Back to Details

veo-video

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Veo Video Generation

Veo视频生成

Generate AI videos through AceDataCloud's Google Veo API.
Setup: See authentication for token setup.
通过AceDataCloud的Google Veo API生成AI视频。
设置： 请查看身份验证了解令牌设置方法。

Quick Start

快速开始

bash
curl -X POST https://api.acedata.cloud/veo/videos \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"action": "text2video", "prompt": "a whale breaching in slow motion at golden hour", "model": "veo3", "callback_url": "https://api.acedata.cloud/health"}'
Async: See async task polling. Poll via 
POST /veo/tasks
with 
{"id": "..."}
. This returns a task ID immediately. Poll for the result:
bash
curl -X POST https://api.acedata.cloud/veo/tasks \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"id": "<task_id from above>"}'
bash
curl -X POST https://api.acedata.cloud/veo/videos \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"action": "text2video", "prompt": "a whale breaching in slow motion at golden hour", "model": "veo3", "callback_url": "https://api.acedata.cloud/health"}'
异步处理： 请查看异步任务轮询。通过
POST /veo/tasks
接口并传入
{"id": "..."}
进行轮询。该接口会立即返回一个任务ID，之后可轮询获取结果：
bash
curl -X POST https://api.acedata.cloud/veo/tasks \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"id": "<task_id from above>"}'

Models

模型

ModelAudioBest For
veo2-fast
NoFast, cost-effective generation (default)
veo3
Yes (native)Full audiovisual generation
veo3-fast
Yes (native)Faster audiovisual generation
veo31
Yes (native)Veo 3.1, highest quality
veo31-fast
Yes (native)Veo 3.1 fast variant
veo31-fast-ingredients
Yes (native)Veo 3.1 fast, ingredient mode
模型音频支持适用场景
veo2-fast
否快速、高性价比生成（默认）
veo3
是（原生）全视听内容生成
veo3-fast
是（原生）更快的视听内容生成
veo31
是（原生）Veo 3.1，最高画质
veo31-fast
是（原生）Veo 3.1快速版
veo31-fast-ingredients
是（原生）Veo 3.1快速版，素材混合模式

Workflows

工作流

1. Text-to-Video

1. 文本转视频

json
POST /veo/videos
{
  "action": "text2video",
  "prompt": "cinematic aerial shot of the Northern Lights over Iceland",
  "model": "veo3",
  "resolution": "1080p"
}
json
POST /veo/videos
{
  "action": "text2video",
  "prompt": "cinematic aerial shot of the Northern Lights over Iceland",
  "model": "veo3",
  "resolution": "1080p"
}

2. Image-to-Video

2. 图片转视频

Animate still images into video.
json
POST /veo/videos
{
  "action": "image2video",
  "prompt": "the scene gently comes to life with wind and subtle motion",
  "image_urls": ["https://example.com/landscape.jpg"],
  "model": "veo2-fast",
  "aspect_ratio": "16:9"
}
将静态图片动化为视频。
json
POST /veo/videos
{
  "action": "image2video",
  "prompt": "the scene gently comes to life with wind and subtle motion",
  "image_urls": ["https://example.com/landscape.jpg"],
  "model": "veo2-fast",
  "aspect_ratio": "16:9"
}

3. Ingredients-to-Video (Multi-Image Blend)

3. 多素材混合转视频

Blend 1–3 reference images into a video (only 
veo31-fast-ingredients
).
json
POST /veo/videos
{
  "action": "ingredients2video",
  "image_urls": [
    "https://example.com/img1.jpg",
    "https://example.com/img2.jpg"
  ],
  "model": "veo31-fast-ingredients"
}
将1-3张参考图片融合为视频（仅支持
veo31-fast-ingredients
）。
json
POST /veo/videos
{
  "action": "ingredients2video",
  "image_urls": [
    "https://example.com/img1.jpg",
    "https://example.com/img2.jpg"
  ],
  "model": "veo31-fast-ingredients"
}

4. Upscale to 1080p

4. 升频至1080p

Convert a previously generated video to full 1080p resolution.
json
POST /veo/videos
{
  "action": "get1080p",
  "video_id": "your-video-id",
  "model": "veo3"
}
将已生成的视频转换为全1080p分辨率。
json
POST /veo/videos
{
  "action": "get1080p",
  "video_id": "your-video-id",
  "model": "veo3"
}

