fix(tts): trimite lang=ro explicit la Supertonic API

Parametrul `lang` era definit (DEFAULT_LANG = "ro") dar nu era inclus
in request-ul HTTP catre /v1/audio/speech. Adaugat "lang": lang in
body-ul JSON si lang="ro" explicit in _tts_synthesize().

OpenAPI-ul Supertonic confirma ca /v1/audio/speech accepta `lang`
ca parametru optional (OpenAISpeechRequest schema).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/fast_commands.py

@@ -800,7 +800,7 @@ def _tts_synthesize(text: str, voice: str) -> dict:
         import tts as _tts_mod
         # Re-import pentru a prinde modificări la hot-reload
         importlib.reload(_tts_mod)
-        return _tts_mod.synthesize(text, voice=voice)
+        return _tts_mod.synthesize(text, voice=voice, lang="ro")
     except ImportError as e:
         return {"ok": False, "error": f"tools/tts.py nu poate fi importat: {e}"}
     except Exception as e:

tools/tts.py

@@ -46,6 +46,7 @@ def synthesize(text: str, voice: str = DEFAULT_VOICE, lang: str = DEFAULT_LANG)
                 "input": text,
                 "voice": voice,
                 "response_format": "wav",
+                "lang": lang,
             },
             timeout=60.0,
         )