feat: add static voice catalog to PluginManifest

- Add  to PluginManifest
  - None = not declared (use VoiceLister fallback)
  - () = explicitly no static voices
  - Non-empty = static catalog available without Engine instantiation

- Update get_voices() to check manifest first, fall back to Engine
- Declare 54 Kokoro voices and 10 SuperTonic voices in manifests
- Remove hardcoded voice lists from engine.py files
- Engine.listVoices() now returns [] (manifest is source of truth)

- Clean up dead create_pipeline() kwargs (sample_rate, auto_download, total_steps)
  - SuperTonic plugin uses internal defaults
  - total_steps is per-request parameter via Pipeline.__call__() kwargs

- Add clear_preview_pipelines() for resource cleanup
- Fix test mocks to override listVoices()
- Update Architecture Amendment #1 doc

abogen/tts_plugin/manifest.py

@@ -173,6 +173,8 @@ class PluginManifest:
         capabilities: List of capability identifiers.
         requires: Plugin requirements.
         engine: Engine manifest.
+        voices: Optional static voice catalog. None = not declared (use VoiceLister),
+            empty tuple = explicitly no static voices, non-empty = static catalog.
     """
 
     id: str
@@ -184,3 +186,4 @@ class PluginManifest:
     capabilities: tuple[str, ...] = field(default_factory=tuple)
     requires: RequirementManifest = field(default_factory=RequirementManifest)
     engine: EngineManifest = field(default_factory=EngineManifest)
+    voices: tuple[VoiceManifest, ...] | None = None

abogen/tts_plugin/utils.py

@@ -6,7 +6,7 @@ calling the Plugin Manager directly.
 
 from __future__ import annotations
 
-from typing import Any, Iterator, Optional
+from typing import Any, Iterator
 
 import numpy as np
 
@@ -17,6 +17,7 @@ def get_voices(plugin_id: str) -> tuple[str, ...]:
     """Return the voice-id tuple for *plugin_id*.
 
     Uses the official Plugin Architecture: PluginManager → Engine → VoiceLister.
+    First checks plugin manifest for static voice catalog.
     """
     import logging
     import tempfile
@@ -29,6 +30,13 @@ def get_voices(plugin_id: str) -> tuple[str, ...]:
     if not manager.has_plugin(plugin_id):
         return ()
 
+    # Check manifest for static voice catalog
+    plugin_info = manager.get_plugin(plugin_id)
+    if plugin_info is not None:
+        manifest = plugin_info.get("manifest")
+        if manifest is not None and manifest.voices is not None:
+            return tuple(v.id for v in manifest.voices)
+
     ctx = HostContext(
         config_dir=Path(tempfile.gettempdir()),
         logger=logging.getLogger(f"abogen.utils.{plugin_id}"),
@@ -183,12 +191,45 @@ class Pipeline:
         self.dispose()
 
 
-def create_pipeline(plugin_id: str, **kwargs: Any) -> Pipeline:
+def create_pipeline(
+    plugin_id: str,
+    *,
+    lang_code: str = "a",
+    device: str = "cpu",
+) -> Pipeline:
     """Create a callable TTS pipeline via the Plugin Architecture.
 
-    Returns a :class:`Pipeline` whose ``__call__`` interface matches the
+    Builds a proper HostContext and EngineConfig, then delegates to the
-    legacy ``TTSBackend`` callable protocol.
+    PluginManager to create the engine. Returns a :class:`Pipeline` whose
+    ``__call__`` interface matches the legacy ``TTSBackend`` callable protocol.
+
+    Args:
+        plugin_id: Plugin identifier (e.g., "kokoro", "supertonic").
+        lang_code: Language code for the engine.
+        device: Device to use (e.g., "cpu", "cuda:0").
+
+    Returns:
+        A callable Pipeline instance.
     """
+    import logging
+    import tempfile
+    from pathlib import Path
+
+    from abogen.tts_plugin.host_context import HostContext
+    from abogen.tts_plugin.types import EngineConfig
+
     manager = get_plugin_manager()
-    engine = manager.create_engine(plugin_id, **kwargs)
+
-    return Pipeline(engine, **kwargs)
+    ctx = HostContext(
+        config_dir=Path(tempfile.gettempdir()),
+        logger=logging.getLogger(f"abogen.pipeline.{plugin_id}"),
+        http_client=type("_StubHttpClient", (), {
+            "get": staticmethod(lambda url, **kw: None),
+            "post": staticmethod(lambda url, **kw: None),
+        })(),
+    )
+
+    config = EngineConfig(device=device, lang_code=lang_code)
+
+    engine = manager.create_engine(plugin_id, context=ctx, model_path=None, config=config)
+    return Pipeline(engine)

