Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.globalaiopc.com/llms.txt

Use this file to discover all available pages before exploring further.

​
API Introduction

Provides various AI video generation, image generation, and text processing APIs, supporting mainstream models including Sora, VEO, Seedance, Vidu, Grok, and more.

​
Core API Services

Video Generation API

Support for Sora, VEO, Seedance, Vidu, Grok and other video generation models, providing text-to-video and image-to-video capabilities

Image Generation API

Support for Navo Banana image generation model, creating high-quality images from text prompts

Text Processing API

Support for Gemini chat model, providing intelligent conversation and text generation capabilities

​
Video Generation Models

Support for multiple mainstream video generation models to meet different scenario requirements:

​
Sora

OpenAI’s video generation model, supporting various duration and resolution options.
  • sora2Stable: Stable version, supports 10 or 15 seconds
  • openAiSora2: Supports 4, 8, 12 seconds
  • openAiSora2Stable: Stable version, supports 4, 8, 12 seconds
  • openAiSora2Plus: Enhanced version, supports 4, 8, 12 seconds
View Sora Documentation

​
VEO

Google’s video generation model, providing high-quality video output.
  • Supports various durations and resolutions
  • Text-to-video and image-to-video
View VEO Documentation

​
Seedance1.5

Volcano Engine’s video generation model, supporting multiple resolutions and durations.
  • seedance_1_5_pro_720p: 720p HD output
  • seedance_1_5_pro_1080p: 1080p Full HD output
  • Supports 5-10 second video generation
View Seedance1.5 Documentation

​
Seedance2.0

Volcano Engine’s latest video generation model, providing more powerful generation capabilities.
  • seedance_2_0: Standard version
  • seedance_2_0_fast: Fast version
  • seedance_2_0_pro: Professional version
  • seedance_2_0_fast_pro: Fast professional version
  • Supports asset management features
View Seedance2.0 Documentation

​
Vidu

Flexible video generation model supporting text-to-video, image-to-video, and first-last frame guidance.
  • viduq3-pro: High-quality output, better results
  • viduq3-turbo: Fast generation, faster speed
  • Supports adjustable duration from 1-16 seconds
  • Supports multiple resolutions: 540p, 720p, 1080p
View Vidu Documentation

​
Grok

xAI’s video generation model, supporting flexible duration and resolution configuration.
  • grok_video3: Supports 6-30 seconds adjustable, 480p/720p resolution
  • grok_video3_pro: Fixed 10 seconds, does not support specifying resolution
  • Supports image-to-video (grok_video3 up to 7 reference images)
View Grok Documentation

​
Authentication

All API requests require a Bearer token in the request header: 
Authorization: Bearer {{key}}

​
Base URL

https://zcbservice.aizfw.cn/kyyReactApiServer

​
Asynchronous Task Processing

Both video generation and image generation use asynchronous task processing:
  1. Task ID is returned after creating a task
  2. Use task ID to query task status and results
  3. Task statuses include: queued (queued), processing (processing), completed (completed), failed (failed)

​
Code Examples

import requests

# Create video generation task
response = requests.post(
    'https://zcbservice.aizfw.cn/kyyReactApiServer/v1/sora/videos',
    headers={
        'Authorization': 'Bearer {{key}}',
        'Content-Type': 'application/json'
    },
    json={
        'model': 'sora2Stable',
        'prompt': 'A cat dancing in the rain, cinematic style',
        'aspect_ratio': '16:9',
        'seconds': 10
    }
)

task_id = response.json()['id']

# Query task status
status_response = requests.get(
    f'https://zcbservice.aizfw.cn/kyyReactApiServer/v1/sora/videos/{task_id}',
    headers={'Authorization': 'Bearer {{key}}'}
)

​
Frequently Asked Questions

Please contact us to obtain an API Key. All requests require a Bearer token in the Authorization header.
Video generation time depends on the model and video duration, typically taking a few minutes. You can get real-time task status through the query interface.
Different models support different resolutions, commonly 480p, 540p, 720p, 1080p. Please refer to each model’s documentation for details.
Provide reference image URLs when creating a task. Different models have different requirements for the number and format of reference images. Please check specific model documentation.