feat: Supertonic language + total_steps propagation

Language enum expanded from 9 to 33 languages:
- Added 24 new ISO 639-1 languages: AR, BG, CS, DA, DE, EL, ET, FI,
  HR, HU, ID, KO, LT, LV, NL, PL, RO, RU, SK, SL, SV, TR, UK, VI
- Updated display_name, is_cjk (added KO)

Supertonic language mapping (32 languages, no ZH):
- engine.py: _SUPERTONIC_LANG_MAP, engine_language(), supported_languages()
- __init__.py: create_engine() passes config.language to pipeline
- pipeline.py: __init__() accepts language, resolves to ISO code;
  __call__() passes lang= to TTS.synthesize()

total_steps propagation:
- tts_segments(): +total_steps param, conditionally passed to backend
- synthesize_text(): +total_steps param
- run_tts_segment_loop(): +total_steps param
- executor: all 5 synthesize_text() calls pass total_steps

Integration:
- pipeline_factory: create_pipeline_for_job() passes language to supertonic
- preview path: create_pipeline('supertonic', language=language)

Tests updated to accept total_steps in FakeBackend.__call__

abogen/application/conversion_executor.py

@@ -277,6 +277,7 @@ def execute_conversion(
                 backend=intro_backend,
                 voice=intro_voice,
                 speed=intro_speed or request.speed,
+                total_steps=intro_steps,
                 chapter_sink=None,
                 preview_callback=lambda text: events.log(f"  {text[:80]}"),
             )
@@ -347,6 +348,7 @@ def execute_conversion(
                     backend=intro_backend,
                     voice=intro_voice,
                     speed=intro_speed or request.speed,
+                    total_steps=intro_steps,
                     chapter_sink=chapter_sink,
                     preview_callback=lambda text: events.log(f"  Intro: {text[:80]}"),
                 )
@@ -421,6 +423,7 @@ def execute_conversion(
                     seg_provider = chapter_provider
                     seg_voice = chapter_voice
                     seg_speed = chapter_speed
+                    seg_steps = chapter_steps
                     seg_backend = chapter_backend
 
                 # Track voice for chapter marker
@@ -452,6 +455,7 @@ def execute_conversion(
                         backend=seg_backend,
                         voice=seg_voice,
                         speed=seg_speed or request.speed,
+                        total_steps=seg_steps,
                         chapter_sink=chapter_sink,
                         preview_callback=lambda text: events.log(f"  {text[:80]}"),
                         split_pattern_override=active_split,
@@ -539,6 +543,7 @@ def execute_conversion(
                 backend=outro_backend,
                 voice=outro_voice,
                 speed=outro_speed or request.speed,
+                total_steps=outro_steps,
                 chapter_sink=None,
                 preview_callback=lambda text: events.log(f"  {text[:80]}"),
             )

abogen/domain/conversion_engine.py

@@ -61,6 +61,7 @@ def run_tts_segment_loop(
     voice: Any,
     speed: float,
     split_pattern: str,
+    total_steps: Optional[int] = None,
     chapter_sink: Optional[AudioSink] = None,
     preview_callback: Optional[Callable[[str], None]] = None,
     on_segment: Optional[Callable[[SegmentInfo], None]] = None,
@@ -74,6 +75,7 @@ def run_tts_segment_loop(
         voice: Voice name/id for the backend.
         speed: Speech speed multiplier.
         split_pattern: Regex pattern used by the TTS engine for sentence splitting.
+        total_steps: Inference quality steps (Supertonic only, ignored by Kokoro).
         preview_callback: Called with a short preview string per segment.
         on_segment: Called with a SegmentInfo for each segment *before*
             audio is written.  Useful for callers that need per-segment
@@ -95,6 +97,7 @@ def run_tts_segment_loop(
         speed=speed,
         split_pattern=split_pattern,
         current_time=params.stats.current_time,
+        total_steps=total_steps,
     ):
         if params.check_cancel():
             break
@@ -212,6 +215,7 @@ def synthesize_text(
     backend: Any,
     voice: Any,
     speed: float,
+    total_steps: Optional[int] = None,
     chapter_sink: Optional[AudioSink] = None,
     preview_callback: Optional[Callable[[str], None]] = None,
     on_segment: Optional[Callable[[SegmentInfo], None]] = None,
@@ -229,6 +233,7 @@ def synthesize_text(
         backend=backend,
         voice=voice,
         speed=speed,
+        total_steps=total_steps,
         split_pattern=split_pattern_override or params.tts_context.split_pattern,
         chapter_sink=chapter_sink,
         preview_callback=preview_callback,

abogen/domain/conversion_pipeline.py

@@ -146,6 +146,7 @@ def tts_segments(
     speed: float,
     split_pattern: str,
     current_time: float = 0.0,
+    total_steps: Optional[int] = None,
 ) -> Iterator[SegmentResult]:
     """Invoke TTS backend on (already normalized) text and yield SegmentResults.
 
