Generate videos from text descriptions with OpenAI’s Sora 2 model. Supports multiple duration options and aspect ratios.
| Property | Value |
|---|
| Provider | OpenAI |
| Model | Sora 2 |
| Capability | Text to Video |
| Base Cost | 100,000 micro-cents/second ($0.10/sec) |
| Processing Time | ~180 seconds |
Request Body
Model slug. Use openai/sora-2/text-to-video for text-to-video generation.
Input parameters for text-to-video generation.
Text description of the video to generate (max 1000 characters).
Video aspect ratio. Default: 16:9. Options: 16:9, 9:16.
Video duration in seconds. Default: 4. Options: 4, 8, 12.
HTTPS URL to receive a webhook notification when the job completes or fails.
Pricing
Base cost: 100,000 micro-cents per second ($0.10/sec)
finalCost = baseCost × duration
| Factor | Option | Multiplier |
|---|
| Duration | 4 | 4x |
| 8 | 8x |
| 12 | 12x |
Default cost: 4 seconds = 100,000 × 4 = 400,000 micro-cents ($0.40)
Response
Unique identifier for the submitted job.
Initial job status. Always "pending" on successful submission.
ISO 8601 timestamp of the estimated completion time.
The cost of the job in micro-cents.
Code Examples
curl -X POST https://api.muvi.video/v1/jobs/submit \
-H "Authorization: Bearer $PIXELBYTE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/sora-2/text-to-video",
"input": {
"prompt": "A timelapse of a flower blooming in a garden",
"aspect_ratio": "16:9",
"duration": "8"
}
}'