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
NewsGoogle launches Guided Vision in Gemini Live on Android
NewsGoogle Research introduces Diffusion Controller to steer image generation
NewsAWS adds Qwen3-TTS voice cloning to SageMaker JumpStart
NewsGoogle rolls out Gemini 3.8 Flash and Flash-Lite text-to-speech models
NewsApple researchers shrink streaming audio encoders with latent-space distillation
NewsMicrosoft adds voice agents and optimization tools to Foundry
NewsXiaomi releases MiMo-V2.6-Pro-RL open-weight multimodal model
NewsxAI releases Grok Voice Transcribe 2.0 for its speech-to-text API
NewsUniversal Music and ElevenLabs strike multiyear AI music licensing deal
NewsNVIDIA expands real-time AI production tools at IBC 2026
NewsOpenAI launches GPT-Live-1 for full-duplex voice agents
NewsApple begins rolling out rebuilt Siri AI in English-language beta