The Twelve Labs Video Understanding Platform uses state-of-the-art ("SOTA") video understanding foundation models that process contextual, spatial, and temporal information in your videos.
This repository contains quickstart guides and other resources that show how you can integrate the capabilities of the platform into your applications.
To use the platform, you need an API key:
- If you don't have an account, sign up for a free account. No credit card is required to use the Free plan. This plan allows you to index up to 600 minutes of videos, which is sufficient for a small project.
- Go to the API Keys page.
- If you need to create a new key, select the Create API Key button. Enter a name and set the expiration period. The default is 12 months.
- Select the Copy icon next to your key to copy it to your clipboard.
Explore these quickstart notebooks containing complete, executable code that you can customize and extend:
| Capability | Description | Try it |
|---|---|---|
| Search | Find specific moments in your videos using text or image queries. |  |
| Analyze | Analyze videos and generate text based on their content. | |
| Segment | Segment videos into structured, timestamped data. | |
| Embed | Create multimodal embeddings. | |
Access the platform using any of these methods:
Python SDK
Node.js SDK
REST API
- Documentation
- Playground
- Partner integrations
- Sample applications
- Applications built by the community
Twelve Labs welcomes contributions! To suggest improvements or add new examples:
- Review the existing issues.
- Open a new issue to discuss your proposal.
- Submit a pull request with your changes.
Review the documentation first to find answers to your questions. If you can't find the answer, join our Discord community. Our team members actively participate in discussions and provide support.