Multimodal AI
Multimodal AI systems work with more than one kind of input or output, such as text, images, audio, or video.
Follow model and application developments in speech, image, and video. Coverage looks at generation, understanding, media formats, and practical developer access.
Latest coverage
Articles
NewsAmazon launched a video generator for its Amazon Ads service
NewsYouTube launched new AI features at its 'Made on YouTube' event
NewsRunway and Lionsgate announce partnership to create a custom cinematic video model
NewsSnap announced new generative AI features at Snap Partner Summit 2024
NewsPixtral 12B is Mistral AI's first open-source multimodal model
NewsA new NotebookLM feature lets users listen to conversations based on their sources
NewsChatGPT-powered voice assist is coming to some Volkswagen models in the US market
NewsGoogle announces Gems, Imagen 3, and an early preview for improved people-generation capabilities
NewsThe Weeknd teased an upcoming concert live stream using AI-generated visuals
NewsMeshy has launched Meshy-4, a model with improved 3D-generation capabilities
NewsIdeogram 2.0 is the latest text-to-image model to boast its superior text rendering capability
NewsMidjourney launched a new web-based editor interface that brings its editing tools together