Create Video

1. Overview

OpenAI’s latest text-to-video generation model can create short videos from brief prompts, featuring synchronized speech and sound effects, improved physical realism, and enhanced controllability. A visible watermark is added to the output to help prevent misuse.

Use this API to create a video generation task. After obtaining the video_id, you can append it as a URL parameter when calling the APIs for creating video editing tasks, querying task status, or downloading the generated video file.

Available model list:

  • sora-2

2. Request Description

  • Request method: POST

  • Request address: https://gateway.theturbo.ai/v1/videos

3. Input Parameters

3.1 Header Parameters

Parameter Name
Type
Required
Description
Example Value

Content-Type

string

Yes

Set the request header type, which must be multipart/form-data

multipart/form-data; boundary=------------------------y0QNRDhXQUE3yHQi7DEbLz

Authorization

string

Yes

API_KEY required for authentication. Format: Bearer $YOUR_API_KEY

Bearer $YOUR_API_KEY

3.2 Body Parameters (application/json)

Parameter Name
Type
Required
Description
Example (Default Value)

model

string

Yes

Model ID to use. See available models listed in the Overview for details, such as sora-2.

sora-2

prompt

string

Yes

The text used to generate video.

A calico cat playing a piano on stage

input_reference

string

No

Optional image reference used to guide generation. It must match the resolution of the generated video.

seconds

string

No

Duration of the generated video (in seconds). Default: 4 seconds.

4

size

string

No

Video resolution in the format width × height. Default: 720×1280. Currently, Sora-2 only supports 720×1280 and 1280×720.

720x1280

4. Request Example

5. Response Example

Last updated