diff --git a/docker-compose.yml b/docker-compose.yml
index e900f6b..5e69d72 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -17,6 +17,11 @@ services:
   ollama:
     image: ollama/ollama:latest
     restart: unless-stopped
+    environment:
+      # Keep the chat + embed models resident so voice turns never pay a cold
+      # reload. Default keep_alive is 5 min, so every post-idle turn took
+      # ~30-60s while Qwen3 8B reloaded into the GPU. -1 = never unload.
+      OLLAMA_KEEP_ALIVE: "-1"
     volumes:
       - ollama_models:/root/.ollama
     # GPU: needs nvidia-container-toolkit on the host (CDI). Verified on the