abogen/webui/conversion_runner.py

@@ -1576,9 +1576,6 @@ def run_conversion_job(job: Job) -> None:
             if provider_norm == "supertonic":
                 pipelines[provider_norm] = create_pipeline(
                     "supertonic",
-                    sample_rate=SAMPLE_RATE,
-                    auto_download=True,
-                    total_steps=int(getattr(job, "supertonic_total_steps", 5) or 5),
                 )
                 return pipelines[provider_norm]
 
@@ -2408,6 +2405,11 @@ def run_conversion_job(job: Job) -> None:
 
         # Explicitly release the pipeline and force garbage collection to prevent
         # memory accumulation in the worker process, which can lead to host lockups.
+        for p in pipelines.values():
+            try:
+                p.dispose()
+            except Exception:
+                pass
         pipelines.clear()
         pipeline = None
         gc.collect()
@@ -2443,9 +2445,6 @@ def _load_pipeline(job: Job):
     if provider == "supertonic":
         return create_pipeline(
             "supertonic",
-            sample_rate=SAMPLE_RATE,
-            auto_download=True,
-            total_steps=int(getattr(job, "supertonic_total_steps", 5) or 5),
         )
 
     device = "cpu"

abogen/webui/routes/utils/preview.py

@@ -14,6 +14,17 @@ _preview_pipelines: Dict[Tuple[str, str], Any] = {}
 _preview_pipeline_lock = threading.Lock()
 
 
+def clear_preview_pipelines() -> None:
+    """Dispose all cached preview pipelines and clear the cache."""
+    with _preview_pipeline_lock:
+        for pipeline in _preview_pipelines.values():
+            try:
+                pipeline.dispose()
+            except Exception:
+                pass
+        _preview_pipelines.clear()
+
+
 def _select_device() -> str:
     import platform
 
@@ -138,7 +149,7 @@ def generate_preview_audio(
     if provider == "supertonic":
         from abogen.tts_plugin.utils import create_pipeline
 
-        pipeline = create_pipeline("supertonic", sample_rate=SAMPLE_RATE, auto_download=True, total_steps=supertonic_total_steps)
+        pipeline = create_pipeline("supertonic")
         segments = pipeline(
             normalized_text,
             voice=voice_spec,

