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
NewsByteDance releases Seedance 2.5, generating 30 seconds of audio and video in one pass
NewsGoogle Earth's new Nano Banana AI can fabricate photorealistic satellite scenes
NewsOwen Song releases Inflect-Micro-v2, a 9.36M-parameter open text-to-speech model on Hugging Face
NewsOpenAI brings ChatGPT Voice to its desktop app for hands-free agent control
NewsBlack Forest Labs debuts FLUX 3 x mimic robot model, already on Audi's line
NewsAdobe adds an AI Playground to its experimental Project Indigo camera app
NewsAlibaba ships Qwen-Image-3.0 with longer prompts but no benchmarks or open weights
NewsMicrosoft open-sources Mage-Flow, a 4B image generation and editing model under MIT license
NewsResearchers introduce VideoChat3, a 4B-parameter open video model, with weights still pending
NewsThinking Machines Lab releases Inkling, its first open-weight multimodal model
NewsGoogle Images turns 25 with a discovery feed and in-search AI image generation
NewsSpotify launches 'Talk to Spotify,' a conversational AI assistant in beta for Premium users