diff --git a/stacks/fish-cpp/server.py b/stacks/fish-cpp/server.py
index 324bf88..a55cbf4 100644
--- a/stacks/fish-cpp/server.py
+++ b/stacks/fish-cpp/server.py
@@ -84,9 +84,13 @@ def tts(req: TTSRequest) -> FileResponse:
         "-t", str(TOKENIZER_PATH),
         "-text", req.text,
         "-o", str(out_path),
-        # -v selects voice mode; 0 = default (no preset). Preset voices
-        # would need s2.cpp to ship a voice library; clone via -pa/-pt.
-        "-v", "0",
+        # -c <device> selects CUDA backend on the given device id. The
+        # README example uses `-v 0` (which is --vulkan 0 — easy to
+        # misread as "voice 0"); we want CUDA so that the work hits
+        # the A6000 tensor cores instead of falling back to CPU.
+        # Without a backend flag, s2 prints "NPU not compiled, falling
+        # back to CPU" and runs at single-digit RTF on a 4-core CPU.
+        "-c", "0",
     ]
 
     if req.references: