synchronized dialogue. 1080p 10-10s Text-to-Video, Image-to-Video
Higgsfield Advanced AI model with excellent motion understanding and photorealistic output. Perfect for cinematic scenes. 1080p 5-15s Text-to-Video
Kling 2.5 Kling 2.5 Turbo Pro: Top-tier text-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision. 1080p 5-10s Text-to-Video, Image-to-Video
Veo 3 Fast Google's most advanced video generation model with unparalleled quality and incredible detail. 1080p 8-8s Text-to-Video, Image-to-Video
Veo 3.1 Fast Google's cutting-edge video generation model, delivering unmatched quality, hyper-realistic details, and enhanced creative control for stunning visuals. 1080p 8-8s Text-to-Video, Image-to-Video
Nano Banana Lightweight and fast AI model for quick creative video generation. Perfect for short clips and rapid prototyping. 720p 5-10s Text-to-Video, Image-to-Video
LTV Video 2 Create high-fidelity video and audio from text with LTXV 2 the new open source video model. 4K 6-10s Text-to-Video, Image-to-Video
LTX-Video 13B LTX 480p 1-60s Text-to-Video
Seedance Lightning-fast model perfect for quick prototyping and creative experimentation. 1080p 5-10s Text-to-Video, Image-to-Video
Wan 2.5 Wan 2.5 Video is an open-source AI model capable of automatically generating realistic videos with audio. 1080p 5-10s Text-to-Video, Image-to-Video
api

Endpoints

POST

Generate Video

/v1/generate

Submit a video generation request from a text description (text-to-video) or from an image + text (image-to-video).

Automatic Mode Detection

The API automatically detects the generation mode based on parameters:

  • Text-to-Video: When only the prompt parameter is provided
  • Image-to-Video: When both prompt and image_url parameters are provided (single image)
  • Image-to-Video (Multi-image): When prompt and reference_image_urls are provided (1-5 images). Supported by Veo 3.1 and other models that support reference-to-video

Available AI Models

Free Models
  • sora-2 - Sora 2 (1080p, 10-10s)
  • higgsfield_v1 - Higgsfield (1080p, 5-15s)
  • kling_25 - Kling 2.5 (1080p, 5-10s)
  • nanobanana-video - Nano Banana (720p, 5-10s)
  • ltxv-2 - LTV Video 2 (4K, 6-10s)
  • ltxv-13b - LTX-Video 13B (480p, 1-60s)
  • seedance - Seedance (1080p, 5-10s)
  • wan-25 - Wan 2.5 (1080p, 5-10s)
Premium Models
  • veo_3 - Veo 3 Fast (1080p, 8-8s)
  • veo-31 - Veo 3.1 Fast (1080p, 8-8s)

Parameters

Parameter Type Required Description Default
model string Optional AI model to use (sora-2, higgsfield_v1, kling_25, veo_3, veo-31, nanobanana-video, ltxv-2, ltxv-13b, seedance, wan-25) sora-2
prompt string Required Text description of the video (max 1000 characters) -
image_url string Optional Source image URL (jpg, jpeg, png, gif, webp). If provided, activates image-to-video mode (single image) -
reference_image_urls array Optional Array of image URLs (1-5 images). For Veo 3.1: 1-2 images uses FIRST_AND_LAST_FRAMES_2_VIDEO mode, 3+ images uses REFERENCE_2_VIDEO mode (forces veo3_fast and 16:9) -
duration integer Optional Duration in seconds (varies by model: 5-60s) 5
resolution string Optional Video resolution (480p, 720p, 1080p, 4K - varies by model) 720p
aspect_ratio string Optional Aspect ratio (16:9, 4:3, 1:1, 9:21). Only for text-to-video mode 16:9
seed integer Optional Random seed to control generation (-1 for random) random
camera_fixed boolean Optional Whether to fix the camera position false
add_audio boolean Optional Add AI-generated sound effects synchronized with video false
audio_prompt string Optional Guide audio generation with custom description -

Text-to-Video Example (cURL)

cURL Request 
curl -X POST "https://videogenapi.com/api/v1/generate" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling_25",
    "prompt": "A cat playing with a ball in a sunny garden",
    "duration": 10,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "seed": 42
  }'

Image-to-Video Example (cURL)

cURL Request 
curl -X POST "https://videogenapi.com/api/v1/generate" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo_3",
    "prompt": "The dog runs in the park chasing a butterfly",
    "image_url": "https://example.com/images/my-dog.jpg",
    "duration": 15,
    "resolution": "4K",
    "camera_fixed": false,
    "seed": 123456
  }'

