Jamulix: Optimierungen übernehmen, lokale Voice-Modelle ignorieren

app/dependencies.py

@@ -18,6 +18,7 @@ from app.providers.stt.faster_whisper import FasterWhisperProvider
 from app.providers.llm.local_openai_compatible import LocalOpenAICompatibleLLM
 from app.providers.llm.openrouter import OpenRouterLLMProvider
 from app.providers.tts.openrouter import OpenRouterTTSProvider
+from app.providers.tts.cartesia import CartesiaTTSProvider
 from app.providers.tts.chatterbox import ChatterboxTTSProvider
 from app.providers.tts.piper import PiperTTSProvider
 from app.providers.fallback import (
@@ -80,6 +81,10 @@ TTS_REGISTRY = {
         s.chatterbox_timeout,
         voices_dir=s.chatterbox_voices_dir,
     ),
+    "cartesia": lambda s: CartesiaTTSProvider(
+        s.cartesia_api_key, s.cartesia_voice_id, s.cartesia_tts_model, s.tts_sample_rate,
+        voices_str=s.cartesia_voices,
+    ),
     "piper": lambda s: PiperTTSProvider(
         s.piper_bin, s.piper_voices_dir, s.piper_voice, s.tts_sample_rate
     ),
@@ -151,32 +156,74 @@ ROUTE_KEYS = (
     "tts_provider",
     "language",
     "language_mode",
+    "voice_gender",
 )
 
-# Stimm-Auswahl nach Sprache: (effektive) Sprache → beste Piper-Stimme.
-# Gilt in BEIDEN Modi — die gesprochene Stimme folgt immer der Antwortsprache.
+# Stimm-Auswahl nach Sprache: (effektive) Sprache → beste Piper-Stimme (gender-agnostisch).
 LANG_TO_PIPER_VOICE: dict[str, str] = {
     "de":  "de_DE-thorsten-high",
     "en":  "en_US-lessac-high",
     "fr":  "fr_FR-siwis-medium",
     "es":  "es_ES-sharvard-medium",
     "it":  "it_IT-paola-medium",
-    "nl":  "nl_NL-mls-medium",
+    "pt":  "pt_BR-faber-medium",
+    "pl":  "pl_PL-darkman-medium",
+    "ar":  "ar_JO-kareem-medium",
     "ru":  "ru_RU-irina-medium",
     "zh":  "zh_CN-huayan-medium",
     "cmn": "zh_CN-huayan-medium",
 }
 
+# Geschlechtsspezifische Piper-Stimmen für Sprachen mit m+f Varianten.
+# Präzedenz: PIPER_VOICE_GENDERED > LANG_TO_PIPER_VOICE.
+# ES sharvard ist ein Multi-Speaker-Modell: #0=M, #1=F (speaker_id_map: {'M':0,'F':1})
+PIPER_VOICE_GENDERED: dict[tuple[str, str], str] = {
+    ("de", "f"): "de_DE-kerstin-low",
+    ("de", "m"): "de_DE-thorsten-high",
+    ("en", "f"): "en_US-amy-medium",
+    ("en", "m"): "en_US-lessac-high",
+    ("fr", "f"): "fr_FR-siwis-medium",
+    ("fr", "m"): "fr_FR-tom-medium",
+    ("es", "f"): "es_ES-sharvard-medium#1",
+    ("es", "m"): "es_ES-sharvard-medium#0",
+    ("it", "f"): "it_IT-paola-medium",
+    ("it", "m"): "it_IT-riccardo-x_low",
+    ("ru", "f"): "ru_RU-irina-medium",
+    ("ru", "m"): "ru_RU-ruslan-medium",
+    ("pl", "f"): "pl_PL-gosia-medium",
+    ("pl", "m"): "pl_PL-darkman-medium",
+}
+
 
 def piper_voice_for_language(tts_provider: str, language: str | None) -> str | None:
-    """Liefert die zur Sprache passende Piper-Stimme (sonst None → Provider-Default).
+    """Kompatibilitäts-Alias für voice_for_route ohne gender."""
+    return voice_for_route(tts_provider, language, "any")
 
-    Nur für Piper sinnvoll: Cloud-TTS (OpenRouter) und Chatterbox haben eigene
-    Stimmnamen (z. B. "Zephyr") und steuern die Sprache anders. Bei None nimmt der
-    jeweilige Provider seine konfigurierte Default-Stimme.
+
+def voice_for_route(
+    tts_provider: str, language: str | None, voice_gender: str = "any"
+) -> str | None:
+    """Liefert den voice-Parameter für synthesize() passend zum Provider.
+
+    - piper:    Piper-Stimmmodell-Name; geschlechtsspezifisch wenn Varianten vorhanden
+    - cartesia: Geschlechts-Code ("m"/"f"/"any") → CartesiaTTSProvider löst UUID auf
+    - andere:   None (Provider nutzt seinen eigenen Default)
     """
     if tts_provider == "piper" and language:
-        return LANG_TO_PIPER_VOICE.get(language)
+        lang = language.lower()
+        gender = (voice_gender or "any").lower()
+        # Geschlechtsspezifische Stimme: bevorzugte Richtung, dann Gegenteil
+        if gender in ("m", "f"):
+            candidates = [gender, "f" if gender == "m" else "m"]
+        else:  # "any" → weiblich bevorzugt (konsistent mit Cartesia)
+            candidates = ["f", "m"]
+        for g in candidates:
+            voice = PIPER_VOICE_GENDERED.get((lang, g))
+            if voice:
+                return voice
+        return LANG_TO_PIPER_VOICE.get(lang)
+    if tts_provider == "cartesia":
+        return voice_gender or "any"
     return None
 
 
@@ -189,6 +236,7 @@ class ResolvedRoute:
     tts_provider: str
     language: str
     language_mode: str = "fix"
+    voice_gender: str = "any"
 
     def as_dict(self) -> dict:
         return {
@@ -199,6 +247,7 @@ class ResolvedRoute:
             "tts_provider": self.tts_provider,
             "language": self.language,
             "language_mode": self.language_mode,
+            "voice_gender": self.voice_gender,
         }