" height="1.90314px" id="wtDTm6bEW" transform="translate(26.225 0)" width="2.4723000000000006px"/>)](/content/ja/index.html)

プラットフォーム

価格

ソリューション

構築

資料

会社

Select LanguageEnglishKoreanJapanese

Playground

営業担当に相談する\ \ " height="9.18705px" id="AiyYyR90G" transform="translate(3.406 3.406)" width="9.18685px"/>)

ブログ

Welcome to everything that’s happening at TwelveLabs, from product updates to new tutorials.

All

会社

Partnerships

プレス

Product

Tutorials

Research

트웰브랩스

\ \ Multi-Source Legal Evidence Reporting: Building an Investigation Platform with TwelveLabs via AWS Bedrock and NeMo Retriever](/content/ja/blog/legal-evidence-investigator/index.html) \ \ Pegasus 1.5를 만든 사람들](/content/ja/blog/pegasus-1-5-seoul-builders/index.html) \ \ Building Pegasus 1.5: From Clip-Based QA to Time-Based Metadata](/content/ja/blog/introducing-pegasus-1-5/index.html) \ \ 의미의 경계를 찾아서: 영상을 이해하는 임베딩을 만드는 사람](/content/ja/blog/dankim-marengo-research-interview/index.html) \ \ Rebuilding Our HLS Pipeline In House: How TwelveLabs Eliminated a Costly Playback Bottleneck](/content/ja/blog/in-house-hls-pipeline-engineering/index.html) \ \ 밖에서는 잔잔한 항해처럼 보이지만, 안은 폭풍 속이에요](/content/ja/blog/estherkim-eng-interview/index.html) \ \ Why Video Understanding Is the Most Important Infrastructure Decision in Media Right Now](/content/ja/blog/the-most-important-decision-in-media-right-now/index.html) \ \ 영상에 진심인 곳은 전 세계에 몇 군데 없어요](/content/ja/blog/kiankim-pegasus-research-interview/index.html) \ \ Video vs Text for Public Sector: A Video-Native Case For Spatio-Temporal Reasoning with Marengo and Pegasus](/content/ja/blog/video-vs-text-for-public-sector/index.html) \ \ The Design Choices Behind Indexing 3.0: Consolidation, Packaging, Execution, and Deployment](/content/ja/blog/indexing-3-0-part-2/index.html) \ \ 아무리 뛰어난 모델도, 안 쓰이면 ‘신기하다’에서 끝이에요](/content/ja/blog/sjkim-mle-interview/index.html) \ \ Prologue - 트웰브랩스 한국팀 블로그를 시작하며](/content/ja/blog/prologue/index.html) \ \ Announcing TwelveLabs Claude Code Plugin: Work With Videos Without Leaving Your Terminal](/content/ja/blog/claude-code-plugin/index.html) \ \ The Apparatus: Building the Machine That Runs While We Don't](/content/ja/blog/the-apparatus-building-the-machine-that-runs-while-we-don-t/index.html) \ \ How TwelveLabs Saves Hours of Manual Video Annotation with a Few API Calls](/content/ja/blog/automated-video-data-labeler/index.html) \ \ From Raw Surveillance to Training-Ready Datasets in Minutes: Building an Automated Video Curator with TwelveLabs and FiftyOne](/content/ja/blog/worker-safety-dataset/index.html) \ \ From Manual Review to Automated Intelligence: Building a Surgical Video Analysis Platform with YOLO and Twelve Labs](/content/ja/blog/surgical-video-intelligence/index.html) \ \ Automate Video Analysis and Semantic Search with n8n and TwelveLabs](/content/ja/blog/twelve-labs-and-n8n/index.html) \ \ From Microservices Mesh to Streamlined Layers: Why We Rebuilt Our Internal Video Indexing System](/content/ja/blog/indexing-3-0-part-1/index.html) \ \ Building Cross-Modal Video Search with TwelveLabs and Pixeltable](/content/ja/blog/twelve-labs-and-pixeltable/index.html) \ \ Solving Compliance Video Intelligence: A Hands-On Guide with Mux and TwelveLabs MCP Servers](/content/ja/blog/twelve-labs-and-mux/index.html) \ \ Building Recurser: Iterative AI Video Enhancement with