Parameters

参数

ParameterValuesDescription
action
"text2video"
, 
"image2video"
, 
"ingredients2video"
, 
"get1080p"
Generation mode
model
see Models tableModel to use (default: 
veo2-fast
)
resolution
"4k"
, 
"1080p"
, 
"gif"
Output resolution (default: 720p)
aspect_ratio
"16:9"
, 
"9:16"
Aspect ratio — only valid for 
image2video
image_urls
array of stringsReference image URLs — for 
image2video
(up to 2) or 
ingredients2video
(up to 3)
video_id
stringVideo to upscale — only for 
get1080p
translation
true
/ 
false
Auto-translate prompt to English (default: false)
参数可选值描述
action
"text2video"
, 
"image2video"
, 
"ingredients2video"
, 
"get1080p"
生成模式
model
见模型表格使用的模型（默认：
veo2-fast
）
resolution
"4k"
, 
"1080p"
, 
"gif"
输出分辨率（默认：720p）
aspect_ratio
"16:9"
, 
"9:16"
宽高比 — 仅对
image2video
有效
image_urls
字符串数组参考图片URL — 适用于
image2video
（最多2张）或
ingredients2video
（最多3张）
video_id
字符串待升频的视频ID — 仅适用于
get1080p
translation
true
/ 
false
自动将提示词翻译为英文（默认：false）

Post-Generation Endpoints

生成后处理接口

After generating a video, use these endpoints to further process it:
视频生成完成后，可使用以下接口进行进一步处理：

Upsample (
POST /veo/upsample
)

升采样（
POST /veo/upsample
）

Upscale a generated video to 1080p, 4K, or convert to GIF.
json
POST /veo/upsample
{
  "video_id": "your-video-id",
  "action": "4k"
}
ParameterValuesDescription
video_id
stringTask ID from 
/veo/videos
, 
/veo/extend
, 
/veo/reshoot
, or 
/veo/objects
action
"1080p"
, 
"4k"
, 
"gif"
Upsample target
将生成的视频升频至1080p、4K，或转换为GIF。
json
POST /veo/upsample
{
  "video_id": "your-video-id",
  "action": "4k"
}
参数可选值描述
video_id
字符串来自
/veo/videos
、
/veo/extend
、
/veo/reshoot
或
/veo/objects
的任务ID
action
"1080p"
, 
"4k"
, 
"gif"
升采样目标

Extend (
POST /veo/extend
)

延长视频（
POST /veo/extend
）

Continue an existing video — AI auto-generates the next segment.
json
POST /veo/extend
{
  "video_id": "your-video-id",
  "model": "veo31-fast",
  "prompt": "the camera slowly zooms out"
}
ParameterValuesDescription
video_id
stringTask ID from 
/veo/videos
or a prior 
/veo/extend
model
"veo31-fast"
, 
"veo31"
Only Veo 3.1 series is supported
prompt
stringOptional: guides the extended segment
延续现有视频——AI自动生成后续片段。
json
POST /veo/extend
{
  "video_id": "your-video-id",
  "model": "veo31-fast",
  "prompt": "the camera slowly zooms out"
}
参数可选值描述
video_id
字符串来自
/veo/videos
或之前
/veo/extend
的任务ID
model
"veo31-fast"
, 
"veo31"
仅支持Veo 3.1系列
prompt
字符串可选：引导后续片段的生成

Reshoot (
POST /veo/reshoot
)

重拍视频（
POST /veo/reshoot
）

Re-render a video keeping the same content but applying new camera motion.
json
POST /veo/reshoot
{
  "video_id": "your-video-id",
  "motion_type": "LEFT_TO_RIGHT"
}
ParameterValuesDescription
video_id
stringTask ID from 
/veo/videos
(cannot use 
/veo/extend
output)
motion_type
see table belowCamera motion to apply
motion_type
values: 
STATIONARY
, 
STATIONARY_UP
, 
STATIONARY_DOWN
, 
STATIONARY_LEFT
, 
STATIONARY_RIGHT
, 
STATIONARY_DOLLY_IN_ZOOM_OUT
, 
STATIONARY_DOLLY_OUT_ZOOM_IN
, 
UP
, 
DOWN
, 
LEFT_TO_RIGHT
, 
RIGHT_TO_LEFT
, 
FORWARD
, 
BACKWARD
, 
DOLLY_IN_ZOOM_OUT
, 
DOLLY_OUT_ZOOM_IN
重新渲染视频，保留原有内容但应用新的镜头运动。
json
POST /veo/reshoot
{
  "video_id": "your-video-id",
  "motion_type": "LEFT_TO_RIGHT"
}
参数可选值描述
video_id
字符串来自
/veo/videos
的任务ID（不可使用
/veo/extend
的输出）
motion_type
见下表应用的镜头运动类型
motion_type
可选值： 
STATIONARY
, 
STATIONARY_UP
, 
STATIONARY_DOWN
, 
STATIONARY_LEFT
, 
STATIONARY_RIGHT
, 
STATIONARY_DOLLY_IN_ZOOM_OUT
, 
STATIONARY_DOLLY_OUT_ZOOM_IN
, 
UP
, 
DOWN
, 
LEFT_TO_RIGHT
, 
RIGHT_TO_LEFT
, 
FORWARD
, 
BACKWARD
, 
DOLLY_IN_ZOOM_OUT
, 
DOLLY_OUT_ZOOM_IN

