Machine Readiness
Stored receipt and evidence
20
65
0
0
0
Samples
No stored offer samples.
Samples
No stored action samples.
Samples
No stored product samples.
Document
User-agent: * Allow: / Sitemap: https://www.twelvelabs.io/sitemap.xml
Document
# TwelveLabs > TwelveLabs is a multimodal AI company that builds video-native foundation models and provides a Video Intelligence API Platform. Developers use the TwelveLabs API to search, analyze, and embed video content using natural language and other modalities. The platform is built around two proprietary foundation models: Marengo (multimodal video embedding and semantic search) and Pegasus (video-language generation, understanding, and analysis). TwelveLabs enables developers to index video libraries at scale and query them with text, images, or composed queries — without manual tagging or annotation. Use cases span media and entertainment, sports, manufacturing, security, advertising, automotive, education, and enterprise video intelligence. ## Product - [Product Overview](https://www.twelvelabs.io/product/product-overview): Full platform capabilities and how Marengo and Pegasus work together. - [Video Search](https://www.twelvelabs.io/product/video-search): Semantic search across indexed video libraries using text, image, audio, or composed queries. Find any moment in video using natural language. - [Analyze](https://www.twelvelabs.io/product/analyze): Video-to-text generation and structured understanding using Pegasus. Extract chapters, summaries, highlights, sentiment, and open-ended Q&A from any video. - [Embed](https://www.twelvelabs.io/product/embed): Generate multi-vector video embeddings with Marengo for similarity search, clustering, and vector database integration. - [Models Overview](https://www.twelvelabs.io/product/models-overview): Marengo and Pegasus model specifications, capabilities, version history, and performance benchmarks. ## Developer Resources - [Documentation](https://docs.twelvelabs.io): Quickstart guides, API reference, SDK documentation, concept explanations, and integration tutorials. - [Developer Hub](https://www.twelvelabs.io/developer-hub): Sample applications, integration guides, SDKs, and tutorials for building with Twelve Labs. - [Sample Apps](https://www.twelvelabs.io/sample-apps): Reference implementations across video search, analysis, and embedding use cases. - [Whitepapers](https://www.twelvelabs.io/whitepapers): Technical deep-dives on video intelligence architecture and multimodal AI. - [Research](https://www.twelvelabs.io/research): Video-native and multimodal AI research from the Twelve Labs team. ## Pricing & Enterprise - [Pricing](https://www.twelvelabs.io/pricing): API usage tiers, free tier details, and paid plan options. - [Pricing Calculator](https://www.twelvelabs.io/pricing-calculator): Estimate API costs for your video indexing and query volume. - [Enterprise](https://www.twelvelabs.io/enterprise): Custom contracts, SLAs, dedicated infrastructure, and enterprise support options. ## Solutions by Industry - [Media & Entertainment](https://www.twelvelabs.io/solutions/media-and-entertainment): Video search and intelligence for broadcasters, streaming platforms, and content archives. - [Government & Security](https://www.twelvelabs.io/solutions/government-and-security): Video intelligence for security operations, surveillance analysis, and public safety. - [Advertising](https://www.twelvelabs.io/solutions/advertising): Brand safety, sponsorship measurement, and contextual video advertising intelligence. - [Automotive](https://www.twelvelabs.io/solutions/automotive): Video understanding for vehicle safety systems, manufacturing QA, and fleet intelligence. ## Case Studies - [Case Studies Overview](https://www.twelvelabs.io/case-studies): Enterprise video AI results across sports, media, marketing, and government. - [Dyn Sport](https://www.twelvelabs.io/case-studies/dyn-sport): Sports broadcast video intelligence. - [MLSE](https://www.twelvelabs.io/case-studies/mlse): Semantic video search applied to live and archived sports content. - [Affiliate Network](https://www.twelvelabs.io/case-studies/affiliatenetwork): Video analysis for affiliate marketing and performance