TwelveLabs and Google Veo](/content/ja/blog/recurser/index.html) \ \ Building an AI-Powered Sponsorship ROI Analysis Platform with TwelveLabs](/content/ja/blog/brand-sponsorship-measurement/index.html) \ \ Building SAGE: Semantic Video Comparison with TwelveLabs Embeddings](/content/ja/blog/sage/index.html) \ \ Building a Multi-Sport Video Analysis System with TwelveLabs API](/content/ja/blog/sports-analysis/index.html) \ \ Building An Enterprise Video Analysis Agent on AWS AgentCore with TwelveLabs and Strands Agent](/content/ja/blog/enterprise-video-analysis/index.html) \ \ Elevating AI Content Creation with Sora 2 and TwelveLabs MCP](/content/ja/blog/twelve-labs-mcp-and-sora-mcp/index.html) \ \ Marengo 3.0: Video Intelligence Turns Video Into Strategic Assets](/content/ja/blog/video-intelligence-transforms-storage-costs-into-strategic-assets/index.html) \ \ Marengo 3.0: Defining Real-World Embedding AI for Videos, Audios, Texts, Images, and Composition of Them](/content/ja/blog/marengo-3-0-blog/index.html) \ \ From Manual Search to Instant Discovery: Bringing TwelveLabs Video Intelligence Capabilities to Frame.io Workflows](/content/ja/blog/twelve-labs-and-frame-io/index.html) \ \ Video-to-Text Arena: From Pixels to Text with Video-Language Models](/content/ja/blog/video-to-text-arena/index.html) \ \ Join Twelve Labs at AWS re:Invent 2025](/content/ja/blog/join-twelve-labs-at-aws-re-invent-2025/index.html) \ \ Teaching Agents to Understand Video: TwelveLabs Integration with Strands Agents](/content/ja/blog/twelve-labs-and-strands-agents/index.html) \ \ Search, Match, Measure: A Full‑Stack Creator Platform with Twelve Labs](/content/ja/blog/creator-discovery/index.html) \ \ Building A Workplace Safety Compliance Application with TwelveLabs and NVIDIA VSS](/content/ja/blog/manufacturing-automation/index.html) \ \ How TwelveLabs Users Use Pegasus](/content/ja/blog/how-twelvelabs-users-use-pegasus/index.html) \ \ A Technical Guide to using TwelveLabs MCP for Advanced Use Cases](/content/ja/blog/technical-guide-to-using-twelvelabs-mcp-for-advanced-use-cases/index.html) \ \ Every Video Revolution Evolved What Stories We Could Tell](/content/ja/blog/every-video-revolution-evolved-what-stories-we-could-tell/index.html) \ \ Why I Joined TwelveLabs](/content/ja/blog/why-i-joined-twelvelabs/index.html) \ \ Building Video Deep Research with TwelveLabs and Perplexity Sonar](/content/ja/blog/video-deep-research/index.html) \ \ Context Engineering for Video Understanding](/content/ja/blog/context-engineering-for-video-understanding/index.html) \ \ Finding Needles in Video Haystacks: Building Intelligent Video Search with TwelveLabs Marengo, Amazon Bedrock, and Elasticsearch](/content/ja/blog/twelve-labs-and-elastic-search/index.html) \ \ Bring Video Intelligence to Your Agents with TwelveLabs MCP Server](/content/ja/blog/twelve-labs-mcp-server/index.html) \ \ Building An AI-Powered Lecture Analysis Platform with TwelveLabs API](/content/ja/blog/lecture-analysis/index.html) \ \ Building Semantic Video Recommendations with TwelveLabs and LanceDB](/content/ja/blog/twelve-labs-and-lancedb-geneva/index.html) \ \ From Embeddings to Insights: Hands-On Cross-Modal Search with TwelveLabs Marengo and S3 Vectors](/content/ja/blog/marengo-and-s3-vectors/index.html) \ \ Building A Shoppable Video Application with TwelveLabs