fix(gemini): support native TTS generateContent endpoint

Pass Gemini AUDIO/TTS generateContent requests through to Google's native
v1beta endpoint instead of converting to chat, with per-credential fallback
(504 timeout, 502 fetch failure). Accept client keys from Bearer,
x-goog-api-key, or ?key= while forwarding only the configured Gemini
credential upstream. Expose native v1beta model names and rewrites, and add
Gemini 3.1 Flash TTS to the catalogs.

Co-authored-by: Cursor <cursoragent@cursor.com>

next.config.mjs

@@ -66,6 +66,14 @@ const nextConfig = {
         source: "/responses",
         destination: "/api/v1/responses"
       },
+      {
+        source: "/v1beta/:path*",
+        destination: "/api/v1beta/:path*"
+      },
+      {
+        source: "/v1beta",
+        destination: "/api/v1beta"
+      },
       {
         source: "/v1/:path*",
         destination: "/api/v1/:path*"