measurement. - [Protege](https://www.twelvelabs.io/case-studies/protege): Video understanding for talent development and coaching. - [SBS](https://www.twelvelabs.io/case-studies/sbs): Broadcast media video search and content management. ## Partners & Integrations - [Partners Overview](https://www.twelvelabs.io/partners): Technology and solution partners. - [NVIDIA](https://www.twelvelabs.io/partners/nvidia): GPU infrastructure and AI acceleration partnership. - [AWS](https://www.twelvelabs.io/partners/aws): Amazon Web Services integration — Marengo and Pegasus available on Amazon Bedrock. - [Databricks](https://www.twelvelabs.io/partners/databricks): Data lakehouse integration for video intelligence at scale. - [Snowflake](https://www.twelvelabs.io/partners/snowflake): Video AI integrated with Snowflake Cortex for enterprise data workflows. - [Monks](https://www.twelvelabs.io/partners/monks): Creative and media production partnership. ## Blog — Model Releases & Research - [Marengo 3.0 Release](https://www.twelvelabs.io/blog/marengo-3-0): Latest generation of the Marengo multimodal embedding model. - [Introducing Pegasus 1.2](https://www.twelvelabs.io/blog/introducing-pegasus-1-2): Video-language model update with enhanced generation capabilities. - [Introducing Pegasus 1](https://www.twelvelabs.io/blog/introducing-pegasus-1): Original Pegasus model release — video understanding and generation. - [Introducing Marengo 2.7](https://www.twelvelabs.io/blog/introducing-marengo-2-7): Advanced multi-vector video embedding model. - [Introducing Marengo 2.6](https://www.twelvelabs.io/blog/introducing-marengo-2-6): Previous generation Marengo embedding model. - [Upgrading Pegasus 1](https://www.twelvelabs.io/blog/upgrading-pegasus-1): Iterative improvements to the Pegasus model family. - [TWLV-I Model](https://www.twelvelabs.io/blog/twlv-i): Internal model research announcement. - [Multimodal Embeddings](https://www.twelvelabs.io/blog/multimodal-embeddings): Technical guide to multi-vector video embeddings. - [NeurIPS 2024 Workshop Recap](https://www.twelvelabs.io/blog/neurips-2024-workshop-recap): Research presented at NeurIPS 2024. - [Foundation Models Are Going Multimodal](https://www.twelvelabs.io/blog/foundation-models-are-going-multimodal): Technical perspective on multimodal AI and video understanding. - [What Makes Foundation Models Special](https://www.twelvelabs.io/blog/what-makes-foundation-models-special): Deep dive into foundation model architecture for video. - [What Is Multimodal AI](https://www.twelvelabs.io/blog/what-is-multimodal-ai): Primer on multimodal AI and its applications. - [Building Multimodal Video Foundation Models](https://www.twelvelabs.io/blog/twelve-labs-building-multimodal-video-foundation-models-for-better-understanding): Technical overview of Twelve Labs' model development approach. ## Blog — Technical Guides & Tutorials - [Context Engineering for Video Understanding](https://www.twelvelabs.io/blog/context-engineering-for-video-understanding): Advanced techniques for video AI prompting. - [Video Deep Research](https://www.twelvelabs.io/blog/video-deep-research): Using video intelligence for deep research workflows. - [Technical Guide to MCP for Advanced Use Cases](https://www.twelvelabs.io/blog/technical-guide-to-using-twelvelabs-mcp-for-advanced-use-cases): Advanced Model Context Protocol integration patterns. - [How TwelveLabs Users Use Pegasus](https://www.twelvelabs.io/blog/how-twelvelabs-users-use-pegasus): Real-world Pegasus usage patterns from the developer community. - [Indexing 3.0 Part 1](https://www.twelvelabs.io/blog/indexing-3-0-part-1): Next-generation video indexing architecture. - [Automated Video Data Labeler](https://www.twelvelabs.io/blog/automated-video-data-labeler): Using Pegasus for automated video annotation. - [Video OCR Using Twelve Labs API](https://www.twelvelabs.io/blog/how-to-perform-video-ocr-using-twelve-labs-api): Extract on-screen text from video. - [Logo Detection Using Twelve Labs API](https://www.twelvelabs.io/blog/perform-logo-detection-using-twelve-labs-api): Brand and logo detection in video. - [Search by Combining Queries](https://www.twelvelabs.io/blog/search-by-combining-queries-with-twelve-labs-api): Composed