Jockey

Jockey is a unified multimodal model that reasons across video collections. The current version is Jockey 1.0.

Key features

  • Unified multimodal reasoning: Processes all modalities automatically.
  • Natural-language instructions: Describe what you want in natural language instead of selecting which modalities to use.
  • Corpus-level analysis: Reasons across every item in a knowledge store to answer questions.
  • Multi-turn sessions: Maintains conversation context across follow-up requests.
  • Structured output: Returns typed JSON responses when you provide a JSON Schema.
  • Domain-specific behavior: Uses instructions to adapt responses for specific domains, including but not limited to editorial review, compliance, education, or security.

Use cases

  • Corpus overview: Generate responses that reason across your entire video collection
  • Search and discovery: Find moments across videos by describing what you want in natural language
  • Entity extraction: Identify people, places, objects, and other entities across a knowledge store
  • Content organization: Categorize videos by themes, topics, formats, or other useful dimensions
  • Cross-video tracking: Track a subject across multiple videos and reconstruct a timeline of appearances
  • Content assembly: Identify and sequence specific moments into highlight reels or compilations
  • Content enrichment: Analyze existing content through a specific domain lens or schema

Input requirements

The specifications on this page reflect the maximum capabilities of the model. Your actual requirements also depend on the upload method you choose. For details about the available upload methods and the corresponding limits, see the Upload content page.

Video file requirements

  • File size: ≤ 2 GB
  • Resolution: 360x360 to 5184x2160
  • Aspect ratio: Between 1:1 and 1:2.4, or between 2.4:1 and 1:1. For example, you can use 1:1, 4:3, 4:5, 5:4, 16:9, 9:16, or 17:9.
  • Formats: FFmpeg supported
Notes
  • If you upload files using publicly accessible URLs, use direct links to raw video files that play without user interaction or custom video players (example: https://example.com/videos/sample-video.mp4). Video hosting platforms like YouTube and cloud storage sharing links are not supported.

  • For videos in other formats or if you require different options, contact us at support@twelvelabs.io.

Support

For support or feedback regarding Jockey, contact support@twelvelabs.io.