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
NewsKineMask gives video models an initial push, then predicts collisions
NewsMagnific launches Magnific One image generator with Brand Kit controls
NewsHiggsfield rebuilds AI Influencer for short-form video
NewsApple spotlights Normalizing Trajectory Models for four-step image generation
NewsTII introduces Falcon-ASR for Arabic and multilingual speech
NewsTwelveLabs Releases Pegasus 1.6 With Egocentric Video Support
NewsMistral launches Large 4 in public preview
NewsOpenAI plans visual ads for ChatGPT image generation
NewsMBZUAI and Khalifa University researchers introduce FaceGuardian for identity-safe image editing
NewsApple study finds language cues narrow gaps in multilingual speech models
NewsSuno opens Speech voice-and-music generator to public beta
NewsMicrosoft launches MAI streaming transcription and two Voice 2.1 models