query search tutorial. - [Find Specific Moments in Video](https://www.twelvelabs.io/blog/find-specific-moments-within-your-video-using-twelve-labs-simple-search-api): Simple search API tutorial. - [Effortless Video Classifiers](https://www.twelvelabs.io/blog/effortless-video-classifiers-with-twelve-labs-api-no-ml-training-required): Zero-shot video classification without ML training. ## Blog — AI Agent & Agentic Workflows - [Video Intelligence Is Going Agentic](https://www.twelvelabs.io/blog/video-intelligence-is-going-agentic): How AI agents are using video intelligence APIs. - [Twelve Labs MCP Server](https://www.twelvelabs.io/blog/twelve-labs-mcp-server): Model Context Protocol server for AI agent video access. - [Twelve Labs MCP and Sora MCP](https://www.twelvelabs.io/blog/twelve-labs-mcp-and-sora-mcp): Integrating video generation and understanding via MCP. - [Twelve Labs and Strands Agents](https://www.twelvelabs.io/blog/twelve-labs-and-strands-agents): Agentic video intelligence with AWS Strands. - [Introducing Jockey](https://www.twelvelabs.io/blog/introducing-jockey): Video intelligence AI agent framework. ## Blog — Integrations & Partnerships - [Twelve Labs on Amazon Bedrock](https://www.twelvelabs.io/blog/twelvelabs-x-aws-amazon-bedrock): Deploying Marengo and Pegasus through AWS Bedrock. - [Marengo and Pegasus on Amazon Bedrock](https://www.twelvelabs.io/blog/marengo-pegasus-on-amazon-bedrock): Detailed Bedrock integration guide. - [Twelve Labs and Databricks Mosaic AI](https://www.twelvelabs.io/blog/twelve-labs-and-databricks-mosaic-ai): Data lakehouse video intelligence integration. - [Twelve Labs and Snowflake Cortex](https://www.twelvelabs.io/blog/twelve-labs-and-snowflake-cortex): Video AI in Snowflake data workflows. - [Twelve Labs and Elastic Search](https://www.twelvelabs.io/blog/twelve-labs-and-elastic-search): Vector search integration with Elasticsearch. - [Twelve Labs and Pinecone](https://www.twelvelabs.io/blog/twelve-labs-and-pinecone): Video embeddings in Pinecone vector database. - [Twelve Labs and Weaviate](https://www.twelvelabs.io/blog/twelve-labs-and-weaviate): Video intelligence with Weaviate vector search. - [Twelve Labs and MongoDB](https://www.twelvelabs.io/blog/twelve-labs-and-mongodb): Video search integrated with MongoDB. - [Twelve Labs and Milvus](https://www.twelvelabs.io/blog/twelve-labs-and-milvus): Milvus vector database integration. - [Twelve Labs and LanceDB](https://www.twelvelabs.io/blog/twelve-labs-and-lancedb): LanceDB multimodal vector store integration. - [Twelve Labs and Qdrant](https://www.twelvelabs.io/blog/twelve-labs-and-qdrant): Qdrant vector database integration. - [Twelve Labs and Oracle 23ai](https://www.twelvelabs.io/blog/twelve-labs-and-oracle-23ai): Oracle AI vector search integration. - [Marengo and S3 Vectors](https://www.twelvelabs.io/blog/marengo-and-s3-vectors): AWS S3 Vectors integration with Marengo embeddings. - [Twelve Labs and Mux](https://www.twelvelabs.io/blog/twelve-labs-and-mux): Video delivery and intelligence integration with Mux. - [Twelve Labs and Frame.io](https://www.twelvelabs.io/blog/twelve-labs-and-frame-io): Creative video workflow integration with Frame.io. - [Twelve Labs and VideoDB](https://www.twelvelabs.io/blog/twelve-labs-and-videodb): VideoDB integration for video storage and search. - [Twelve Labs and n8n](https://www.twelvelabs.io/blog/twelve-labs-and-n8n): Low-code automation workflow integration. - [Twelve Labs and Langflow](https://www.twelvelabs.io/blog/twelve-labs-and-langflow): Visual LLM workflow builder integration. - [Twelve Labs and Pixeltable](https://www.twelvelabs.io/blog/twelve-labs-and-pixeltable): Data orchestration for multimodal AI pipelines. - [Twelve Labs and Vespa](https://www.twelvelabs.io/blog/twelve-labs-and-vespa): Vespa search engine integration. - [Twelve Labs and Chroma](https://www.twelvelabs.io/blog/twelve-labs-and-chroma): Chroma vector database integration. - [Twelve Labs and MindsDB](https://www.twelvelabs.io/blog/twelve-labs-and-mindsdb): MindsDB AI data platform integration. - [Twelve Labs and Voxel51](https://www.twelvelabs.io/blog/twelve-labs-and-voxel51): Computer vision dataset management integration. - [Twelve Labs and