Image-to-Video Example (cURL)

cURL Request 
curl -X POST "https://videogenapi.com/api/v1/generate" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo_3",
    "prompt": "The dog runs in the park chasing a butterfly",
    "image_url": "https://example.com/images/my-dog.jpg",
    "duration": 15,
    "resolution": "4K",
    "camera_fixed": false,
    "seed": 123456
  }'

Veo 3.1 Multi-Image Example (cURL)

info

Veo 3.1 Multi-Image Support

Veo 3.1 supports multiple images via reference_image_urls. With 1-2 images, it uses FIRST_AND_LAST_FRAMES_2_VIDEO mode. With 3+ images, it uses REFERENCE_2_VIDEO mode (automatically forces veo3_fast and 16:9).

cURL Request - Veo 3.1 with 2 images 
curl -X POST "https://videogenapi.com/api/v1/generate" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo-31",
    "prompt": "The scene transitions smoothly from day to night",
    "reference_image_urls": [
      "https://example.com/day.jpg",
      "https://example.com/night.jpg"
    ],
    "aspect_ratio": "16:9",
    "veo_model": "veo3_fast"
  }'
cURL Request - Veo 3.1 Reference Mode (3+ images) 
curl -X POST "https://videogenapi.com/api/v1/generate" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo-31",
    "prompt": "A stylized animation of a character walking",
    "reference_image_urls": [
      "https://example.com/ref1.jpg",
      "https://example.com/ref2.jpg",
      "https://example.com/ref3.jpg"
    ]
  }'

Note: With 3+ images, Veo 3.1 automatically uses REFERENCE_2_VIDEO mode, forces veo3_fast model, and aspect_ratio: "16:9". The veo_model and aspect_ratio parameters will be ignored.

Text-to-Video with Audio Enhancement (cURL)

cURL Request with Audio 
curl -X POST "https://videogenapi.com/api/v1/generate" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling_25",
    "prompt": "A cat playing with a ball in a sunny garden",
    "duration": 10,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "add_audio": true,
    "audio_prompt": "Cheerful ambient sounds with soft nature background"
  }'

Response Example (Text-to-Video)

JSON Response 
{
  "success": true,
  "generation_id": "gen_686717fe97bd3_055867",
  "request_id": "24076931-9c23-4d18-a1d4-9d5cb5369c62",
  "status": "pending",
  "type": "text-to-video",
  "model": {
    "key": "kling_25",
    "name": "Kling 2.5",
    "provider": "Kuaishou"
  },
  "prompt": "A cat playing with a ball in a sunny garden",
  "duration": 10,
  "resolution": "1080p",
  "style": "realistic",
  "fps": 30,
  "aspect_ratio": "16:9",
  "seed": 42,
  "status_url": "/v1/status/gen_686717fe97bd3_055867",
  "message": "Video generation request submitted successfully.",
  "usage": {
    "current_month_usage": 1,
    "monthly_limit": 100
  }
}
GET

Check Status

/v1/status/{generation_id}

Check the status of a video generation request.

cURL Example

cURL Request 
curl -X GET "https://videogenapi.com/api/v1/status/gen_686717fe97bd3_055867" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response Example (Completed)

JSON Response 
{
  "success": true,
  "generation_id": "gen_686717fe97bd3_055867",
  "status": "completed",
  "type": "text-to-video",
  "model": {
    "key": "kling_25",
    "name": "Kling 2.5",
    "provider": "Kuaishou"
  },
  "video_url": "https://videogenapi.com/api/v1/video/gen_686717fe97bd3_055867",
  "prompt": "A cat playing with a ball in a sunny garden",
  "duration": 10,
  "resolution": "1080p",
  "style": "realistic",
  "fps": 30,
  "aspect_ratio": "16:9",
  "processing_time": 764,
  "completed_at": "2025-01-04 00:08:42",
  "seed": 622177285
}
public

Public Access

The video URL is publicly accessible without authentication. You can share it directly!

Possible Status Values

Status Description
pending Request submitted, waiting for processing
in_queue Request is in the processing queue
in_progress Video generation in progress
completed Generation completed successfully
failed Generation failed
GET

List Generations

/v1/generations

Retrieve a list of your video generation requests.

cURL Example

cURL Request 
curl -X GET "https://videogenapi.com/api/v1/generations?page=1&limit=10" \
  -H "Authorization: Bearer YOUR_API_KEY"
GET

User Information

/v1/user

Retrieve user information and usage statistics.

cURL Example

cURL Request 
curl -X GET "https://videogenapi.com/api/v1/user" \
  -H "Authorization: Bearer YOUR_API_KEY"
error

Error Codes

The API uses conventional HTTP response codes to indicate the success or failure of an API request.