Objects (
POST /veo/objects
)

物体编辑（
POST /veo/objects
）

Insert or remove objects in a video using mask-based inpainting.
json
POST /veo/objects
{
  "video_id": "your-video-id",
  "action": "insert",
  "prompt": "add a flying bird"
}
json
POST /veo/objects
{
  "video_id": "your-video-id",
  "action": "remove",
  "image_mask": "https://example.com/mask.jpg"
}
ParameterValuesDescription
video_id
stringTask ID (cannot use 
/veo/extend
output)
action
"insert"
, 
"remove"
Operation type
prompt
stringRequired for 
insert
; optional for 
remove
image_mask
stringURL or base64 JPEG — white pixels = target region. Required for 
remove
; optional for 
insert
基于蒙版的修复技术在视频中插入或移除物体。
json
POST /veo/objects
{
  "video_id": "your-video-id",
  "action": "insert",
  "prompt": "add a flying bird"
}
json
POST /veo/objects
{
  "video_id": "your-video-id",
  "action": "remove",
  "image_mask": "https://example.com/mask.jpg"
}
参数可选值描述
video_id
字符串任务ID（不可使用
/veo/extend
的输出）
action
"insert"
, 
"remove"
操作类型
prompt
字符串
insert
操作必填；
remove
操作可选
image_mask
字符串URL或base64格式的JPEG图片——白色像素代表目标区域。
remove
操作必填；
insert
操作可选

Gotchas

注意事项

  • Veo 3 and 3.1 models generate native audio — 
    veo2-fast
    does NOT support audio
  • The 
    get1080p
    action uses 
    video_id
    (from a prior generation), not a URL
  • aspect_ratio
    is only valid for the 
    image2video
    action
  • image_urls
    accepts an array — up to 2 images for 
    image2video
    , up to 3 for 
    ingredients2video
  • veo31-fast-ingredients
    requires image input — it cannot do text-only generation
  • Documented 
    aspect_ratio
    values are only 
    "16:9"
    and 
    "9:16"
  • translation: true
    auto-translates Chinese or other non-English prompts before sending to Veo
  • Task polling uses 
    id
    (not 
    task_id
    ) in the 
    /veo/tasks
    request body
  • Task states use 
    "succeeded"
    (not "completed") — check for this value when polling
  • /veo/extend
    output cannot be used as input for 
    /veo/reshoot
    or 
    /veo/objects
MCP: 
pip install mcp-veo
| Hosted: 
https://veo.mcp.acedata.cloud/mcp
| See all MCP servers
  • Veo 3和3.1模型会生成原生音频——
    veo2-fast
    不支持音频
  • get1080p
    操作使用
    video_id
    （来自之前的生成任务），而非URL
  • aspect_ratio
    仅对
    image2video
    操作有效
  • image_urls
    接受数组——
    image2video
    最多2张图片，
    ingredients2video
    最多3张
  • veo31-fast-ingredients
    必须传入图片输入——不支持纯文本生成
  • 文档中记录的
    aspect_ratio
    可选值仅为
    "16:9"
    和
    "9:16"
  • translation: true
    会自动将中文或其他非英文提示词翻译为英文后发送给Veo
  • 任务轮询时，
    /veo/tasks
    请求体中使用
    id
    （而非
    task_id
    ）
  • 任务状态使用
    "succeeded"
    （而非"completed"）——轮询时需检查该值
  • /veo/extend
    的输出不可作为
    /veo/reshoot
    或
    /veo/objects
    的输入
MCP： 
pip install mcp-veo
| 托管地址：
https://veo.mcp.acedata.cloud/mcp
| 查看所有MCP服务器