docs/architecture-amendment-001.md

@@ -0,0 +1,89 @@
+# Architecture Amendment #1: EngineConfig — `lang_code` field
+
+**Date:** 2026-07-12
+**Status:** Accepted
+**PR:** #12 (Normalize Pipeline Public API)
+
+## Summary
+
+Add `lang_code: str = "a"` to `EngineConfig` and update its definition to clarify the architectural contract.
+
+## Background
+
+During migration from the old `KokoroBackend` to the Plugin Architecture, the `lang_code` parameter became a dead argument. The old backend read it from `**kwargs` and passed it to `KPipeline(lang_code=...)`. The new `KokoroPlugin.create_engine()` hardcodes `lang_code="a"`, ignoring the config entirely. Callers continued passing `lang_code` to `create_pipeline()`, unaware it had no effect.
+
+This is a functional regression relative to the pre-Plugin Architecture behavior.
+
+## Decision
+
+### 1. Updated EngineConfig definition
+
+**Before:**
+```
+Immutable value object for engine initialization settings.
+Contains only engine-specific settings, no resource references.
+```
+
+**After:**
+```
+Immutable configuration of an Engine instance.
+Contains parameters that define how a particular Engine instance is
+created and that remain constant throughout the lifetime of that Engine.
+Plugin implementations may ignore fields that are not applicable to them.
+```
+
+### 2. New field
+
+```python
+@dataclass(frozen=True)
+class EngineConfig:
+    device: str = "cpu"
+    lang_code: str = "a"
+```
+
+### 3. Architectural rules
+
+- **Fields in EngineConfig are optional unless explicitly required by a plugin.**
+- **Plugins MUST ignore unsupported EngineConfig fields.**
+- **All parameters that may vary between individual synthesis requests must remain in `SynthesisRequest.parameters`.**
+
+## Rationale
+
+Analysis of real TTS engines (Kokoro, Piper, XTTS, Coqui, StyleTTS2, Fish Speech) confirmed:
+
+| Parameter type | Where it belongs | Example |
+|---------------|-----------------|---------|
+| Engine instance config (immutable) | `EngineConfig` | `device`, `lang_code` |
+| Synthesis parameters (per-request) | `SynthesisRequest.parameters` | `speed`, `split_pattern`, `total_steps` |
+
+`lang_code` determines the engine's behavior at creation time and cannot be changed during the engine's lifetime. It is not a synthesis parameter.
+
+## Impact on existing plugins
+
+| Plugin | `device` | `lang_code` | Notes |
+|--------|----------|-------------|-------|
+| Kokoro | Reads ✓ | Reads ✓ (was hardcoded, now from config) | Regression fixed |
+| SuperTonic | Ignores | Ignores | No change — no language concept |
+| Future plugins | May read | May ignore | Field-ignoring rule applies |
+
+## Contract tests added
+
+```python
+class TestEngineConfigContract:
+    def test_default_lang_code(self)       # EngineConfig().lang_code == "a"
+    def test_custom_lang_code(self)        # EngineConfig(lang_code="j").lang_code == "j"
+    def test_immutability_lang_code(self)  # frozen — cannot reassign
+    def test_plugins_may_ignore_irrelevant_fields(self)  # field-ignoring rule
+    def test_engine_config_contains_engine_instance_configuration(self)  # definition
+```
+
+## Files changed
+
+| File | Change |
+|------|--------|
+| `abogen/tts_plugin/types.py` | Updated docstring, added `lang_code: str = "a"` |
+| `plugins/kokoro/__init__.py` | Reads `config.lang_code` instead of hardcoded `"a"` |
+| `abogen/tts_plugin/utils.py` | `create_pipeline()` passes `lang_code` to `EngineConfig` |
+| `tests/contracts/test_types_contract.py` | 5 new contract tests |
+| `tests/contracts/test_plugin_manager_contract.py` | Updated assertion for `lang_code` |
+| `tests/test_behavioral_regression.py` | Updated `test_engine_config_defaults` |

