Building a German Speaking Partner with ElevenLabs Agents and Cloudflare Workers

A developer built a German-language conversation partner using ElevenLabs voice agents and Cloudflare Workers, adding cross-session memory that ElevenLabs agents lacked at the time. The Cloudflare Worker (Hono) serves a Vite + TypeScript page, stores session data in D1, and exposes recall and store endpoints that the agent calls. The developer secured the setup by injecting an HMAC-signed user ID into the page via HTMLRewriter with a no-store cache header, and verifies that signature on every tool route and the post-call webhook so the browser cannot forge an identity.

Anyone who has learned a foreign language knows the gap between a passed exam and real fluency with native speakers. Closing it takes practice with someone at native level, and not everyone has a native-speaking partner or the budget and time for endless lessons. So I asked myself: what if an AI voice agent could be that partner? Someone to have casual conversations with, like a buddy who speaks at native level, never loses patience, and points out your mistakes when they matter. I built it with ElevenLabs agents and Cloudflare Workers. An ElevenLabs agent handles the voice, and a Cloudflare Worker Hono does everything else: it serves a small Vite + TypeScript page, stores data in D1, and exposes the endpoints the agent calls. recall , which returns what happened in recent sessions, and store , which saves items from the conversation. Memory. When I built this, ElevenLabs agents had no built-in memory across sessions, so I added it myself: the webhook stores each session, and the agent calls recall when a call starts. I load only the last two or three sessions. Pulling in more makes the agent sound robotic. Nobody remembers a hundred earlier conversations with a friend. No secrets in the browser. The Worker puts the user's identity into the page before it reaches the browser, as an HMAC-signed ID. The signing key only exists in the Worker. js const rewritten = new HTMLRewriter .on 'elevenlabs-convai', { element el { el.setAttribute 'dynamic-variables', JSON.stringify { user id: token, name: displayName } , ; }, } .transform response ; rewritten.headers.set 'Cache-Control', 'no-store' ; The no-store header matters, because this page is personalized and must never be served from a shared cache. The agent's endpoints are not public. The agent never decides whose data it touches. The widget passes the signed user ID to the agent as a dynamic variable, and every tool call sends it back. The tool routes verify the signature before reading or writing anything, so an invented or altered ID is rejected. The post-call webhook has its own check. Route wiring, simplified: app.get '/tools/recall', recallHandler ; // verifies the signed user id first app.post '/tools/store', storeHandler ; // same check before any write app.post '/api/webhook', saveSession ; // webhook signature check The browser sees the signed ID but can't create a new one. Routing. Static files come straight from the asset bundle. Only / , /api/ and /tools/ invoke the Worker. If you're building voice agents and want to know more about my agent - drop a comment, I'm happy to share details.