Skip to main content

OpenAI Sora - Text to Video

Generate richly detailed, dynamic video clips with audio from natural language descriptions or reference images using OpenAI's state-of-the-art Sora models. Built on years of research into multimodal diffusion, Sora brings deep understanding of 3D space, motion, and scene continuity to text-to-video generation.

Endpoint

Request Headers

FieldValue
API-KEY<api-key>
Content-Typeapplication/json

Request Parameters

Field NameTypeExampleDescriptionRequired
typestringTEXT_TO_VIDEOFeature identifier✔️
modelstringsora-2AI model to use (sora-2 or sora-2-pro)✔️
conversationIdstringTEXT_TO_VIDEOConversation context✔️
promptObject.promptstringWide shot of a child flying a red kiteText description of the video to generate✔️
promptObject.secondsnumber4Video duration in seconds (4, 8, or 12)✔️
promptObject.sizestring720x1280Output resolution (widthxheight)✔️
promptObject.reference_image_pathstringimages/2024_example.pngS3 path to optional reference image
promptObject.reference_image_namestringreference.jpgFilename for reference image
promptObject.reference_image_typestringimage/jpegMIME type of reference image

Available Models

Sora 2 (sora-2)

  • Best for: Speed and flexibility, rapid iteration, concepting
  • Use cases: Social media content, prototypes, rough cuts, exploration phase
  • Quality: Good quality results with fast generation
  • Supported resolutions: 720x1280 (Portrait), 1280x720 (Landscape)

Sora 2 Pro (sora-2-pro)

  • Best for: Production-quality output, high fidelity
  • Use cases: High-resolution cinematic footage, marketing assets, professional content
  • Quality: Higher quality, more polished and stable results
  • Supported resolutions:
    • 720x1280 (Portrait)
    • 1280x720 (Landscape)
    • 1024x1792 (Portrait HD)
    • 1792x1024 (Landscape HD)

Reference Image Guidelines

  • Purpose: Acts as the first frame of your video
  • Use cases: Preserving brand assets, characters, or specific environments
  • Format: JPEG, PNG, or WebP
  • Size limit: 10 MB
  • Important: Image dimensions must match target video resolution

Code Examples

curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "TEXT_TO_VIDEO",
"model": "sora-2",
"conversationId": "TEXT_TO_VIDEO",
"promptObject": {
"prompt": "Wide shot of a child flying a red kite in a grassy park, golden hour sunlight, camera slowly pans upward",
"seconds": 8,
"size": "1280x720"
}
}'

Example with Reference Image

curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "TEXT_TO_VIDEO",
"model": "sora-2-pro",
"conversationId": "TEXT_TO_VIDEO",
"promptObject": {
"prompt": "Camera slowly zooms in on the landscape as birds fly across the sky",
"seconds": 12,
"size": "1792x1024",
"reference_image_path": "uploads/user123/landscape.jpg",
"reference_image_name": "landscape.jpg",
"reference_image_type": "image/jpeg"
}
}'

Interactive Playground

API Playground

https://api.1min.ai/api/features
S3 path to reference image (acts as first frame)

Generated cURL Command:

curl -X POST "https://api.1min.ai/api/features" \
-H "API-KEY: <your-api-key>" \
-H "Content-Type: application/json" \
-d '{
"type": "TEXT_TO_VIDEO",
"model": "sora-2",
"conversationId": "TEXT_TO_VIDEO",
"promptObject": {
"prompt": "Wide shot of a child flying a red kite in a grassy park, golden hour sunlight, camera slowly pans upward",
"seconds": 8,
"size": "1280x720"
}
}'

Response

{}