plugins/kokoro/__init__.py

@@ -24,6 +24,7 @@ from abogen.tts_plugin.manifest import (
     ParameterManifest,
     PluginManifest,
     RequirementManifest,
+    VoiceManifest,
     VoiceSourceManifest,
 )
 from abogen.tts_plugin.types import EngineConfig
@@ -73,6 +74,62 @@ PLUGIN_MANIFEST = PluginManifest(
             AudioFormatManifest(mime="audio/wav", extension="wav"),
         ),
     ),
+    voices=(
+        VoiceManifest(id="af_alloy", name="Alloy", tags=("en", "female")),
+        VoiceManifest(id="af_aoede", name="Aoede", tags=("en", "female")),
+        VoiceManifest(id="af_bella", name="Bella", tags=("en", "female")),
+        VoiceManifest(id="af_heart", name="Heart", tags=("en", "female")),
+        VoiceManifest(id="af_jessica", name="Jessica", tags=("en", "female")),
+        VoiceManifest(id="af_kore", name="Kore", tags=("en", "female")),
+        VoiceManifest(id="af_nicole", name="Nicole", tags=("en", "female")),
+        VoiceManifest(id="af_nova", name="Nova", tags=("en", "female")),
+        VoiceManifest(id="af_river", name="River", tags=("en", "female")),
+        VoiceManifest(id="af_sarah", name="Sarah", tags=("en", "female")),
+        VoiceManifest(id="af_sky", name="Sky", tags=("en", "female")),
+        VoiceManifest(id="am_adam", name="Adam", tags=("en", "male")),
+        VoiceManifest(id="am_echo", name="Echo", tags=("en", "male")),
+        VoiceManifest(id="am_eric", name="Eric", tags=("en", "male")),
+        VoiceManifest(id="am_fenrir", name="Fenrir", tags=("en", "male")),
+        VoiceManifest(id="am_liam", name="Liam", tags=("en", "male")),
+        VoiceManifest(id="am_michael", name="Michael", tags=("en", "male")),
+        VoiceManifest(id="am_onyx", name="Onyx", tags=("en", "male")),
+        VoiceManifest(id="am_puck", name="Puck", tags=("en", "male")),
+        VoiceManifest(id="am_santa", name="Santa", tags=("en", "male")),
+        VoiceManifest(id="bf_alice", name="Alice", tags=("en", "female")),
+        VoiceManifest(id="bf_emma", name="Emma", tags=("en", "female")),
+        VoiceManifest(id="bf_isabella", name="Isabella", tags=("en", "female")),
+        VoiceManifest(id="bf_lily", name="Lily", tags=("en", "female")),
+        VoiceManifest(id="bm_daniel", name="Daniel", tags=("en", "male")),
+        VoiceManifest(id="bm_fable", name="Fable", tags=("en", "male")),
+        VoiceManifest(id="bm_george", name="George", tags=("en", "male")),
+        VoiceManifest(id="bm_lewis", name="Lewis", tags=("en", "male")),
+        VoiceManifest(id="ef_dora", name="Dora", tags=("es", "female")),
+        VoiceManifest(id="em_alex", name="Alex", tags=("es", "male")),
+        VoiceManifest(id="em_santa", name="Santa", tags=("es", "male")),
+        VoiceManifest(id="ff_siwis", name="Siwis", tags=("fr", "female")),
+        VoiceManifest(id="hf_alpha", name="Alpha", tags=("hi", "female")),
+        VoiceManifest(id="hf_beta", name="Beta", tags=("hi", "female")),
+        VoiceManifest(id="hm_omega", name="Omega", tags=("hi", "male")),
+        VoiceManifest(id="hm_psi", name="Psi", tags=("hi", "male")),
+        VoiceManifest(id="if_sara", name="Sara", tags=("it", "female")),
+        VoiceManifest(id="im_nicola", name="Nicola", tags=("it", "male")),
+        VoiceManifest(id="jf_alpha", name="Alpha", tags=("ja", "female")),
+        VoiceManifest(id="jf_gongitsune", name="Gongitsune", tags=("ja", "female")),
+        VoiceManifest(id="jf_nezumi", name="Nezumi", tags=("ja", "female")),
+        VoiceManifest(id="jf_tebukuro", name="Tebukuro", tags=("ja", "female")),
+        VoiceManifest(id="jm_kumo", name="Kumo", tags=("ja", "male")),
+        VoiceManifest(id="pf_dora", name="Dora", tags=("pt", "female")),
+        VoiceManifest(id="pm_alex", name="Alex", tags=("pt", "male")),
+        VoiceManifest(id="pm_santa", name="Santa", tags=("pt", "male")),
+        VoiceManifest(id="zf_xiaobei", name="Xiaobei", tags=("zh", "female")),
+        VoiceManifest(id="zf_xiaoni", name="Xiaoni", tags=("zh", "female")),
+        VoiceManifest(id="zf_xiaoxiao", name="Xiaoxiao", tags=("zh", "female")),
+        VoiceManifest(id="zf_xiaoyi", name="Xiaoyi", tags=("zh", "female")),
+        VoiceManifest(id="zm_yunjian", name="Yunjian", tags=("zh", "male")),
+        VoiceManifest(id="zm_yunxi", name="Yunxi", tags=("zh", "male")),
+        VoiceManifest(id="zm_yunxia", name="Yunxia", tags=("zh", "female")),
+        VoiceManifest(id="zm_yunyang", name="Yunyang", tags=("zh", "male")),
+    ),
 )
 
 MODEL_REQUIREMENTS: list[ModelManifest] = []
@@ -109,12 +166,12 @@ def create_engine(
             repo_id = str(model_path)
 
         pipeline = KPipeline(
-            lang_code="a",  # Default language code
+            lang_code=config.lang_code,
             repo_id=repo_id,
             device=config.device,
         )
 