Aperture Data](https://www.twelvelabs.io/blog/twelve-labs-and-aperture-data): Unstructured data management integration. - [Twelve Labs and ApertureDB](https://www.twelvelabs.io/blog/twelve-labs-and-aperturedb): ApertureDB multimodal data integration. - [Twelve Labs and MASV](https://www.twelvelabs.io/blog/twelve-labs-and-masv): High-speed video file transfer integration. - [Twelve Labs and Avid](https://www.twelvelabs.io/blog/twelve-labs-and-avid): Professional media production integration. - [Twelve Labs and ROE AI](https://www.twelvelabs.io/blog/twelvel-labs-and-roe-ai): Video AI pipeline integration. - [Twelve Labs and Phyllo](https://www.twelvelabs.io/blog/twelve-labs-and-phyllo): Creator economy video data integration. - [Twelve Labs and LanceDB Geneva](https://www.twelvelabs.io/blog/twelve-labs-and-lancedb-geneva): LanceDB Geneva release integration. ## Blog — Use Cases & Applications - [Sports Analysis](https://www.twelvelabs.io/blog/sports-analysis): AI video intelligence for sports performance and broadcast. - [Manufacturing Automation](https://www.twelvelabs.io/blog/manufacturing-automation): Video AI for industrial manufacturing quality control. - [Security Analysis](https://www.twelvelabs.io/blog/security-analysis): Video intelligence for security monitoring and threat detection. - [Surgical Video Intelligence](https://www.twelvelabs.io/blog/surgical-video-intelligence): Medical video understanding for surgical training and analysis. - [Enterprise Video Analysis](https://www.twelvelabs.io/blog/enterprise-video-analysis): Enterprise-scale video processing and intelligence. - [Brand Sponsorship Measurement](https://www.twelvelabs.io/blog/brand-sponsorship-measurement): Measuring brand exposure in video content. - [Brand Integration Assistant](https://www.twelvelabs.io/blog/brand-integration-assistant): AI-assisted brand placement and measurement. - [Creator Discovery](https://www.twelvelabs.io/blog/creator-discovery): Finding and evaluating video creators using AI. - [Shoppable Video](https://www.twelvelabs.io/blog/shoppable-video): E-commerce video intelligence and product detection. - [Video to Text Arena](https://www.twelvelabs.io/blog/video-to-text-arena): Benchmarking video-to-text generation models. - [Lecture Analysis](https://www.twelvelabs.io/blog/lecture-analysis): Educational video intelligence for lecture indexing. - [Interview Analyzer](https://www.twelvelabs.io/blog/interview-analyzer): AI-powered video interview analysis. - [Olympics Classification](https://www.twelvelabs.io/blog/olympics-classification): Sports event classification using video AI. - [YouTube Chapter Timestamp](https://www.twelvelabs.io/blog/youtube-chapter-timestamp): Automatic chapter generation for YouTube videos. - [Summarize YouTube Video](https://www.twelvelabs.io/blog/summarize-youtube-video): AI-generated video summaries. - [Content Recommender](https://www.twelvelabs.io/blog/content-recommender): Video content recommendation using multimodal embeddings. - [Multilingual Video Transcriber](https://www.twelvelabs.io/blog/multilingual-video-transriber): Multi-language video transcription and search. - [Video MCQ Generator](https://www.twelvelabs.io/blog/video-mcq-generator): Automatic question generation from video content. - [Fashion Chat Assistant](https://www.twelvelabs.io/blog/fashion-chat-assistant): Video-based fashion AI assistant. - [Shade Finder](https://www.twelvelabs.io/blog/shade-finder): Visual product matching in video. - [Worker Safety Dataset](https://www.twelvelabs.io/blog/worker-safety-dataset): Safety compliance video dataset and detection. - [Sage](https://www.twelvelabs.io/blog/sage): Video intelligence for knowledge extraction. - [Video2Game](https://www.twelvelabs.io/blog/video2game): Extracting game data from video content. - [Crop and Seek](https://www.twelvelabs.io/blog/crop-and-seek): Region-of-interest video search. - [Accelerate Film Production](https://www.twelvelabs.io/blog/accelerate-your-film-production-with-twelve-labs): AI-assisted film production workflows. - [Generate Social Posts](https://www.twelvelabs.io/blog/generate-social-posts): Automatic social media post generation from video. - [Generate Titles and