Merge pull request #183 from denizsafak/refactor/store-supported-voices-in-backend-metadata

feat: store supported voices in TTSBackendMetadata

abogen/tts_backend.py

@@ -18,11 +18,13 @@ class TTSBackendMetadata:
         id: Unique backend identifier (e.g. ``"kokoro"``, ``"supertonic"``).
         name: Human-readable display name.
         description: Short description of the backend.
+        voices: Tuple of supported voice identifiers.
     """
 
     id: str
     name: str
     description: str
+    voices: tuple[str, ...] = ()
 
 
 class TTSBackend(Protocol):

abogen/tts_backends/kokoro.py

@@ -10,6 +10,16 @@ from typing import Any, Dict, Iterator, List, Optional
 
 import numpy as np
 
+from abogen.constants import VOICES_INTERNAL
+from abogen.tts_backend import TTSBackendMetadata
+
+_KOKORO_METADATA = TTSBackendMetadata(
+    id="kokoro",
+    name="Kokoro",
+    description="Kokoro TTS engine",
+    voices=tuple(VOICES_INTERNAL),
+)
+
 
 def _load_kpipeline():
     """Lazy-load Kokoro dependencies."""
@@ -39,14 +49,8 @@ class KokoroBackend:
         self._lang_code = lang_code
 
     @property
-    def metadata(self):
-        from abogen.tts_backend import TTSBackendMetadata
-
-        return TTSBackendMetadata(
-            id="kokoro",
-            name="Kokoro",
-            description="Kokoro TTS engine",
-        )
+    def metadata(self) -> TTSBackendMetadata:
+        return _KOKORO_METADATA
 
     def __call__(
         self,
@@ -89,9 +93,7 @@ class KokoroBackend:
 
     def get_available_voices(self) -> List[str]:
         """Return known Kokoro voice identifiers."""
-        from abogen.constants import VOICES_INTERNAL
-
-        return list(VOICES_INTERNAL)
+        return list(self.metadata.voices)
 
     def get_supported_formats(self) -> List[str]:
         """Kokoro outputs raw PCM float32 audio."""
@@ -111,14 +113,9 @@ def create_kokoro_backend(**kwargs: Any) -> KokoroBackend:
 
 
 # --- Registration ---
-from abogen.tts_backend import TTSBackendMetadata  # noqa: E402
 from abogen.tts_backend_registry import register_backend  # noqa: E402
 
 register_backend(
-    metadata=TTSBackendMetadata(
-        id="kokoro",
-        name="Kokoro",
-        description="Kokoro TTS engine",
-    ),
+    metadata=_KOKORO_METADATA,
     factory=create_kokoro_backend,
 )

abogen/tts_backends/supertonic.py

@@ -15,6 +15,15 @@ logger = logging.getLogger(__name__)
 
 DEFAULT_SUPERTONIC_VOICES = ("M1", "M2", "M3", "M4", "M5", "F1", "F2", "F3", "F4", "F5")
 
+from abogen.tts_backend import TTSBackendMetadata
+
+_SUPERTONIC_METADATA = TTSBackendMetadata(
+    id="supertonic",
+    name="SuperTonic",
+    description="SuperTonic TTS engine",
+    voices=DEFAULT_SUPERTONIC_VOICES,
+)
+
 
 @dataclass
 class SupertonicSegment:
@@ -282,12 +291,8 @@ class SupertonicBackend:
     """
 
     @property
-    def metadata(self) -> "TTSBackendMetadata":
-        return TTSBackendMetadata(
-            id="supertonic",
-            name="SuperTonic",
-            description="SuperTonic TTS engine",
-        )
+    def metadata(self) -> TTSBackendMetadata:
+        return _SUPERTONIC_METADATA
 
     def __init__(self, **kwargs: Any) -> None:
         self._pipeline = SupertonicPipeline(
@@ -333,7 +338,7 @@ class SupertonicBackend:
 
     def get_available_voices(self) -> List[str]:
         """Return the list of built-in SuperTonic voice identifiers."""
-        return list(DEFAULT_SUPERTONIC_VOICES)
+        return list(self.metadata.voices)
 
     def get_supported_formats(self) -> List[str]:
         return ["wav"]
@@ -379,14 +384,9 @@ def create_supertonic_backend(**kwargs: Any) -> SupertonicBackend:
     return SupertonicBackend(**kwargs)
 
 
-from abogen.tts_backend import TTSBackendMetadata
-from abogen.tts_backend_registry import register_backend
+from abogen.tts_backend_registry import register_backend  # noqa: E402
 
 register_backend(
-    metadata=TTSBackendMetadata(
-        id="supertonic",
-        name="SuperTonic",
-        description="SuperTonic TTS engine",
-    ),
+    metadata=_SUPERTONIC_METADATA,
     factory=create_supertonic_backend,
 )

tests/test_tts_backend.py

@@ -18,6 +18,23 @@ class TestTTSBackendMetadata:
         assert meta.name == "Test Backend"
         assert meta.description == "A test backend"
 
+    def test_voices_field_default_empty(self):
+        meta = TTSBackendMetadata(
+            id="test",
+            name="Test",
+            description="Test backend",
+        )
+        assert meta.voices == ()
+
+    def test_voices_field_stored(self):
+        meta = TTSBackendMetadata(
+            id="test",
+            name="Test",
+            description="Test backend",
+            voices=("v1", "v2"),
+        )
+        assert meta.voices == ("v1", "v2")
+
     def test_is_immutable(self):
         import pytest
 
@@ -132,6 +149,26 @@ class TestBackendRegistration:
         assert meta.name == "SuperTonic"
         assert "SuperTonic" in meta.description
 
+    def test_kokoro_metadata_has_voices(self):
+        import abogen.tts_backends  # noqa: F401
+
+        from abogen.tts_backend_registry import _registry
+
+        meta = _registry.get_metadata("kokoro")
+        assert isinstance(meta.voices, tuple)
+        assert len(meta.voices) > 0
+        assert all(isinstance(v, str) for v in meta.voices)
+
+    def test_supertonic_metadata_has_voices(self):
+        import abogen.tts_backends  # noqa: F401
+
+        from abogen.tts_backend_registry import _registry
+
+        meta = _registry.get_metadata("supertonic")
+        assert isinstance(meta.voices, tuple)
+        assert len(meta.voices) == 10
+        assert meta.voices == ("M1", "M2", "M3", "M4", "M5", "F1", "F2", "F3", "F4", "F5")
+
     def test_kokoro_factory_callable(self):
         import abogen.tts_backends  # noqa: F401
 
@@ -147,3 +184,21 @@ class TestBackendRegistration:
 
         factory = _registry._factories["supertonic"]
         assert callable(factory)
+
+    def test_kokoro_metadata_voices_match_registry(self):
+        """Ensure the metadata property on the instance shares voices with registry."""
+        from abogen.tts_backends.kokoro import _KOKORO_METADATA
+        from abogen.tts_backend_registry import _registry
+
+        registry_meta = _registry.get_metadata("kokoro")
+        assert _KOKORO_METADATA is registry_meta
+        assert _KOKORO_METADATA.voices == registry_meta.voices
+
+    def test_supertonic_metadata_voices_match_registry(self):
+        """Ensure the metadata property on the instance shares voices with registry."""
+        from abogen.tts_backends.supertonic import _SUPERTONIC_METADATA
+        from abogen.tts_backend_registry import _registry
+
+        registry_meta = _registry.get_metadata("supertonic")
+        assert _SUPERTONIC_METADATA is registry_meta
+        assert _SUPERTONIC_METADATA.voices == registry_meta.voices