Text-to-Video Generation via OpenAI's Sora 2
Direct short video clips with plain language — subject, camera moves, lighting, mood, even audio cues — straight from a CNAPS Studio flow. Choose sora-2 for fast, everyday generation or sora-2-pro for cinematic, professional-grade output. Runs on OpenAI's servers via API.
🔑 Requires a OpenAI API key
What it does
This node connects your CNAPS Studio flows to OpenAI's Sora 2 video generation models through the OpenAI API. Describe what you want in natural language — including cinematic direction, camera angles, lighting, mood, and audio cues — and the node returns a generated video clip. Because generation runs on OpenAI's servers, you get top-tier generative quality without hosting any model locally.
Problem it solves
- Video generation without infrastructure — No GPUs to provision, no weights to download. The node calls OpenAI's hosted models directly.
- Quality/speed trade-off in one node — Switch between
sora-2-pro(cinematic quality, professional production) andsora-2(fast generation, everyday creation) without changing your flow. - Video inside a pipeline — Chain generated clips into downstream CNAPS Studio nodes (upscaling, compare, batch processing) instead of juggling separate tools
Configuring the Node
Basic Settings
Model name
Model | Best For |
sora-2-pro | Cinematic quality, professional production |
sora-2 | Fast generation, everyday video creation |
System prompt or instruction for video generation
- Your main instruction for what to generate. Supports natural language including cinematic direction, camera angles, lighting, mood, audio cues, and style references.
Aspect ratio of the generated video
720x1280,1280x720,1024x1792,1792x1024
Video-specific settings
- Clip durations in seconds: 4, 8, 12
How Sora 2 compares
Sora 2 is one of two external video generation options in CNAPS Studio:
Sora 2 | Veo 3.1 | |
Provider | OpenAI | Google |
Best for | Fast everyday creation ( sora-2), cinematic production (sora-2-pro) | Cinematic video with synced audio, iterative/social content ( veo-3.1-fast) |
Clip durations | 4 / 8 / 12 s | 4 / 6 / 8 s |
Output resolution control | — (aspect-ratio presets) | 720p / 1080p / 4K |
Negative prompt | ❌ | ✅ |
Seed control | ❌ | ✅ |
Both run inside CNAPS Studio — compare outputs side-by-side with the Video Compare tool, or chain them into a larger pipeline.
Compliance & Provenance
Provider | OpenAI |
Provider type | GPAI — General-Purpose AI (GPAI) |
License | OpenAI Commercial Terms |
EU AI Act risk class | Limited Risk |
Art. 50 transparency | Required — outputs are marked. See AI Policy §2. |
Region availability | Available globally |
Training data summary |
For more on how we classify models and mark outputs, see our AI Policy.