@@ -159,16 +160,20 @@ def tts_segments(
         speed: TTS speed multiplier.
         split_pattern: Regex pattern for sentence splitting.
         current_time: Current position in the audio timeline (seconds).
+        total_steps: Inference quality steps (Supertonic only, ignored by Kokoro).
 
     Yields:
         SegmentResult for each non-empty TTS segment.
     """
-    segment_iter = backend(
-        text,
+    kwargs: dict[str, Any] = dict(
         voice=voice,
         speed=speed,
         split_pattern=split_pattern,
     )
+    if total_steps is not None:
+        kwargs["total_steps"] = total_steps
+
+    segment_iter = backend(text, **kwargs)
 
     chunk_start = current_time
 
@@ -215,6 +220,7 @@ def emit_text_segments(
     speed: float,
     split_pattern: str,
     current_time: float = 0.0,
+    total_steps: Optional[int] = None,
     # normalization
     heteronym_rules: Any = None,
     pronunciation_rules: Any = None,
@@ -265,6 +271,7 @@ def emit_text_segments(
         speed=speed,
         split_pattern=split_pattern,
         current_time=current_time,
+        total_steps=total_steps,
     )
 
 

abogen/domain/enums.py

@@ -128,8 +128,8 @@ class InputFormat(str, Enum):
 class Language(str, Enum):
     """TTS language code (ISO 639-1 with region where needed).
 
-    Each engine (Kokoro, Supertonic) maps these to its own
-    internal language identifiers.
+    Each engine maps these to its own internal language identifiers.
+    Engines report which languages they support via ``supported_languages()``.
     """
     EN_US = "en-US"
     EN_GB = "en-GB"
@@ -140,6 +140,30 @@ class Language(str, Enum):
     JA = "ja"
     PT_BR = "pt-BR"
     ZH = "zh"
+    AR = "ar"
+    BG = "bg"
+    CS = "cs"
+    DA = "da"
+    DE = "de"
+    EL = "el"
+    ET = "et"
+    FI = "fi"
+    HR = "hr"
+    HU = "hu"
+    ID = "id"
+    KO = "ko"
+    LT = "lt"
+    LV = "lv"
+    NL = "nl"
+    PL = "pl"
+    RO = "ro"
+    RU = "ru"
+    SK = "sk"
+    SL = "sl"
+    SV = "sv"
+    TR = "tr"
+    UK = "uk"
+    VI = "vi"
 
     @property
     def display_name(self) -> str:
@@ -154,13 +178,37 @@ class Language(str, Enum):
             "ja": "Japanese",
             "pt-BR": "Brazilian Portuguese",
             "zh": "Mandarin Chinese",
+            "ar": "Arabic",
+            "bg": "Bulgarian",
+            "cs": "Czech",
+            "da": "Danish",
+            "de": "German",
+            "el": "Greek",
+            "et": "Estonian",
+            "fi": "Finnish",
+            "hr": "Croatian",
+            "hu": "Hungarian",
+            "id": "Indonesian",
+            "ko": "Korean",
+            "lt": "Lithuanian",
+            "lv": "Latvian",
+            "nl": "Dutch",
+            "pl": "Polish",
+            "ro": "Romanian",
+            "ru": "Russian",
+            "sk": "Slovak",
+            "sl": "Slovenian",
+            "sv": "Swedish",
+            "tr": "Turkish",
+            "uk": "Ukrainian",
+            "vi": "Vietnamese",
         }
         return _names[self.value]
 
     @property
     def is_cjk(self) -> bool:
-        """True for CJK languages (Chinese, Japanese)."""
-        return self in (self.ZH, self.JA)
+        """True for CJK languages (Chinese, Japanese, Korean)."""
+        return self in (self.ZH, self.JA, self.KO)
 
     @property
     def supports_subtitle_tokens(self) -> bool:

abogen/domain/pipeline_factory.py

@@ -45,7 +45,7 @@ def create_pipeline_for_job(
         provider = "kokoro"
 
     if provider == "supertonic":
-        return create_pipeline("supertonic")
+        return create_pipeline("supertonic", language=language)
 
     device = resolve_device(use_gpu)
     return create_pipeline("kokoro", language=language, device=device)

abogen/webui/routes/utils/synthesize.py

@@ -116,7 +116,7 @@ def generate_preview_audio(
     if provider == "supertonic":
         from abogen.tts_plugin.utils import create_pipeline
 
-        pipeline = create_pipeline("supertonic")
+        pipeline = create_pipeline("supertonic", language=language)
         segments = pipeline(
             normalized_text,
             voice=voice_spec,