API docs / Video models

Sora 2 API

Generates videos with synchronized audio from text prompts or images. Creates richly detailed, dynamic video clips with sophisticated background soundscapes, dialogue, and sound effects. Features advanced physics simulation including gravity, momentum, buoyancy, and object permanence. Supports multi-shot sequences with consistent characters, environments, and lighting across scene transitions. Offers fine-grained control over camera movements, framing, lighting, and composition. Excels at various aesthetic styles including realistic, cinematic, and anime. Capable of generating accurate lip-sync for speaking characters. Supports portrait and landscape aspect ratios with durations of 4, 8, or 12 seconds.

Model id
openai/sora-2
Provider
openai
Output
Video
Price
From 140 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "openai/sora-2". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "openai/sora-2",
  "input": {
    "prompt": "A red fox standing in fresh snow at golden hour, soft light"
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
promptrequiredstring

A text description of the video to generate

first_framearray of URLs

An optional image to use as the first frame of the video. The image must be the same aspect ratio as the video.

Up to 1 files · Accepts image/*

aspect_ratiostring

Default: portrait

One of: portrait, landscape

duration_secondsnumber

Default: 4

One of: 4, 8, 12