Move audio keep-alive into the gateway container (Cloudron scheduler addon, every 10m)

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)