HTTP Code Error Description
400 Bad Request Invalid parameters or missing required fields
401 Unauthorized Invalid or missing API key
404 Not Found Resource not found
429 Too Many Requests Rate limit or monthly usage limit exceeded
500 Internal Server Error Internal server error
code

Code Examples

PHP Complete PHP Example

videogen-api.php 
<?php
class videogenAPI {
    private $apiKey;
    private $baseUrl = 'https://videogenapi.com/api/v1';

    public function __construct($apiKey) {
        $this->apiKey = $apiKey;
    }

    public function generateTextToVideo($prompt, $options = []) {
        $data = array_merge([
            'model' => 'higgsfield',
            'prompt' => $prompt,
            'duration' => 5,
            'resolution' => '720p',
            'aspect_ratio' => '16:9'
        ], $options);

        return $this->makeRequest('/generate', 'POST', $data);
    }

    public function generateImageToVideo($prompt, $imageUrl, $options = []) {
        $data = array_merge([
            'model' => 'kling_2_1',
            'prompt' => $prompt,
            'image_url' => $imageUrl,
            'duration' => 5,
            'resolution' => '720p',
            'camera_fixed' => false
        ], $options);

        return $this->makeRequest('/generate', 'POST', $data);
    }

    public function getStatus($generationId) {
        return $this->makeRequest('/status/' . $generationId);
    }

    private function makeRequest($endpoint, $method = 'GET', $data = null) {
        // Implementation details...
    }
}

// Usage examples...
?>

JS JavaScript Example

videogen-api.js 
class videogenAPI {
    constructor(apiKey) {
        this.apiKey = apiKey;
        this.baseUrl = 'https://videogenapi.com/api/v1';
    }

    async generateTextToVideo(prompt, options = {}) {
        const data = {
            model: 'higgsfield',
            prompt,
            duration: 5,
            resolution: '720p',
            aspect_ratio: '16:9',
            ...options
        };

        return await this.makeRequest('/generate', 'POST', data);
    }

    async generateImageToVideo(prompt, imageUrl, options = {}) {
        const data = {
            model: 'kling_2_1',
            prompt,
            image_url: imageUrl,
            duration: 5,
            resolution: '720p',
            camera_fixed: false,
            ...options
        };

        return await this.makeRequest('/generate', 'POST', data);
    }

    // Additional methods...
}
music_note

AI Audio Enhancement

Automatically add synchronized sound effects to your videos using the Mirelo SFX V1.5 model. This feature automatically detects the video content and generates appropriate audio, or you can provide a custom audio prompt for fine-tuned control.

auto_awesome

How It Works

  1. Submit a video generation request with add_audio: true
  2. Video is generated normally by the selected model
  3. Audio enhancement automatically begins after video generation completes
  4. AI-generated sound effects are synchronized with the video
  5. Final video with audio is returned when complete

Audio Enhancement Parameters

Parameter Type Description
add_audio boolean Enable automatic audio enhancement (default: false)
audio_prompt string Optional custom guidance for audio generation. Examples: "upbeat pop music", "nature sounds with birds", "cinematic orchestral soundtrack"

Example Request

With Audio Enhancement 
{
  "model": "kling_25",
  "prompt": "A cat playing with a ball in a sunny garden",
  "duration": 10,
  "resolution": "1080p",
  "add_audio": true,
  "audio_prompt": "cheerful ambient sounds with soft nature background"
}
schedule

Processing Time

Audio enhancement adds additional processing time after video generation. Total time will be the video generation time plus audio synthesis time (typically 10-30 seconds). The same generation_id is used throughout the process.

support_agent

Support

email Contact Us

Need help? Contact us at:

contact@lannetech.com

schedule Response Time

We typically respond within:

24-48 hours
video_settings

Video Specifications

Feature Value
Output format MP4 (H.264 codec)
Duration 5-10 seconds
Resolutions 480p, 720p, 1080p, 4K
Aspect ratios 16:9, 4:3, 1:1, 9:21
Frame rate 30 FPS

Ready to Start Building?

Get your API key and start generating amazing videos with just a few lines of code.

Get API Key View Examples
bolt Fast Integration
description Complete Documentation
support_agent 24/7 Support
code Multiple SDKs