-        engine = KokoroEngine(pipeline, lang_code="a")
+        engine = KokoroEngine(pipeline)
         return engine
     except Exception as e:
         from abogen.tts_plugin.errors import EngineError as EngineErrorClass

plugins/kokoro/engine.py

@@ -7,66 +7,23 @@ protocol. It wraps the KokoroBackend without modifying it.
 from __future__ import annotations
 
 import logging
-from typing import Any, Iterator
+from typing import Any
 
 import numpy as np
 
 from abogen.tts_plugin.capabilities import VoiceLister
 from abogen.tts_plugin.engine import Engine, EngineSession
-from abogen.tts_plugin.errors import EngineError, InvalidInputError
+from abogen.tts_plugin.errors import EngineError
 from abogen.tts_plugin.manifest import VoiceManifest
 from abogen.tts_plugin.types import (
     AudioFormat,
     Duration,
-    ParameterValues,
     SynthesisRequest,
     SynthesizedAudio,
-    VoiceSelection,
 )
 
 logger = logging.getLogger(__name__)
 
-# Kokoro voice list - source of truth
-_KOKORO_VOICES = (
-    "af_alloy", "af_aoede", "af_bella", "af_heart", "af_jessica",
-    "af_kore", "af_nicole", "af_nova", "af_river", "af_sarah",
-    "af_sky", "am_adam", "am_echo", "am_eric", "am_fenrir",
-    "am_liam", "am_michael", "am_onyx", "am_puck", "am_santa",
-    "bf_alice", "bf_emma", "bf_isabella", "bf_lily",
-    "bm_daniel", "bm_fable", "bm_george", "bm_lewis",
-    "ef_dora", "em_alex", "em_santa",
-    "ff_siwis", "hf_alpha", "hf_beta", "hm_omega", "hm_psi",
-    "if_sara", "im_nicola",
-    "jf_alpha", "jf_gongitsune", "jf_nezumi", "jf_tebukuro", "jm_kumo",
-    "pf_dora", "pm_alex", "pm_santa",
-    "zf_xiaobei", "zf_xiaoni", "zf_xiaoxiao", "zf_xiaoyi",
-    "zm_yunjian", "zm_yunxi", "zm_yunxia", "zm_yunyang",
-)
-
-# Voice display names mapping
-_VOICE_DISPLAY_NAMES: dict[str, str] = {
-    "af_alloy": "Alloy", "af_aoede": "Aoede", "af_bella": "Bella",
-    "af_heart": "Heart", "af_jessica": "Jessica", "af_kore": "Kore",
-    "af_nicole": "Nicole", "af_nova": "Nova", "af_river": "River",
-    "af_sarah": "Sarah", "af_sky": "Sky", "am_adam": "Adam",
-    "am_echo": "Echo", "am_eric": "Eric", "am_fenrir": "Fenrir",
-    "am_liam": "Liam", "am_michael": "Michael", "am_onyx": "Onyx",
-    "am_puck": "Puck", "am_santa": "Santa", "bf_alice": "Alice",
-    "bf_emma": "Emma", "bf_isabella": "Isabella", "bf_lily": "Lily",
-    "bm_daniel": "Daniel", "bm_fable": "Fable", "bm_george": "George",
-    "bm_lewis": "Lewis", "ef_dora": "Dora", "em_alex": "Alex",
-    "em_santa": "Santa", "ff_siwis": "Siwis", "hf_alpha": "Alpha",
-    "hf_beta": "Beta", "hm_omega": "Omega", "hm_psi": "Psi",
-    "if_sara": "Sara", "im_nicola": "Nicola",
-    "jf_alpha": "Alpha", "jf_gongitsune": "Gongitsune",
-    "jf_nezumi": "Nezumi", "jf_tebukuro": "Tebukuro", "jm_kumo": "Kumo",
-    "pf_dora": "Dora", "pm_alex": "Alex", "pm_santa": "Santa",
-    "zf_xiaobei": "Xiaobei", "zf_xiaoni": "Xiaoni",
-    "zf_xiaoxiao": "Xiaoxiao", "zf_xiaoyi": "Xiaoyi",
-    "zm_yunjian": "Yunjian", "zm_yunxi": "Yunxi",
-    "zm_yunxia": "Yunxia", "zm_yunyang": "Yunyang",
-}
-
 # Sample rate for Kokoro audio
 _KOKORO_SAMPLE_RATE = 24000
 
