> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ttapi.io/llms.txt
> Use this file to discover all available pages before exploring further.

# HappyHorse Video API Documentation

> View HappyHorse Video API documentation, including text-to-video, image-to-video, reference-to-video, video editing and task query interfaces, suitable for AI video application integration.

# HappyHorse Video API

This is the **HappyHorse Video API** overview page. Here you can quickly learn about HappyHorse's various video generation and editing capabilities and access the specific API documentation.

## What Can HappyHorse Video API Do

HappyHorse provides multiple video generation and editing capabilities to meet different scenarios:

* **Text-to-Video**: Generate high-quality videos directly from text prompts
* **Image-to-Video (First Frame)**: Generate videos based on a single first-frame image
* **Reference-to-Video**: Generate videos based on multiple reference images (1-9 images), supporting character reference through identifiers
* **Video Editing**: Edit based on existing videos and reference images, supporting style transfer, partial replacement, etc.
* **Task Query**: Query the status and results of asynchronous video generation tasks

## Common HappyHorse Video API Interfaces

| Use Case           | Interface                                                       | Description                                   |
| :----------------- | :-------------------------------------------------------------- | :-------------------------------------------- |
| Text-to-Video      | [Generations API](/api/en/happyhorse/generations)               | Generate video from text prompt               |
| Image-to-Video     | [Image-to-Video API](/api/en/happyhorse/image-to-video)         | Generate video from first-frame image         |
| Reference-to-Video | [Reference-to-Video API](/api/en/happyhorse/reference-to-video) | Generate video from multiple reference images |
| Video Editing      | [Video Edit API](/api/en/happyhorse/video-edit)                 | Edit video with video and reference images    |
| Query Task Result  | [Fetch API](/api/en/happyhorse/fetch)                           | Query asynchronous task status and results    |

## Recommended Integration Flow

### Text-to-Video / Image-to-Video / Reference-to-Video / Video Editing

1. Select the appropriate generation interface based on your needs (text-to-video, image-to-video, reference-to-video, or video editing)
2. Call the corresponding generation API to submit a task, get `task_id`
3. Use [Fetch API](/api/en/happyhorse/fetch) to poll for task status
4. When `task_status` is `SUCCEEDED`, get the video URL from the response

### Task Status Description

* `PENDING`: Task is queued
* `RUNNING`: Task is processing
* `SUCCEEDED`: Task completed successfully
* `FAILED`: Task failed
* `CANCELED`: Task was canceled
* `UNKNOWN`: Task does not exist or status is unknown

## Why Use HappyHorse Video API

* **Multiple Generation Modes**: Supports text-to-video, image-to-video, reference-to-video, video editing and more
* **High-Quality Output**: Supports 720P/1080P resolution with various aspect ratio options
* **Flexible Control**: Supports duration control, seed setting, watermark toggle and other parameters
* **Unified Gateway**: Uses unified API gateway and authentication mechanism
* **Complete Lifecycle**: Provides complete task submission, query, and result retrieval workflow

## HappyHorse Video API FAQ

### Which interface is best for new users to start with?

We recommend starting with [Generations API](/api/en/happyhorse/generations) (text-to-video), which is the most basic and commonly used interface.

### What's the difference between Image-to-Video and Reference-to-Video?

* **Image-to-Video**: Generates videos based on a single first-frame image, suitable for scenarios that need to start from a specific frame
* **Reference-to-Video**: Generates videos based on multiple reference images (1-9 images), supporting character references through identifiers like character1, character2, etc., suitable for complex scenarios with multiple characters or elements

### What functions does Video Editing support?

Supports style transfer, partial replacement and other editing functions. Requires providing the video to edit (required) and optional reference images (0-5), describing the editing intent through text prompts.

### How to query task results?

Use [Fetch API](/api/en/happyhorse/fetch) to query the final result of asynchronous tasks. Note that:

* `task_id` is valid for 24 hours
* Video URL is retained for only 24 hours, and will be automatically deleted after timeout, please save generated videos promptly

### How long are the generated videos?

* Text-to-Video / Image-to-Video / Reference-to-Video: 3-15 seconds (customizable)
* Video Editing: Output video duration 3-15 seconds (consistent with input when input video ≤15 seconds, truncates to first 15 seconds when input >15 seconds)

### What resolutions and aspect ratios are supported?

* **Resolution**: 720P, 1080P
* **Aspect Ratio**: 16:9, 9:16, 3:4, 4:3, 1:1