fix: crash when audio.cpp is only serving clone model

3 files changed, 67 insertions, 11 deletions

diff --git a/converter/converter.py b/converter/converter.py
index eb3e80e..6994a31 100644
--- a/converter/converter.py
+++ b/converter/converter.py
@@ -519,7 +519,7 @@ class AudiobookConverter:
             print(f"Voice: {self.voice or config.FASTER_VOICE}")
         elif self.backend == BACKEND_AUDIOCPP:
             print(f"audio.cpp endpoint: {config.AUDIOCPP_API_URL}")
-            print(f"Model id: {config.AUDIOCPP_MODEL_ID}")
+            print(f"Model id: {self.tts.model_id}")
             if self.voice:
                 print("Backend: audio.cpp (voice cloning, reference configured on server)")
                 print(f"Voice: {self.voice}")
diff --git a/converter/tts.py b/converter/tts.py
index a1c0b09..1a5b1a0 100644
--- a/converter/tts.py
+++ b/converter/tts.py
@@ -719,7 +719,10 @@ class AudioCppTTSClient(_BaseTTSClient):
       startup because an unresolvable name would silently fall back to
       plain TTS on the Base model instead of failing. When
       AUDIOCPP_CLONE_MODEL_ID names a second server entry (typically the
-      Base model), preset requests are routed to it.
+      Base model), preset requests are routed to it. Only the entry
+      actually used needs to exist on the server: a clone-only (Base)
+      server works for --voice runs, while speaker mode on such a server
+      fails with a hint to pass --voice.
 
     Each response is a complete WAV file, so sub-request audio is
     concatenated with the same lossless path used for the Gradio client.
@@ -738,13 +741,17 @@ class AudioCppTTSClient(_BaseTTSClient):
         self.preset_mode = bool(voice)
         self.voice = voice or speaker_display_name()
         self._check_health()
-        model_ids = self._check_model()
+        model_ids = self._list_model_ids()
         if self.preset_mode:
+            # Resolve the model before validating so the check covers the
+            # id actually used; a clone-only server works for --voice runs.
             self._select_model(model_ids)
+            self._require_model_id(model_ids)
             self._check_voice()
             print(f"[OK] Connected to audio.cpp server at {self.api_url} "
                   f"(model '{self.model_id}', voice '{self.voice}')")
         else:
+            self._require_model_id(model_ids)
             print(f"[OK] Connected to audio.cpp server at {self.api_url} "
                   f"(model '{self.model_id}', speaker '{self.voice}')")
             print("[INFO] Speaker mode expects the server to be configured with the "
@@ -787,8 +794,8 @@ class AudioCppTTSClient(_BaseTTSClient):
                 f"The audio.cpp server at {self.api_url} reports status "
                 f"{payload.get('status')!r} instead of 'ok'")
 
-    def _check_model(self) -> List[str]:
-        """Verify the configured model id exists; return all server model ids."""
+    def _list_model_ids(self) -> List[str]:
+        """Fetch the model ids reported by the server."""
         try:
             payload = self._get_json("/v1/models")
         except Exception as exc:
@@ -797,15 +804,35 @@ class AudioCppTTSClient(_BaseTTSClient):
                 f"/v1/models: {exc}") from exc
         entries = payload.get("data") or []
         model_ids = [entry.get("id") for entry in entries if isinstance(entry, dict)]
-        if self.model_id not in model_ids:
-            configured = ", ".join(str(mid) for mid in model_ids if mid) or "none"
+        return [mid for mid in model_ids if mid]
+
+    def _require_model_id(self, model_ids: List[str]) -> None:
+        """Verify the model id chosen for this run exists on the server.
+
+        Speaker mode needs AUDIOCPP_MODEL_ID (the CustomVoice entry).
+        Preset mode validates whichever id _select_model resolved, so a
+        server hosting only the Base (cloning) model works for --voice.
+        """
+        if self.model_id in model_ids:
+            return
+        configured = ", ".join(model_ids) or "none"
+        if self.preset_mode:
             raise RuntimeError(
                 f"The audio.cpp server at {self.api_url} has no model id "
-                f"'{self.model_id}' (configured: {configured}). Add a qwen3_tts "
-                "model entry to the server config and match AUDIOCPP_MODEL_ID "
-                "in converter/config.py to its id (see README)."
+                f"'{self.model_id}' or clone model id "
+                f"'{config.AUDIOCPP_CLONE_MODEL_ID}' (configured: {configured}). "
+                "Add a qwen3_tts model entry to the server config and match "
+                "AUDIOCPP_MODEL_ID / AUDIOCPP_CLONE_MODEL_ID in "
+                "converter/config.py to its id (see README)."
             )
-        return [mid for mid in model_ids if mid]
+        raise RuntimeError(
+            f"The audio.cpp server at {self.api_url} has no model id "
+            f"'{self.model_id}' (configured: {configured}). Speaker mode needs "
+            "the CustomVoice model: add a qwen3_tts model entry to the server "
+            "config and match AUDIOCPP_MODEL_ID in converter/config.py to its "
+            "id, or rerun with --voice to use a cloning preset on the Base "
+            "model (see README)."
+        )
 
     def _select_model(self, model_ids: List[str]) -> None:
         """Pick the model for preset (cloning) requests.
diff --git a/tests/test_tts.py b/tests/test_tts.py
index f2dda0e..9ca6f0d 100644
--- a/tests/test_tts.py
+++ b/tests/test_tts.py
@@ -657,6 +657,35 @@ class AudioCppTTSClientHealthTests(unittest.TestCase):
             client = self._client(voice="narrator")
         self.assertEqual(client.model_id, config.AUDIOCPP_MODEL_ID)
 
+    def test_preset_mode_with_clone_only_server_uses_clone_model(self):
+        with patch.object(config, "AUDIOCPP_MODEL_ID", "qwen3-tts"), \
+                patch.object(config, "AUDIOCPP_CLONE_MODEL_ID", "qwen3-tts-clone"):
+            client = self._client(
+                voice="narrator",
+                models={"data": [{"id": "qwen3-tts-clone"}]})
+        self.assertEqual(client.model_id, "qwen3-tts-clone")
+
+    def test_speaker_mode_with_clone_only_server_suggests_voice(self):
+        with patch.object(config, "AUDIOCPP_MODEL_ID", "qwen3-tts"), \
+                patch.object(config, "AUDIOCPP_CLONE_MODEL_ID", "qwen3-tts-clone"):
+            with self.assertRaises(RuntimeError) as ctx:
+                self._client(models={"data": [{"id": "qwen3-tts-clone"}]})
+        message = str(ctx.exception)
+        self.assertIn("qwen3-tts", message)
+        self.assertIn("--voice", message)
+
+    def test_preset_mode_with_no_matching_model_lists_both_ids(self):
+        with patch.object(config, "AUDIOCPP_MODEL_ID", "qwen3-tts"), \
+                patch.object(config, "AUDIOCPP_CLONE_MODEL_ID", "qwen3-tts-clone"), \
+                self.assertLogs("converter.tts", level="WARNING"):
+            with self.assertRaises(RuntimeError) as ctx:
+                self._client(voice="narrator",
+                             models={"data": [{"id": "pocket-tts"}]})
+        message = str(ctx.exception)
+        self.assertIn("qwen3-tts", message)
+        self.assertIn("qwen3-tts-clone", message)
+        self.assertIn("pocket-tts", message)
+
 
 class AudioCppTTSClientRequestTests(unittest.TestCase):
     """The /v1/audio/speech payload and response validation."""