Skip to content
Monogram
VideoMax quality

Sora 2 Pro

by OpenAI

Physically convincing scenes with synced audio and strong continuity.

Request accessRead the quickstart

Spec sheet

Model ID
openai/sora-2-pro
Type
Video
Max output
1792 x 1024, 12 s
Speed
Max quality
Sound
Generates audio
Capabilities
  • Text to video
  • Image to video
  • Native audio

About the model

Sora 2 Pro models how the world moves: weight, momentum, collisions and light. It generates matching sound, follows multi-shot directions and keeps characters and settings consistent from cut to cut.

Swap it anytime

Every model takes the same request, so moving to another one means changing the model ID and nothing else.

Call it in a few lines.

curl https://api.monogram.dev/v1/generations \
  -H "Authorization: Bearer $MONOGRAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/sora-2-pro",
    "input": {
      "prompt": "Slow dolly through a 1920s ballroom, chandeliers glowing, couples dancing",
      "duration": 5,
      "aspect_ratio": "16:9",
      "audio": true
    }
  }'

More video models

See all
VideoMax quality

Veo 3.1

Google

Cinematic text and image to video with native sound and dialogue.

Max output1080p, 8 s
VideoFast

Kling 2.5 Turbo

Kuaishou

Fluid, dynamic motion with strong prompt adherence at a fast clip.

Max output1080p, 10 s
VideoBalanced

Seedance 1.5 Pro

ByteDance

Multi-shot storytelling with native audio and lip-synced speech.

Max output720p, 12 s