seedance1.5-api

Seedance 1.5 API Skill

Seedance is a series of foundational video generation models launched by ByteDance's Doubao large model team, providing API services through the Volcano Ark platform. This skill covers how to use the video generation API for the full Seedance 1.5 pro, 1.0 pro, 1.0 pro fast, and 1.0 lite model series.

Note: Seedance 2.0 currently only supports experience in the console experience center and does not yet support API calls.

When to Use This Skill

This skill should be triggered when:

• Call the Seedance API to generate videos (text-to-video, image-to-video)
• Use the video generation API of the Volcano Ark platform
• Need to understand the parameter configuration of Seedance models (resolution, aspect ratio, duration, etc.)
• Write prompts for Seedance video generation (prompt)
• Use the Python/Go/Java SDK to call Seedance
• Handle the creation, querying, and cancellation of video generation tasks
• Debug Seedance API error codes

Quick Reference

API Base URL

https://ark.cn-beijing.volces.com/api/v3

Authentication method

Authorization: Bearer $ARK_API_KEY

Model ID list

Model	Model ID	Capability
Seedance 1.5 pro	doubao-seedance-1-5-pro-251215	Text-to-video, first-frame image-to-video, first-and-last-frame image-to-video, audio video, sample mode
Seedance 1.0 pro	doubao-seedance-1-0-pro-250528	Text-to-video, first-frame image-to-video, first-and-last-frame image-to-video
Seedance 1.0 pro fast	doubao-seedance-1-0-pro-fast-250528	Text-to-video, first-frame image-to-video
Seedance 1.0 lite t2v	doubao-seedance-1-0-lite-t2v	Text-to-video
Seedance 1.0 lite i2v	doubao-seedance-1-0-lite-i2v	First frame/first and last frame/reference image (1-4 images) image-to-video

Core API endpoints

Operation	Method	Endpoint
Create video generation task	POST	/contents/generations/tasks
Query video generation task	GET	/contents/generations/tasks/{id}
Query task list	GET	/contents/generations/tasks?page_num=&page_size=&filter.status=
Cancel/delete task	DELETE	/contents/generations/tasks/{id}

Quick start - text-to-video (curl)

curl -X POST https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ARK_API_KEY" \
  -d '{
    "model": "doubao-seedance-1-5-pro-251215",
    "content": [
        {
            "type": "text",
            "text": "写实风格，晴朗的蓝天之下，一大片白色的雏菊花田，镜头逐渐拉近，最终定格在一朵雏菊花的特写上，花瓣上有几颗晶莹的露珠"
        }
    ],
    "ratio": "16:9",
    "duration": 5,
    "resolution": "720p",
    "watermark": false
}'

Quick start - image-to-video (first frame)

curl -X POST https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ARK_API_KEY" \
  -d '{
    "model": "doubao-seedance-1-5-pro-251215",
    "content": [
        {"type": "text", "text": "老人缓缓戴上眼镜，微笑"},
        {
            "type": "image_url",
            "image_url": {"url": "https://example.com/image.jpg"},
            "role": "first_frame"
        }
    ],
    "ratio": "16:9",
    "duration": 5
}'

Quick start - audio video (Seedance 1.5 pro)

curl -X POST https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ARK_API_KEY" \
  -d '{
    "model": "doubao-seedance-1-5-pro-251215",
    "content": [
        {
            "type": "text",
            "text": "男人叫住女人说：\"你记住，以后不可以用手指指月亮。\""
        }
    ],
    "generate_audio": true,
    "ratio": "16:9",
    "duration": 5
}'

Query task status

curl -X GET https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks/cgt-2025xxxx \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ARK_API_KEY"

Python SDK example

import os
from volcenginesdkarkruntime import Ark

client = Ark(
    api_key=os.environ.get("ARK_API_KEY"),
    base_url="https://ark.cn-beijing.volces.com/api/v3",
    timeout=1800,
)

# 创建文生视频任务
task = client.content.generations.tasks.create(
    model="doubao-seedance-1-5-pro-251215",
    content=[{"type": "text", "text": "一只小猫对着镜头打哈欠"}],
    ratio="16:9",
    duration=5,
)
print(f"Task ID: {task.id}")

# 查询任务状态
result = client.content.generations.tasks.get(task.id)
print(f"Status: {result.status}")
if result.status == "succeeded":
    print(f"Video URL: {result.content.video_url}")

Video parameters quick reference

Parameter	Value	Default value	Description
resolution	480p / 720p / 1080p	1.5pro/lite: 720p, 1.0pro: 1080p	Resolution
ratio	16:9 / 4:3 / 1:1 / 3:4 / 9:16 / 21:9 / adaptive	Text generation: 16:9, image generation: adaptive	Aspect ratio
duration	2~12 seconds (1.5pro supports -1 automatic)	5	Video duration
seed	-1 ~ 2^32-1	-1 (random)	Random seed
camera_fixed	true / false	false	Fixed camera
watermark	true / false	false	Watermark
generate_audio	true / false	true	Audio video (only 1.5pro)
draft	true / false	false	Sample mode (only 1.5pro)
service_tier	default / flex	default	flex is offline mode, half price

References

• api-create-task.md - Complete parameter description for the Create Video Generation Task API
• api-query-task.md - Query Video Generation Task API
• api-query-task-list.md - Query Video Generation Task List API
• api-cancel-delete-task.md - Cancel or Delete Video Generation Task API
• authentication.md - Base URL, authentication method, and API Key configuration
• sdk-examples.md - Python/Go/Java SDK usage examples
• openai-sdk-compat.md - Compatible with OpenAI SDK calling method
• prompt-guide.md - Seedance prompt usage techniques
• error-codes.md - Error code reference