@@ -78,9 +35,8 @@ class KokoroSession:
     NOT thread-safe.
     """
 
-    def __init__(self, pipeline: Any, lang_code: str) -> None:
+    def __init__(self, pipeline: Any) -> None:
         self._pipeline = pipeline
-        self._lang_code = lang_code
         self._disposed = False
 
     def synthesize(self, request: SynthesisRequest) -> SynthesizedAudio:
@@ -137,50 +93,26 @@ class KokoroEngine:
     Factory for KokoroSession instances. Stateless and thread-safe.
     """
 
-    def __init__(self, pipeline: Any, lang_code: str) -> None:
+    def __init__(self, pipeline: Any) -> None:
         self._pipeline = pipeline
-        self._lang_code = lang_code
         self._disposed = False
 
     def createSession(self) -> KokoroSession:
         """Create a new KokoroSession."""
         if self._disposed:
             raise EngineError("Engine disposed")
-        return KokoroSession(self._pipeline, self._lang_code)
+        return KokoroSession(self._pipeline)
 
     def dispose(self) -> None:
         """Release engine resources. Idempotent."""
         self._disposed = True
 
     def listVoices(self, sourceId: str) -> list[VoiceManifest]:
-        """List available Kokoro voices. Implements VoiceLister capability."""
+        """List available Kokoro voices. Implements VoiceLister capability.
+
+        Note: Static voices are declared in the plugin manifest.
+        This method is a fallback for dynamic plugins.
+        """
         if self._disposed:
             raise EngineError("Engine disposed")
-        return [
+        return []
-            VoiceManifest(
-                id=voice_id,
-                name=_VOICE_DISPLAY_NAMES.get(voice_id, voice_id),
-                tags=(_get_language_tag(voice_id), _get_gender_tag(voice_id)),
-            )
-            for voice_id in _KOKORO_VOICES
-        ]
-
-
-def _get_language_tag(voice_id: str) -> str:
-    """Extract language tag from voice ID."""
-    prefix = voice_id.split("_")[0]
-    lang_map = {
-        "af": "en-us", "am": "en-us", "bf": "en-gb", "bm": "en-gb",
-        "ef": "es", "em": "es", "ff": "fr", "hf": "hi", "hm": "hi",
-        "if": "it", "im": "it", "jf": "ja", "jm": "ja",
-        "pf": "pt", "pm": "pt", "zf": "zh", "zm": "zh",
-    }
-    return lang_map.get(prefix, "unknown")
-
-
-def _get_gender_tag(voice_id: str) -> str:
-    """Extract gender tag from voice ID."""
-    prefix = voice_id.split("_")[0]
-    if prefix.startswith("a") or prefix.startswith("b") or prefix.startswith("e"):
-        return "female" if prefix[1] == "f" else "male"
-    return "unknown"

plugins/supertonic/__init__.py

@@ -24,6 +24,7 @@ from abogen.tts_plugin.manifest import (
     ParameterManifest,
     PluginManifest,
     RequirementManifest,
+    VoiceManifest,
     VoiceSourceManifest,
 )
 from abogen.tts_plugin.types import EngineConfig
@@ -31,14 +32,14 @@ from abogen.tts_plugin.types import EngineConfig
 from .engine import SuperTonicEngine
 
 
-def _load_supertonic_pipeline(sample_rate: int = 24000, auto_download: bool = True, total_steps: int = 5) -> Any:
+def _load_supertonic_pipeline() -> Any:
     """Lazy-load SuperTonic dependencies and create pipeline."""
     from plugins.supertonic.pipeline import SupertonicPipeline
 
     return SupertonicPipeline(
-        sample_rate=sample_rate,
+        sample_rate=24000,
-        auto_download=auto_download,
+        auto_download=True,
-        total_steps=total_steps,
+        total_steps=5,
     )
 