API](/content/ja/blog/shoppable-video/index.html) \ \ From MP4 to API: End-to-End Video Understanding with Marengo & Pegasus on AWS Bedrock](/content/ja/blog/marengo-pegasus-on-amazon-bedrock/index.html) \ \ Unlock Real-Time Video Understanding with VideoDB and TwelveLabs](/content/ja/blog/twelve-labs-and-videodb/index.html) \ \ Building an Interactive Learning App from Video Content](/content/ja/blog/video2game/index.html) \ \ TwelveLabs x AWS Amazon Bedrock](/content/ja/blog/twelvelabs-x-aws-amazon-bedrock/index.html) \ \ Building Brand Integration Assistant and Ad Break Finder App with Twelve Labs](/content/ja/blog/brand-integration-assistant/index.html) \ \ Building a Security Analysis Application with Twelve Labs](/content/ja/blog/security-analysis/index.html) \ \ Building a Multimodal Retrieval-Augmented Generation Application with Twelve Labs and Milvus](/content/ja/blog/fashion-chat-assistant/index.html) \ \ Pegasus 1.2: An Industry-Grade Video Language Model for Scalable Applications](/content/ja/blog/introducing-pegasus-1-2/index.html) \ \ The State of Video-Language Models: Research Insights from the Inaugural NeurIPS Workshop](/content/ja/blog/neurips-2024-workshop-recap/index.html) \ \ What makes Foundation Models special?](/content/ja/blog/what-makes-foundation-models-special/index.html) \ \ How to identify the right influencer partner using Twelve Labs API?](/content/ja/blog/who-talked-about-us/index.html) \ \ Why I joined Twelve Labs as the Chief Scientist](/content/ja/blog/why-i-joined-twelve-labs-as-the-chief-scientist/index.html) \ \ Building a Video Highlight Generator with Twelve Labs](/content/ja/blog/youtube-chapter-timestamp/index.html) \ \ TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models](/content/ja/blog/twlv-i/index.html) \ \ Pegasus 1 Beta: Setting New Standards in Video-Language Modeling](/content/ja/blog/upgrading-pegasus-1/index.html) \ \ Building a Video Content Quiz Generator with Twelve Labs](/content/ja/blog/video-mcq-generator/index.html) \ \ What Is Multimodal AI?](/content/ja/blog/what-is-multimodal-ai/index.html) \ \ Twelve Labs is building AI that can analyze and search through videos](/content/ja/blog/twelve-labs-is-building-ai-that-can-analyze-and-search-through-videos/index.html) \ \ Twelve Labs lands $12M for AI that understands the context of videos](/content/ja/blog/twelve-labs-lands-12m-for-ai-that-understands-the-context-of-videos/index.html) \ \ Twelve Labs launches transformative AI-powered video search platform](/content/ja/blog/twelve-labs-launches-transformative-ai-powered-video-search-platform/index.html) \ \ Twelve Labs makes searching inside videos simple and powerful, propelled by $5M seed round](/content/ja/blog/twelve-labs-makes-searching-inside-videos-simple-and-powerful-propelled-by-5m-seed-round/index.html) \ \ Twelve Labs named to Fast Company’s Most Innovative Companies of 2023](/content/ja/blog/twelve-labs-named-to-fast-companys-most-innovative-companies-of-2023/index.html) \ \ Twelve Labs Named to the CB Insights AI 100 List for the Third Consecutive Year](/content/ja/blog/twelve-labs-named-to-the-cb-insights-ai-100-list-for-the-third-consecutive-year/index.html) \ \ Twelve Labs Partners With Blackbird to Craft the Future of Narrative Excellence Through Video](/content/ja/blog/twelve-labs-partners-with-blackbird-to-craft-the-future-of-narrative-excellence-through-video/index.html) \ \ Twelve Labs Secures $30 Million in Funding, Validating the Importance of Twelve Labs' Video Understanding Technology to the AI Ecosystem](/content/ja/blog/twelve-labs-secures-30-million-in-funding-validating-the-importance-of-twelve-labs-video-understanding-technology-to-the-ai-ecosystem/index.html) \ \ Supercharge Your Video Search with Twelve Labs and Roe AI](/content/ja/blog/twelvel-labs-and-roe-ai/index.html) \ \ Mastering Multimodal AI: Advanced Video Understanding with Twelve Labs + Databricks Mosaic AI](/content/ja/blog/twelve-labs-and-databricks-mosaic-ai/index.html) \ \ Building Advanced Video Understanding Applications: Integrating Twelve Labs Embed API with LanceDB for Multimodal AI](/content/ja/blog/twelve-labs-and-lancedb/index.html) \ \ Multimodal AI and How Video Understanding Will Revolutionize Media](/content/ja/blog/twelve-labs-and-masv/index.html) \ \ Advanced Video Search: Leveraging Twelve Labs and Milvus for Semantic Retrieval](/content/ja/blog/twelve-labs-and-milvus/index.html) \ \ Build a Powerful Video Summarization Tool with Twelve Labs, MindsDB, and Slack](/content/ja/blog/twelve-labs-and-mindsdb/index.html) \ \ Building Semantic Video Search with Twelve Labs Embed API and MongoDB Atlas](/content/ja/blog/twelve-labs-and-mongodb/index.html) \ \ Unlocking Video Insights: The Power of Phyllo and Twelve Labs Collaboration](/content/ja/blog/twelve-labs-and-phyllo/index.html) \ \ Multimodal RAG: Chat with Videos Using Twelve Labs and Pinecone](/content/ja/blog/twelve-labs-and-pinecone/index.html) \ \ Search Your Videos Semantically with Twelve Labs and FiftyOne Plugin](/content/ja/blog/twelve-labs-and-voxel51/index.html) \ \ Twelve Labs: Building Multimodal Video Foundation Models for Better Understanding](/content/ja/blog/twelve-labs-building-multimodal-video-foundation-models-for-better-understanding/index.html) \ \ Twelve Labs introduces new API Playground to foster video search innovation and adoption](/content/ja/blog/twelve-labs-introduces-new-api-playground-to-foster-video-search-innovation-and-adoption/index.html) \ \ Our Series A to Build the Future of Multimodal AI](/content/ja/blog/series-a-announcement/index.html) \ \ Building a Shade Finder App: Using Twelve Labs' API to Pinpoint Specific Colors in Videos](/content/ja/blog/shade-finder/index.html) \ \ How to Automatically Get a Written Summary of a YouTube Video?](/content/ja/blog/summarize-youtube-video/index.html) \ \ The Past, Present, and Future of Video Understanding Applications](/content/ja/blog/the-past-present-and-future-of-video-understanding-applications/index.html) \ \ To make the world’s videos searchable, Twelve Labs raises $5M](/content/ja/blog/to-make-the-worlds-videos-searchable-twelve-labs-raises-5m/index.html) \ \ Managing Video Data with ApertureDB and Twelve Labs](/content/ja/blog/twelve-labs-and-aperture-data/index.html) \ \ Semantic Video Search Engine with TwelveLabs and ApertureDB](/content/ja/blog/twelve-labs-and-aperturedb/index.html) \ \ Semantic Content Discovery for a Post-Production World](/content/ja/blog/twelve-labs-and-avid/index.html) \ \ NAB 2024: The Bold Innovations You Probably Missed at the Show](/content/ja/blog/nab-2024-the-bold-innovations-you-probably-missed-at-the-show/index.html) \ \ Lights, Camera, AI-ction: Twelve Labs Brings Video-Language