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
NewsElevenLabs launches an AI music generator that creates full songs from text prompts
NewsMistral Launches Voxtral: First Open-Source AI Audio Models Challenge Closed Systems
NewsMoonvalley launches Marey, a video generation model trained entirely on open data
NewsGoogle now offers a photo-to-video feature for Veo 3 through the Gemini app
NewsGoogle's newest experiment brings short audio overviews to some Search queries
NewsMicrosoft launches the Sora-powered Bing Video Creator
NewsBlack Forest Labs Unveils FLUX.1 Kontext: AI image generation meets real-time editing
NewsGoogle announced several updates across its media generation models
NewsGoogle announced updates to the Gemini app, including Imagen 4 and Veo 3 access
NewsGoogle introduces Veo 2 for video generation in Gemini and Whisk
NewsLlama 4: Meta's first natively multimodal mixture-of-experts (MoE) architecture models
NewsOpenAI delays the new GPT-4o image generation feature for free users due to high demand