 
@@ -88,6 +89,18 @@ PLUGIN_MANIFEST = PluginManifest(
             AudioFormatManifest(mime="audio/wav", extension="wav"),
         ),
     ),
+    voices=(
+        VoiceManifest(id="M1", name="Male 1", tags=("male",)),
+        VoiceManifest(id="M2", name="Male 2", tags=("male",)),
+        VoiceManifest(id="M3", name="Male 3", tags=("male",)),
+        VoiceManifest(id="M4", name="Male 4", tags=("male",)),
+        VoiceManifest(id="M5", name="Male 5", tags=("male",)),
+        VoiceManifest(id="F1", name="Female 1", tags=("female",)),
+        VoiceManifest(id="F2", name="Female 2", tags=("female",)),
+        VoiceManifest(id="F3", name="Female 3", tags=("female",)),
+        VoiceManifest(id="F4", name="Female 4", tags=("female",)),
+        VoiceManifest(id="F5", name="Female 5", tags=("female",)),
+    ),
 )
 
 MODEL_REQUIREMENTS: list[ModelManifest] = []

plugins/supertonic/engine.py

@@ -8,42 +8,23 @@ from __future__ import annotations
 
 import io
 import logging
-from typing import Any, Optional
+from typing import Any
 
 import numpy as np
 
 from abogen.tts_plugin.capabilities import VoiceLister
 from abogen.tts_plugin.engine import Engine, EngineSession
-from abogen.tts_plugin.errors import EngineError, InvalidInputError
+from abogen.tts_plugin.errors import EngineError
 from abogen.tts_plugin.manifest import VoiceManifest
 from abogen.tts_plugin.types import (
     AudioFormat,
     Duration,
-    ParameterValues,
     SynthesisRequest,
     SynthesizedAudio,
-    VoiceSelection,
 )
 
 logger = logging.getLogger(__name__)
 
-# SuperTonic voice list - source of truth
-_SUPERTONIC_VOICES = ("M1", "M2", "M3", "M4", "M5", "F1", "F2", "F3", "F4", "F5")
-
-# Voice display names mapping
-_VOICE_DISPLAY_NAMES: dict[str, str] = {
-    "M1": "Male 1",
-    "M2": "Male 2",
-    "M3": "Male 3",
-    "M4": "Male 4",
-    "M5": "Male 5",
-    "F1": "Female 1",
-    "F2": "Female 2",
-    "F3": "Female 3",
-    "F4": "Female 4",
-    "F5": "Female 5",
-}
-
 # Sample rate for SuperTonic audio
 _SUPERTONIC_SAMPLE_RATE = 24000
 
@@ -134,23 +115,11 @@ class SuperTonicEngine:
         self._disposed = True
 
     def listVoices(self, sourceId: str) -> list[VoiceManifest]:
-        """List available SuperTonic voices. Implements VoiceLister capability."""
+        """List available SuperTonic voices. Implements VoiceLister capability.
+        
+        Note: Static voice catalog is declared in plugin manifest.
+        This method is retained for VoiceLister interface compliance.
+        """
         if self._disposed:
             raise EngineError("Engine disposed")
-        return [
+        return []
-            VoiceManifest(
-                id=voice_id,
-                name=_VOICE_DISPLAY_NAMES.get(voice_id, voice_id),
-                tags=(_get_gender_tag(voice_id),),
-            )
-            for voice_id in _SUPERTONIC_VOICES
-        ]
-
-
-def _get_gender_tag(voice_id: str) -> str:
-    """Extract gender tag from voice ID."""
-    if voice_id.startswith("M"):
-        return "male"
-    elif voice_id.startswith("F"):
-        return "female"
-    return "unknown"

tests/test_kokoro_plugin.py

@@ -57,7 +57,15 @@ def _make_mock_engine() -> Any:
                     return np.zeros(24000, dtype="float32")
             return [MockSegment()]
 
-    return KokoroEngine(MockPipeline(), "a")
+    engine = KokoroEngine(MockPipeline())
+
+    # Override listVoices for testing (real engine reads from manifest)
+    from abogen.tts_plugin.manifest import VoiceManifest
+    engine.listVoices = lambda source_id: [
+        VoiceManifest(id="test_voice_1", name="Test Voice 1", tags=("en",)),
+        VoiceManifest(id="test_voice_2", name="Test Voice 2", tags=("es",)),
+    ]
+    return engine
 
 
 # ──────────────────────────────────────────────────────────────