Models to Center Stage at NeurIPS 2024](/content/ja/blog/neurips-2024-workshop-announcement/index.html) \ \ Nvidia-backed Twelve Labs is building AI that understands videos like humans](/content/ja/blog/nvidia-backed-twelve-labs-is-building-ai-that-understands-videos-like-humans/index.html) \ \ Twelve Labs featured as a pioneer in multimodal AI in GTC 2023](/content/ja/blog/nvidia-hopper-gpus-expand-reach-as-demand-for-ai-grows/index.html) \ \ Building An Olympic Video Classification Application with Twelve Labs](/content/ja/blog/olympics-classification/index.html) \ \ Our SOC 2 Type 2 Certification](/content/ja/blog/our-soc-2-type-2-certification/index.html) \ \ How to find brand logos within videos using Twelve Labs API?](/content/ja/blog/perform-logo-detection-using-twelve-labs-api/index.html) \ \ Search precisely within videos: combining queries with Twelve Labs API](/content/ja/blog/search-by-combining-queries-with-twelve-labs-api/index.html) \ \ The Multimodal Evolution of Vector Embeddings](/content/ja/blog/multimodal-embeddings/index.html) \ \ Multivector Video Retrieval with TwelveLabs and Vespa](/content/ja/blog/twelve-labs-and-vespa/index.html) \ \ Leveraging RAG for Improved Video Processing Times with TwelveLabs and Weaviate](/content/ja/blog/twelve-labs-and-weaviate/index.html) \ \ Multimodal RAG: Chat with Videos Using TwelveLabs and Chroma](/content/ja/blog/twelve-labs-and-chroma/index.html) \ \ Integrating TwelveLabs Embed API with Snowflake Cortex for Multimodal Video Understanding](/content/ja/blog/twelve-labs-and-snowflake-cortex/index.html) \ \ Unleashing Video Intelligence: A Tutorial for Integrating TwelveLabs Multimodal Embed API with Oracle Database 23ai](/content/ja/blog/twelve-labs-and-oracle-23ai/index.html) \ \ Video Intelligence is Going Agentic](/content/ja/blog/video-intelligence-is-going-agentic/index.html) \ \ Building Video Semantic Recommendation with TwelveLabs Embedding and Qdrant Search](/content/ja/blog/content-recommender/index.html) \ \ From Video to Vector: Building Smart Video Agents with TwelveLabs and Langflow](/content/ja/blog/twelve-labs-and-langflow/index.html) \ \ Building a Semantic Video Search Workflow with TwelveLabs and Qdrant](/content/ja/blog/twelve-labs-and-qdrant/index.html) \ \ TwelveLabs Embed API Beta](/content/ja/blog/introducing-twelve-labs-embed-api-open-beta/index.html) \ \ A Recap of Our Multimodal AI in Media & Entertainment Hackathon in Sunny Los Angeles!](/content/ja/blog/la-hackathon-recap/index.html) \ \ Meet the latest Techstars Seattle cohort: 10 startups on how they’ve adapted to the pandemic](/content/ja/blog/meet-the-latest-techstars-seattle-cohort-10-startups-on-how-theyve-adapted-to-the-pandemic/index.html) \ \ Building a Video Multilingual Transcriber App with Twelve Labs](/content/ja/blog/multilingual-video-transriber/index.html) \ \ Jockey: A Conversational Video Agent Powered by TwelveLabs APIs and LangGraph](/content/ja/blog/introducing-jockey/index.html) \ \ Marengo 2.6: A State-of-the-Art Video Foundation Model for Any-to-Any Search](/content/ja/blog/introducing-marengo-2-6/index.html) \ \ Marengo 2.7: Pioneering Multi-Vector Embeddings for Advanced Video Understanding](/content/ja/blog/introducing-marengo-2-7/index.html) \ \ Introducing Video-To-Text and Pegasus-1 (80B)](/content/ja/blog/introducing-pegasus-1/index.html) \ \ Introducing The Multimodal AI (23Labs) Hackathon](/content/ja/blog/introducing-the-multimodal-ai-23labs-hackathon/index.html) \ \ Effortlessly Craft Social Media Content from Video](/content/ja/blog/generate-social-posts/index.html) \ \ Unleash the Power of Auto-Generating Video Title, Topics, and Hashtags](/content/ja/blog/generate-titles-and-hashtags/index.html) \ \ Introducing the Multimodal AI in Media & Entertainment Hackathon](/content/ja/blog/hackathon-los-angeles/index.html) \ \ How a tiny startup beat the tech giants of the world and ranked #1 in video search (Part 1 — Motivation)](/content/ja/blog/how-a-tiny-startup-beat-the-tech-giants-of-the-world-and-ranked-1-in-video-search-part-1-motivation/index.html) \ \ How to make AI Startup worth over $30MㅣTwelve Labs Jae Lee](/content/ja/blog/how-to-make-ai-startup-worth-over-30mitwelve-labs-jae-lee/index.html) \ \ How to perform Video OCR using Twelve Labs API?](/content/ja/blog/how-to-perform-video-ocr-using-twelve-labs-api/index.html) \ \ Building a Video AI Interview Analyzer with Twelve Labs](/content/ja/blog/interview-analyzer/index.html) \ \ Crop and Seek: Experience Advanced Video Search](/content/ja/blog/crop-and-seek/index.html) \ \ A Recap of Denver Multimodal AI Hackathon](/content/ja/blog/denver-hackathon-recap/index.html) \ \ How to classify videos effortlessly with Twelve Labs API: No ML training required!](/content/ja/blog/effortless-video-classifiers-with-twelve-labs-api-no-ml-training-required/index.html) \ \ EMAM and Twelve Labs Announce an Integrated Solution for Video AI](/content/ja/blog/emam-and-twelve-labs-announce-an-integrated-solution-for-video-ai/index.html) \ \ How to find specific moments within your video using Twelve Labs simple search API](/content/ja/blog/find-specific-moments-within-your-video-using-twelve-labs-simple-search-api/index.html) \ \ Foundation models are going multimodal](/content/ja/blog/foundation-models-are-going-multimodal/index.html) \ \ S.Korea's Twelve Labs ranks among world's top 50 generative AI startups](/content/ja/blog/genai-50-the-most-promising-generative-artificial-intelligence-startups-of-2023/index.html) \ \ Accelerate Your Film Production with Twelve Labs](/content/ja/blog/accelerate-your-film-production-with-twelve-labs/index.html) \ \ AI 100: The most promising artificial intelligence startups of 2022](/content/ja/blog/ai-100-the-most-promising-artificial-intelligence-startups-of-2022/index.html) \ \ AI 100: The most promising artificial intelligence startups of 2023](/content/ja/blog/ai-100-the-most-promising-artificial-intelligence-startups-of-2023/index.html) \ \ Arvato Systems and Twelve Labs Forge Partnership to Take Video AI to the Next Level](/content/ja/blog/arvato-systems-and-twelve-labs-forge-partnership-to-take-video-ai-to-the-next-level/index.html) \ \ CineSys partners with Twelve Labs](/content/ja/blog/cinesys-partners-with-twelve-labs/index.html) \ \ Companies are commercializing multimodal AI models to analyze videos and more](/content/ja/blog/companies-are-commercializing-multimodal-ai-models-to-analyze-videos-and-more/index.html) \ \ A Tour of Video Understanding Use Cases](/content/ja/blog/a-tour-of-video-understanding-use-cases/index.html) \ \ 2021 Techstars Seattle Accelerator Companies](/content/ja/blog/2021-techstars-seattle-accelerator-companies/index.html)