feat: combine --speaker and --voice for clarity

1 files changed, 15 insertions, 23 deletions

diff --git a/app/converter/converter.py b/app/converter/converter.py
index 6e677c8..80411d3 100644
--- a/app/converter/converter.py
+++ b/app/converter/converter.py
@@ -185,7 +185,6 @@ class AudiobookConverter:
                  instructions: Optional[str] = None,
                  request_options: Optional[Dict[str, str]] = None,
                  api_url: Optional[str] = None,
-                 speaker: Optional[str] = None,
                  progress: Optional[Callable[[dict], None]] = None,
                  cancel=None):
         if speed <= 0:
@@ -206,7 +205,6 @@ class AudiobookConverter:
         self.output_format = output_format
         self.backend = backend
         self.voice = voice
-        self.speaker = speaker
         self.debug = bool(debug)
         # Voice design / style instruction and free-form request options
         # (audio.cpp only): forwarded to AudioCppTTSClient, which validates
@@ -219,18 +217,17 @@ class AudiobookConverter:
             # configured on the server, so no local reference audio is needed.
             self.tts = FasterTTSClient(voice=voice, api_url=api_url)
         elif backend == BACKEND_AUDIOCPP:
-            # Speaker mode (--speaker or no flag on a CustomVoice entry) uses
-            # a built-in speaker name; an explicit --voice selects a
-            # server-side preset (cloning). model_id overrides
-            # AUDIOCPP_MODEL_ID for multi-model servers; instructions describe
-            # or style the voice, request_options pass per-model controls
-            # through to the server.
+            # --voice picks the voice: a built-in speaker name on the
+            # CustomVoice entry, or a server-side preset (cloning)
+            # elsewhere. model_id overrides AUDIOCPP_MODEL_ID for
+            # multi-model servers; instructions describe or style the
+            # voice, request_options pass per-model controls through to
+            # the server.
             self.tts = AudioCppTTSClient(voice=voice, language=self.language,
                                          model_id=model_id,
                                          instructions=instructions,
                                          request_options=self.request_options,
-                                         api_url=api_url,
-                                         speaker=speaker)
+                                         api_url=api_url)
         else:
             self.tts = QwenTTSClient(
                 voice_mode=voice_mode,
@@ -294,14 +291,13 @@ class AudiobookConverter:
         """Narrator name used in output file names (see compute_narrator_tag)."""
         return self.compute_narrator_tag(
             self.backend, self.voice, self.voice_mode,
-            self.voice_clone_ref_audio, self.instructions, self.speaker)
+            self.voice_clone_ref_audio, self.instructions)
 
     @staticmethod
     def compute_narrator_tag(backend: str, voice: Optional[str],
                              voice_mode: str,
                              voice_clone_ref_audio: Optional[str],
-                             instructions: Optional[str] = None,
-                             speaker: Optional[str] = None) -> str:
+                             instructions: Optional[str] = None) -> str:
         """Narrator name used in output file names, without a server connection.
 
         Custom voice mode uses the built-in speaker's display name; voice
@@ -322,8 +318,6 @@ class AudiobookConverter:
         elif backend == BACKEND_AUDIOCPP:
             if voice:
                 narrator = voice
-            elif speaker:
-                narrator = speaker
             elif instructions:
                 # The voice comes from the instruction, not a speaker name.
                 narrator = "designed"
@@ -677,12 +671,12 @@ class AudiobookConverter:
             self._say(f"audio.cpp endpoint: {config.AUDIOCPP_API_URL}")
             self._say(f"Model id: {self.tts.model_id}")
             self._say(f"Model family: {getattr(self.tts, 'family', 'unknown')}")
-            if self.voice:
+            if getattr(self.tts, "preset_mode", False):
                 self._say("Backend: audio.cpp (voice cloning, reference configured on server)")
-                self._say(f"Voice: {self.voice}")
-            elif self.speaker:
+                self._say(f"Voice: {self.tts.voice}")
+            elif getattr(self.tts, "speaker_mode", False):
                 self._say("Backend: audio.cpp (custom voice, built-in speaker)")
-                self._say(f"Speaker: {self.speaker}")
+                self._say(f"Speaker: {self.tts.voice}")
             elif self.instructions:
                 self._say("Backend: audio.cpp (voice from --instructions description)")
                 self._say(f"Instruction: {self.instructions}")
@@ -726,7 +720,6 @@ class AudiobookConverter:
                              voice_clone_ref_audio: Optional[str],
                              output_format: str,
                              instructions: Optional[str] = None,
-                             speaker: Optional[str] = None,
                              confirm: Optional[Callable[[str, bool], bool]] = None,
                              ) -> Tuple[List[Path], List[Tuple[Path, str]]]:
         """Discover books and ask every overwrite question up front.
@@ -758,8 +751,7 @@ class AudiobookConverter:
         # starts, so the rest of the run is unattended.
         planned: List[Tuple[Path, str]] = []
         narrator_tag = AudiobookConverter.compute_narrator_tag(
-            backend, voice, voice_mode, voice_clone_ref_audio, instructions,
-            speaker)
+            backend, voice, voice_mode, voice_clone_ref_audio, instructions)
         for book_file in book_files:
             output_name = book_file.stem
             if stem_counts[book_file.stem] > 1:
@@ -795,7 +787,7 @@ class AudiobookConverter:
             book_files, planned = AudiobookConverter.preflight_overwrites(
                 self.backend, self.voice, self.voice_mode,
                 self.voice_clone_ref_audio, self.output_format,
-                self.instructions, self.speaker)
+                self.instructions)
 
         if not book_files:
             self._say(f"[INFO] No supported files found in {BOOKS_FOLDER}")