Documentation menu
Documentation

Voice

Build realtime spoken interfaces while keeping the durable agent and browser surface co-located.

Realtime transport, durable identity

Voice agents use the Cloudflare Voice integration for audio transport while Ayjnt generates the bindings and route plumbing. The browser owns microphone permission and visualization; the agent owns session identity, policy, and durable state.

Use the realtime voice example when integrating Gemini Live or another realtime model. Never place long-lived API keys in committed browser code; accept them for a local demo or exchange them through a server-controlled path.