Sora
by OpenAI · unknown · Last verified 2026-03-17
Sora is a text-to-video diffusion transformer model by OpenAI that generates high-fidelity, minute-long videos from textual prompts. It demonstrates an advanced understanding of language and the physical world, enabling complex scenes with multiple characters, specific motions, and coherent narratives.
https://openai.com/sora ↗B
B—Above Average
Adoption: BQuality: A+Freshness: ACitations: A+Engagement: F
Specifications
- License
- Proprietary
- Pricing
- unknown
- Capabilities
- text-to-video generation, image-to-video animation, video-to-video style transfer, video extension and looping, complex camera motion simulation, long-range coherence and object permanence, dynamic physics simulation, character and style consistency
- Integrations
- Use Cases
- [object Object], [object Object], [object Object], [object Object], [object Object]
- API Available
- No
- Parameters
- Undisclosed
- Context Window
- N/A
- Modalities
- text, image, video
- Training Cutoff
- 2024
- Tags
- video-generation, text-to-video, openai, diffusion-transformer, world-model, generative-ai, ai-video, creative-tool, multimodal-ai, simulation, ai-film
- Added
- 2026-03-17
- Completeness
- 0.9%
Index Score
68Adoption
65
Quality
95
Freshness
85
Citations
92
Engagement
0