curl --request POST \
--url https://api.vidgo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "kwaivgi/kling-video-o3-pro/text-to-video",
"input": {
"duration": 5,
"sound": true,
"multi_shots": true,
"multi_prompt": [
{
"prompt": "Cinematic whimsical realism in a warm oak library. Medium two-shot: a small ivory robot with an oval face and amber eyes shelves a blue book, accidentally knocking one red book onto the floor. Beside it, an adult librarian wears a green cardigan and round glasses. Both remain visible under warm reading lamps. One distinct book thud against quiet room tone. Unmarked book covers. No text, logos or watermarks.",
"duration": 2
},
{
"prompt": "Cut closer to the same ivory robot and green-cardigan librarian in the same oak library. The librarian raises one finger to her lips. The robot tilts its head apologetically and softly says exactly \"Sorry.\" in a gentle robotic voice, synchronized with its small mouth light. Preserve their appearance, positions and warm lighting. End in an embarrassed pause; no music. No text, logos or watermarks.",
"duration": 3
}
],
"aspect_ratio": "16:9"
}
}
'{
"code": 200,
"data": {
"task_id": "task-submitted-example",
"status": "not_started",
"created_time": "2026-09-22T00:00:00Z"
}
}{
"detail": "<string>"
}{
"detail": "<string>"
}{
"detail": "<string>"
}{
"detail": "<string>"
}Request timeout{
"detail": "<string>"
}{
"detail": "<string>"
}{
"detail": "<string>"
}{
"detail": "<string>"
}{
"detail": "<string>"
}Kling
Kling O3 Pro 文生视频
使用 Kling O3 Pro 根据文本提示词生成 3–15 秒的视频。支持单镜头和多镜头生成。需显式设置 sound；多镜头需要开启音频。
POST
/
api
/
generate
/
submit
curl --request POST \
--url https://api.vidgo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "kwaivgi/kling-video-o3-pro/text-to-video",
"input": {
"duration": 5,
"sound": true,
"multi_shots": true,
"multi_prompt": [
{
"prompt": "Cinematic whimsical realism in a warm oak library. Medium two-shot: a small ivory robot with an oval face and amber eyes shelves a blue book, accidentally knocking one red book onto the floor. Beside it, an adult librarian wears a green cardigan and round glasses. Both remain visible under warm reading lamps. One distinct book thud against quiet room tone. Unmarked book covers. No text, logos or watermarks.",
"duration": 2
},
{
"prompt": "Cut closer to the same ivory robot and green-cardigan librarian in the same oak library. The librarian raises one finger to her lips. The robot tilts its head apologetically and softly says exactly \"Sorry.\" in a gentle robotic voice, synchronized with its small mouth light. Preserve their appearance, positions and warm lighting. End in an embarrassed pause; no music. No text, logos or watermarks.",
"duration": 3
}
],
"aspect_ratio": "16:9"
}
}
'{
"code": 200,
"data": {
"task_id": "task-submitted-example",
"status": "not_started",
"created_time": "2026-09-22T00:00:00Z"
}
}{
"detail": "<string>"
}{
"detail": "<string>"
}{
"detail": "<string>"
}{
"detail": "<string>"
}Request timeout{
"detail": "<string>"
}{
"detail": "<string>"
}{
"detail": "<string>"
}{
"detail": "<string>"
}{
"detail": "<string>"
}- 提交后会返回
task_id。如果提供了callback_url，当任务状态变为finished或failed时，系统会向callback_url发送 POST 请求。 - 无论是否提供
callback_url，都可以通过统一的查询任务状态接口获取结果。
参数
使用模型kwaivgi/kling-video-o3-pro/text-to-video。生成参数放在 input 中。
prompt：multi_shots=false 时必填。描述场景、动作和运镜。使用非空文本，去除首尾空白后最多 2,500 个字符。multi_shots=true 时省略 prompt。multi_prompt：multi_shots=true 时必填；单镜头模式下省略。至少提供一个镜头，每个镜头包含不超过 2,500 个字符的非空 prompt 和 1–12 秒的整数 duration。各镜头时长之和必须等于顶层 duration（3–15 秒）。镜头对象中的多余字段会被忽略。duration：必填整数，3 到 15 秒。多镜头模式下必须等于所有镜头时长之和。积分按该值计算。multi_shots：必填：单镜头显式传 false，多镜头传 true。单镜头模式需要 prompt。多镜头模式需要 multi_prompt 和 sound=true，且顶层不能有非空 prompt。省略该字段会报错。sound：必填：显式传 true 生成音频，或传 false 生成无音频视频。单镜头模式两者均可；多镜头模式必须为 true。aspect_ratio：可选：16:9（横屏）、9:16（竖屏）或 1:1（方形）。设置视频宽高比。
计费因素
计费取决于模型档位、视频时长（duration）以及是否生成音频（sound），按生成的秒数计费。
生成失败的任务会退款。
默认示例：轻声道歉
这与模型页面上展示的默认示例相同。{
"model": "kwaivgi/kling-video-o3-pro/text-to-video",
"input": {
"duration": 5,
"sound": true,
"multi_shots": true,
"multi_prompt": [
{
"prompt": "Cinematic whimsical realism in a warm oak library. Medium two-shot: a small ivory robot with an oval face and amber eyes shelves a blue book, accidentally knocking one red book onto the floor. Beside it, an adult librarian wears a green cardigan and round glasses. Both remain visible under warm reading lamps. One distinct book thud against quiet room tone. Unmarked book covers. No text, logos or watermarks.",
"duration": 2
},
{
"prompt": "Cut closer to the same ivory robot and green-cardigan librarian in the same oak library. The librarian raises one finger to her lips. The robot tilts its head apologetically and softly says exactly \"Sorry.\" in a gentle robotic voice, synchronized with its small mouth light. Preserve their appearance, positions and warm lighting. End in an embarrassed pause; no music. No text, logos or watermarks.",
"duration": 3
}
],
"aspect_ratio": "16:9"
}
}
状态接口返回的完成结果
GET /api/generate/status/{task_id}
下面的响应记录的是这个已验证的示例。新的生成任务请查询你自己提交后返回的任务 ID。
{
"code": 200,
"data": {
"task_id": "BRDSCRKN4Q0WH4T6",
"status": "finished",
"files": [
{
"file_type": "video",
"file_url": "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-video-o3-pro/text-to-video/v1/01/output.mp4"
}
],
"created_time": "2026-09-22T18:43:52",
"error_message": null,
"progress": 100
}
}
API 对提示词的校验上限为 2,500 个字符。部分多镜头生成请求在单个镜头提示词超过 512 个字符时失败。建议每个镜头提示词控制在 512 个字符以内；该建议不改变 API 的校验上限。
授权
使用 VIDGO_API_KEY。
请求体
application/json
model 和 callback_url 放在根级。未知的根级字段会被忽略；不支持的 input 字段会被拒绝。
示例:
"kwaivgi/kling-video-o3-pro/text-to-video"
视频生成参数。请使用标准 JSON 数字和布尔值。为兼容起见，也接受 "5" 这样的整数字符串。布尔字符串 true/1/yes/y/on 表示 true；false/0/no/n/off 表示 false。这些字符串不区分大小写，并会去除首尾空白。布尔字段也接受数字 1 和 0。数字和布尔类型的提示词会转换为文本；0、false 和 null 视为空。提示词不接受对象和数组。
Show child attributes
Show child attributes
可选的公开 HTTP(S) 接口，用于接收任务完成通知。建议使用 HTTPS。省略、传 null 或空字符串即可禁用回调。