Step-by-step: add EventTraceRecorder traces to MLC-LLM, use TVMSynchronize to bracket GPU work, and capture OpenCL kernel timings in TVM.

On-device speech synthesis is now available in the AI SDK for React Native. Powered by Apple’s AVSpeechSynthesizer, it delivers private, low-latency text-to-speech with rich voice options and offline support.

Add speech-to-text features to your React Native app using Apple’s SpeechAnalyzer and SpeechTranscriber APIs in iOS 26. Runs entirely on-device, with system-managed language models and support for multiple languages.

Use on-device text embeddings in React Native. Our Vercel AI SDK provider leverages Apple's built-in NLP framework, adding powerful AI features to your app with zero extra downloads or increased bundle size.

The Apple provider for Vercel AI SDK now supports tool calling, enabling on-device LLMs to execute custom functions in React Native apps. Build faster, more interactive mobile AI experiences.

React Native now supports Apple’s on-device LLM for private, fast, and offline AI experiences. Build with Foundation Models and bring Apple Intelligence features to your mobile app.

Learn how to run on-device LLMs in React Native using Vercel’s AI SDK from Michał Pierzchała's talk at DevAI by Data Science Summit.

Adapt React apps for TV with predictable AI. Amazon's Eric Fahsl demos Kiro.dev, a spec-driven assistant that solves complex TV UI challenges like D-pad navigation and focus management.

Lars Grammel from Vercel introduces AI SDK 5, a major rewrite to build next-gen AI apps. Learn about its new provider architecture, type-safe UI and agentic loops for modern AI development.

Learn what it takes to build a custom AI-powered chatbot for your company, including the challenges, solutions, performance, and security considerations.