Today we're releasing a brand new set of components for AI Elements designed to work with the Transcription and Speech functions of the AI SDK, helping you build voice agents.

Vercel is a platform for deploying modern web applications with speed and simplicity, offering developers a seamless experience for hosting and scaling their projects. With features like instant deployment, serverless functions, and global CDN, Vercel empowers developers to focus on building great user experiences without worrying about infrastructure management.

Vercel

Vercel released AI Voice Elements, a new component library for the AI SDK that enables building voice agents and transcription services. The release includes six components: Persona (animated AI visual with Rive WebGL2), SpeechInput (voice capture with Web Speech API fallback), Transcription (synchronized playback display), AudioPlayer (customizable playback built on media-chrome), MicSelector (microphone device selection), and VoiceSelector (AI voice selection interface). All components are built on shadcn/ui and can be installed via npx.

AI Voice Elements

<p>Well this sounds really cool. Guess I need to see all the new AI SDK stuff.</p>
