> ## 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.

> ## Agent Instructions
> Send API requests to https://api.ttapi.io with the TT-API-KEY header. Midjourney account hosting uses https://hold.ttapi.io. Claude Code uses https://cc.ttapi.io.
> Most generation endpoints are asynchronous. The submit response returns a job id. Poll that product's fetch endpoint, or pass a webhook on the submit request. A fetch call does not start a new generation.
> 1 USD = 100 quota. Check the pricing page for that product before estimating cost.
> This file lists the English docs. Follow every /_llms/ link recursively for the API reference, Chinese, and Russian. Open a page's .md URL for the endpoint schema.

# Seedance Video Generation API Documentation

> View Seedance Video Generation API documentation, supporting omni-reference, video editing, video extension, audio video, image-to-video, text-to-video and more.

# Seedance Video Generation API

This is the **Seedance Video Generation API** overview page. You can quickly understand Seedance's video generation capabilities and navigate to specific endpoint documentation.

## What Seedance Video Generation API Can Do

Seedance provides multiple video generation capabilities for different scenarios:

* **Omni Reference**: Generate new video by fusing multi-modal content based on reference images and videos
* **Edit Video**: Edit based on reference video, supports delete, replace, modify operations
* **Extend Video**: Extend and splice multiple reference videos to generate continuous new video
* **Audio Video - First Frame**: Generate video with synchronized audio based on single first frame image
* **Audio Video - First & Last Frame**: Generate video with synchronized audio based on first and last frame images
* **Image-to-Video**: Generate video based on single reference image
* **Text-to-Video**: Generate video only through text prompt

## Supported Models

| Model | Description | Resolution Support |
| :- | :- | :- |
| `doubao-seedance-2-5-260628` | Seedance 2.5 | Default 720p, options: 480p, 720p, 1080p |
| `doubao-seedance-2-0-260128` | Seedance 2.0 | Default 720p, options: 480p, 720p, 1080p, 4k |
| `doubao-seedance-2-0-fast-260128` | Seedance 2.0 Fast | Default 720p, options: 480p, 720p |
| `doubao-seedance-2-0-mini-260615` | Seedance 2.0 Mini | Default 720p, options: 480p, 720p |

## Video Generation Endpoints

Submit a task and get id, then fetch results via query endpoint. Supports webhook callback.

| Scenario | Endpoint | Description | Supported Models |
| :- | :- | :- | :- |
| Omni Reference | [Omni Reference API](https://docs.ttapi.io/api/en/seedance/omni-reference.md) | Generate based on reference images and videos | All 4 models |
| Edit Video | [Edit Video API](https://docs.ttapi.io/api/en/seedance/edit-video.md) | Edit based on reference video | All 4 models |
| Extend Video | [Extend Video API](https://docs.ttapi.io/api/en/seedance/extend-video.md) | Extend and splice reference videos | All 4 models |
| Audio Video - First Frame | [Audio Video - First Frame API](https://docs.ttapi.io/api/en/seedance/audio-first-frame.md) | Generate audio video from first frame | All 4 models |
| Audio Video - First & Last Frame | [Audio Video - First & Last Frame API](https://docs.ttapi.io/api/en/seedance/audio-first-last-frame.md) | Generate audio video from first & last frames | All 4 models |
| Image-to-Video | [Image-to-Video API](https://docs.ttapi.io/api/en/seedance/image-to-video.md) | Generate video from reference image | All 4 models |
| Text-to-Video | [Text-to-Video API](https://docs.ttapi.io/api/en/seedance/text-to-video.md) | Generate video from text prompt | All 4 models |
| Fetch Result | [Fetch API](https://docs.ttapi.io/api/en/seedance/fetch.md) | Query async task status and results | - |

## Recommended Integration Flow

1. Choose the appropriate endpoint based on your scenario
2. Call the endpoint to submit a task, get id
3. Use [Fetch API](https://docs.ttapi.io/api/en/seedance/fetch.md) to poll task status, or set `hook_url` for callback
4. When `status` is `succeeded`, get the video URL from the response

### Async Task Status

* `queued`: Task pending in queue
* `running`: Task running
* `succeeded`: Task completed successfully
* `failed`: Task failed
* `cancelled`: Task cancelled
* `expired`: Task expired

## Why Use Seedance Video Generation API

* **Multiple generation modes**: Supports omni-reference, video editing, video extension, audio video, image-to-video, text-to-video and more
* **High-quality output**: Supports multiple resolutions (480p / 720p / 1080p / 4k) and aspect ratios, Seedance 2.5's 1080p and Seedance 2.0's 4k use 10bit depth and H.265/HEVC encoding
* **Synchronized audio**: Supports generating video with synchronized audio
* **Flexible control**: Supports custom duration, watermark, output format and other parameters
* **Unified gateway**: Uses TTAPI unified API gateway and authentication


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.