languages.py

"""
Language configuration for PlotWeaver.
Three TTS/translation engines:
  1. "qwen" — Qwen 3.5 Omni (end-to-end speech-to-speech, best for global languages)
  2. "yourvoic" — YourVoic API (TTS only, paired with NLLB MT)
  3. "local" — Local MMS-TTS on GPU (for Yoruba, Hausa, etc.), paired with NLLB MT
"""

# Qwen Omni voices (work across all Qwen-supported languages)
QWEN_VOICES = [
    "Cherry", "Serena", "Ethan", "Chelsie", "Momo", "Vivian", "Moon", "Maia",
    "Kai", "Nofish", "Bella", "Jennifer", "Ryan", "Katerina", "Aiden",
    "Eldric Sage", "Mia", "Mochi", "Bellona", "Vincent", "Bunny", "Neil",
    "Elias", "Arthur", "Seren", "Bodega", "Sonrisa", "Alek", "Dolce",
    "Sohee", "Ono Anna", "Lenn", "Emilien", "Andre",
]

# Each language entry:
#   "Display Name": {
#       "nllb": NLLB-200 language code (for local/yourvoic pipeline translation),
#       "yourvoic_lang": YourVoic language code (or None),
#       "yourvoic_voices": list of YourVoic voice names,
#       "tts_engine": "qwen" | "yourvoic" | "local",
#       "qwen_code": short language code for Qwen prompts (or None),
#       "qwen_name": full language name for Qwen system prompt (or None),
#   }

LANGUAGES = {
    # ---- Global Languages (Qwen Omni — best quality) ----
    "Arabic": {
        "nllb": "arb_Arab", "yourvoic_lang": "ar-SA",
        "yourvoic_voices": ["Peter"], "tts_engine": "qwen",
        "qwen_code": "ar", "qwen_name": "Modern Standard Arabic (العربية الفصحى)",
    },
    "Spanish": {
        "nllb": "spa_Latn", "yourvoic_lang": "es-ES",
        "yourvoic_voices": ["Peter", "Kylie"], "tts_engine": "qwen",
        "qwen_code": "es", "qwen_name": "Spanish",
    },
    "French": {
        "nllb": "fra_Latn", "yourvoic_lang": "fr-FR",
        "yourvoic_voices": ["Peter", "Kylie"], "tts_engine": "qwen",
        "qwen_code": "fr", "qwen_name": "French",
    },
    "German": {
        "nllb": "deu_Latn", "yourvoic_lang": "de-DE",
        "yourvoic_voices": ["Peter", "Kylie"], "tts_engine": "qwen",
        "qwen_code": "de", "qwen_name": "German",
    },
    "Mandarin": {
        "nllb": "zho_Hans", "yourvoic_lang": "zh-CN",
        "yourvoic_voices": ["Peter", "Kylie"], "tts_engine": "qwen",
        "qwen_code": "zh", "qwen_name": "Mandarin Chinese",
    },
    "Italian": {
        "nllb": "ita_Latn", "yourvoic_lang": "it-IT",
        "yourvoic_voices": ["Peter", "Kylie"], "tts_engine": "qwen",
        "qwen_code": "it", "qwen_name": "Italian",
    },
    "Japanese": {
        "nllb": "jpn_Jpan", "yourvoic_lang": "ja-JP",
        "yourvoic_voices": ["Peter", "Kylie"], "tts_engine": "qwen",
        "qwen_code": "ja", "qwen_name": "Japanese",
    },
    "Portuguese": {
        "nllb": "por_Latn", "yourvoic_lang": "pt-BR",
        "yourvoic_voices": ["Peter", "Kylie"], "tts_engine": "qwen",
        "qwen_code": "pt", "qwen_name": "Portuguese",
    },
    "Hindi": {
        "nllb": "hin_Deva", "yourvoic_lang": "hi-IN",
        "yourvoic_voices": ["Rahul", "Deepika", "Aditya"], "tts_engine": "qwen",
        "qwen_code": "hi", "qwen_name": "Hindi",
    },
    "Korean": {
        "nllb": "kor_Hang", "yourvoic_lang": "ko-KR",
        "yourvoic_voices": ["Peter", "Kylie"], "tts_engine": "qwen",
        "qwen_code": "ko", "qwen_name": "Korean",
    },
    "Russian": {
        "nllb": "rus_Cyrl", "yourvoic_lang": "ru-RU",
        "yourvoic_voices": ["Peter", "Kylie"], "tts_engine": "qwen",
        "qwen_code": "ru", "qwen_name": "Russian",
    },

