diff --git a/CloudronManifest.json b/CloudronManifest.json
index c96b5be..2036ded 100644
--- a/CloudronManifest.json
+++ b/CloudronManifest.json
@@ -16,7 +16,13 @@
   "addons": {
     "postgresql": {},
     "redis": {},
-    "localstorage": {}
+    "localstorage": {},
+    "scheduler": {
+      "audio_keepalive": {
+        "schedule": "*/10 * * * *",
+        "command": "/app/code/audio_keepalive.py"
+      }
+    }
   },
   "tags": [
     "ai",
diff --git a/Dockerfile b/Dockerfile
index 2a936ed..d9c39b8 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -29,6 +29,11 @@ COPY config.yaml /app/data/config.yaml
 COPY patch_budget_message.py /app/code/patch_budget_message.py
 RUN python3 /app/code/patch_budget_message.py
 
+# Audio keep-alive: scheduled pings keep the Tinfoil TEE audio enclave
+# warm so voice mode skips the ~24s cold-start (see audio_keepalive.py header).
+COPY audio_keepalive.py /app/code/audio_keepalive.py
+RUN chmod +x /app/code/audio_keepalive.py
+
 # Override the base image's ENTRYPOINT (which is `litellm`) so our
 # startup script runs instead of being passed as an argument to litellm.
 ENTRYPOINT ["/app/code/start.sh"]
diff --git a/audio_keepalive.py b/audio_keepalive.py
new file mode 100644
index 0000000..508cafe
--- /dev/null
+++ b/audio_keepalive.py
@@ -0,0 +1,35 @@
+#!/usr/bin/env python3
+"""Audio keep-alive: ping the Tinfoil TEE audio models through localhost LiteLLM
+so voice mode doesn't pay the ~24s cold-start after idle.
+
+Runs INSIDE the gateway container via the Cloudron scheduler addon. Uses the
+LITELLM_MASTER_KEY already in the container env. TTS-only (STT pings cost
+$0.01/request each; TTS $0.002 — see docs, keep-alive economics). Silent on
+success; prints + exits non-zero on failure so scheduler logs capture it.
+"""
+import json, os, urllib.request, urllib.error, sys
+
+PORT = os.environ.get("PORT", "4000")
+KEY = os.environ.get("LITELLM_MASTER_KEY", "")
+if not KEY:
+    print("keepalive: LITELLM_MASTER_KEY not set", file=sys.stderr)
+    sys.exit(1)
+
+fail = 0
+
+# TTS warm (voxtral-tts) — $0.002/request (Tinfoil request-priced)
+req = urllib.request.Request(
+    f"http://127.0.0.1:{PORT}/v1/audio/speech",
+    data=json.dumps({"model": "tinfoil/voxtral-tts", "input": "ok",
+                     "voice": "casual_female"}).encode(),
+    method="POST",
+    headers={"Authorization": f"Bearer {KEY}", "Content-Type": "application/json"})
+try:
+    urllib.request.urlopen(req, timeout=30)
+except Exception as e:
+    print(f"keepalive: TTS ping failed: {e}", file=sys.stderr)
+    fail = 1
+
+# STT warm disabled 2026-10-11: $0.01/STT request × 6/hr ≈ $52/mo. Revisit only
+# with a cheaper warm strategy.
+sys.exit(fail)