Hashtags](https://www.twelvelabs.io/blog/generate-titles-and-hashtags): AI-generated video titles and hashtags. - [Video Intelligence Transforms Storage Costs](https://www.twelvelabs.io/blog/video-intelligence-transforms-storage-costs-into-strategic-assets): ROI analysis of video intelligence for storage optimization. ## Blog — Company & Announcements - [Series A: $12M Funding](https://www.twelvelabs.io/blog/series-a-announcement): Series A funding round announcement. - [Series B: $30M Funding](https://www.twelvelabs.io/blog/twelve-labs-secures-30-million-in-funding-validating-the-importance-of-twelve-labs-video-understanding-technology-to-the-ai-ecosystem): Series B funding validation of video understanding AI. - [Twelve Labs Raises $5M Seed](https://www.twelvelabs.io/blog/twelve-labs-makes-searching-inside-videos-simple-and-powerful-propelled-by-5m-seed-round): Seed round announcement. - [Twelve Labs Named Fast Company Most Innovative 2023](https://www.twelvelabs.io/blog/twelve-labs-named-to-fast-companys-most-innovative-companies-of-2023): Fast Company recognition. - [CB Insights AI 100 (Three Consecutive Years)](https://www.twelvelabs.io/blog/twelve-labs-named-to-the-cb-insights-ai-100-list-for-the-third-consecutive-year): CB Insights AI 100 recognition. - [SOC 2 Type 2 Certification](https://www.twelvelabs.io/blog/our-soc-2-type-2-certification): Security certification announcement. - [NVIDIA-Backed Twelve Labs](https://www.twelvelabs.io/blog/nvidia-backed-twelve-labs-is-building-ai-that-understands-videos-like-humans): NVIDIA backing and product vision. - [Why I Joined Twelve Labs as Chief Scientist](https://www.twelvelabs.io/blog/why-i-joined-twelve-labs-as-the-chief-scientist): Chief Scientist perspective on video AI. - [How a Tiny Startup Beat the Tech Giants in Video Search](https://www.twelvelabs.io/blog/how-a-tiny-startup-beat-the-tech-giants-of-the-world-and-ranked-1-in-video-search-part-1-motivation): Origin story and competitive positioning. - [The Past, Present, and Future of Video Understanding](https://www.twelvelabs.io/blog/the-past-present-and-future-of-video-understanding-applications): History and roadmap of video AI. - [A Tour of Video Understanding Use Cases](https://www.twelvelabs.io/blog/a-tour-of-video-understanding-use-cases): Comprehensive overview of application domains. - [Companies Commercializing Multimodal AI](https://www.twelvelabs.io/blog/companies-are-commercializing-multimodal-ai-models-to-analyze-videos-and-more): Industry landscape for multimodal AI commercialization. - [NAB 2024 Innovation Recap](https://www.twelvelabs.io/blog/nab-2024-the-bold-innovations-you-probably-missed-at-the-show): NAB Show 2024 highlights and trends. ## Company - [About Twelve Labs](https://www.twelvelabs.io/about-us): Company background, mission, and the video-native AI approach. - [Careers](https://www.twelvelabs.io/careers): Open roles at Twelve Labs. - [Press](https://www.twelvelabs.io/press): Media coverage and press releases. - [Security](https://www.twelvelabs.io/security): Security practices, SOC 2 Type 2 certification, and compliance. - [Patents](https://www.twelvelabs.io/patents): Twelve Labs intellectual property. - [Contact](https://www.twelvelabs.io/contact): Get in touch with the Twelve Labs team. ## Optional - [Become a Partner](https://www.twelvelabs.io/become-a-partner): Technology and solution partner program. - [Explore](https://www.twelvelabs.io/explore): Interactive product exploration. - [NAB Show 2026](https://www.twelvelabs.io/nab-show-26): Twelve Labs at NAB Show 2026. - [AWS Re:Invent](https://www.twelvelabs.io/aws-reinvent): Twelve Labs at AWS Re:Invent. - [Amazon Bedrock eBook](https://www.twelvelabs.io/twelvelabs-amazon-bedrock-ebook): Building video intelligence apps on Amazon Bedrock. - [Privacy Policy](https://www.twelvelabs.io/privacy-policy): Data handling and privacy practices. - [Terms of Use](https://www.twelvelabs.io/terms-of-use): Service terms. - [DPA](https://www.twelvelabs.io/dpa): Data Processing Agreement for enterprise customers. - [AUP](https://www.twelvelabs.io/aup): Acceptable Use Policy. - [AI Standard Clauses](https://www.twelvelabs.io/ai-standard-clauses): AI-specific contractual terms.
Document
Not stored for this site.