    # ---- African Languages (Local pipeline: Whisper → NLLB → MMS-TTS) ----
    "Yoruba": {
        "nllb": "yor_Latn", "yourvoic_lang": None,
        "yourvoic_voices": [], "tts_engine": "local",
        "qwen_code": None, "qwen_name": None,
    },
    "Hausa": {
        "nllb": "hau_Latn", "yourvoic_lang": None,
        "yourvoic_voices": [], "tts_engine": "local",
        "qwen_code": None, "qwen_name": None,
    },
    "Igbo": {
        "nllb": "ibo_Latn", "yourvoic_lang": None,
        "yourvoic_voices": [], "tts_engine": "local",
        "qwen_code": None, "qwen_name": None,
    },
    "Swahili": {
        "nllb": "swh_Latn", "yourvoic_lang": "sw-KE",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Zulu": {
        "nllb": "zul_Latn", "yourvoic_lang": None,
        "yourvoic_voices": [], "tts_engine": "local",
        "qwen_code": None, "qwen_name": None,
    },
    "Amharic": {
        "nllb": "amh_Ethi", "yourvoic_lang": "am-ET",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Afrikaans": {
        "nllb": "afr_Latn", "yourvoic_lang": "af-ZA",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },

    # ---- South Asian (YourVoic TTS + NLLB MT) ----
    "Bengali": {
        "nllb": "ben_Beng", "yourvoic_lang": "bn-IN",
        "yourvoic_voices": ["Sneha", "Aryan"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Tamil": {
        "nllb": "tam_Taml", "yourvoic_lang": "ta-IN",
        "yourvoic_voices": ["Priya", "Kumar"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Telugu": {
        "nllb": "tel_Telu", "yourvoic_lang": "te-IN",
        "yourvoic_voices": ["Arjun", "Lakshmi"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Marathi": {
        "nllb": "mar_Deva", "yourvoic_lang": "mr-IN",
        "yourvoic_voices": ["Anjali", "Rohan"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Urdu": {
        "nllb": "urd_Arab", "yourvoic_lang": "ur-PK",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Nepali": {
        "nllb": "npi_Deva", "yourvoic_lang": "ne-NP",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },

    # ---- Southeast Asian (YourVoic) ----
    "Indonesian": {
        "nllb": "ind_Latn", "yourvoic_lang": "id-ID",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Vietnamese": {
        "nllb": "vie_Latn", "yourvoic_lang": "vi-VN",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Thai": {
        "nllb": "tha_Thai", "yourvoic_lang": "th-TH",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Malay": {
        "nllb": "zsm_Latn", "yourvoic_lang": "ms-MY",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Filipino": {
        "nllb": "tgl_Latn", "yourvoic_lang": "fil-PH",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },

    # ---- European (YourVoic) ----
    "Dutch": {
        "nllb": "nld_Latn", "yourvoic_lang": "nl-NL",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Polish": {
        "nllb": "pol_Latn", "yourvoic_lang": "pl-PL",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Turkish": {
        "nllb": "tur_Latn", "yourvoic_lang": "tr-TR",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Swedish": {
        "nllb": "swe_Latn", "yourvoic_lang": "sv-SE",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Romanian": {
        "nllb": "ron_Latn", "yourvoic_lang": "ro-RO",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Greek": {
        "nllb": "ell_Grek", "yourvoic_lang": "el-GR",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Ukrainian": {
        "nllb": "ukr_Cyrl", "yourvoic_lang": "uk-UA",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Finnish": {
        "nllb": "fin_Latn", "yourvoic_lang": "fi-FI",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Danish": {
        "nllb": "dan_Latn", "yourvoic_lang": "da-DK",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Norwegian": {
        "nllb": "nob_Latn", "yourvoic_lang": "nb-NO",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },

    # ---- Middle Eastern (YourVoic) ----
    "Persian": {
        "nllb": "pes_Arab", "yourvoic_lang": "fa-IR",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
    "Hebrew": {
        "nllb": "heb_Hebr", "yourvoic_lang": "he-IL",
        "yourvoic_voices": ["Peter"], "tts_engine": "yourvoic",
        "qwen_code": None, "qwen_name": None,
    },
}


# Group languages by category for the UI
LANGUAGE_GROUPS = {
    "Global Languages": [
        "Spanish", "French", "German", "Mandarin", "Italian",
        "Japanese", "Portuguese", "Hindi", "Arabic", "Korean", "Russian",
    ],
    "African Languages": [
        "Yoruba", "Hausa", "Igbo", "Swahili", "Zulu", "Amharic", "Afrikaans",
    ],
    "South Asian": [
        "Bengali", "Tamil", "Telugu", "Marathi", "Urdu", "Nepali",
    ],
    "Southeast Asian": [
        "Indonesian", "Vietnamese", "Thai", "Malay", "Filipino",
    ],
    "European": [
        "Dutch", "Polish", "Turkish", "Swedish", "Romanian",
        "Greek", "Ukrainian", "Finnish", "Danish", "Norwegian",
    ],
    "Middle Eastern": [
        "Persian", "Hebrew",
    ],
}

# All language display names (for dropdowns)
ALL_LANGUAGE_NAMES = sorted(LANGUAGES.keys())

# Languages that use local TTS (your fine-tuned models)
LOCAL_TTS_LANGUAGES = [k for k, v in LANGUAGES.items() if v["tts_engine"] == "local"]

# Languages that use YourVoic API
YOURVOIC_LANGUAGES = [k for k, v in LANGUAGES.items() if v["tts_engine"] == "yourvoic"]