Make language support more robust

src/pipecat/services/aws.py

@@ -34,35 +34,77 @@ except ModuleNotFoundError as e:
 
 def language_to_aws_language(language: Language) -> str | None:
     language_map = {
+        # Arabic
+        Language.AR: "arb",
+        Language.AR_AE: "ar-AE",
+        # Catalan
         Language.CA: "ca-ES",
-        Language.ZH: "cmn-CN",
+        # Chinese
+        Language.ZH: "cmn-CN",  # Mandarin
+        Language.YUE: "yue-CN",  # Cantonese
+        Language.YUE_CN: "yue-CN",
+        # Czech
+        Language.CS: "cs-CZ",
+        # Danish
         Language.DA: "da-DK",
+        # Dutch
         Language.NL: "nl-NL",
         Language.NL_BE: "nl-BE",
-        Language.EN: "en-US",
+        # English
-        Language.EN_US: "en-US",
+        Language.EN: "en-US",  # Default to US English
         Language.EN_AU: "en-AU",
         Language.EN_GB: "en-GB",
-        Language.EN_NZ: "en-NZ",
         Language.EN_IN: "en-IN",
+        Language.EN_NZ: "en-NZ",
+        Language.EN_US: "en-US",
+        Language.EN_ZA: "en-ZA",
+        # Finnish
         Language.FI: "fi-FI",
+        # French
         Language.FR: "fr-FR",
+        Language.FR_BE: "fr-BE",
         Language.FR_CA: "fr-CA",
+        # German
         Language.DE: "de-DE",
+        Language.DE_AT: "de-AT",
+        Language.DE_CH: "de-CH",
+        # Hindi
         Language.HI: "hi-IN",
+        # Icelandic
+        Language.IS: "is-IS",
+        # Italian
         Language.IT: "it-IT",
+        # Japanese
         Language.JA: "ja-JP",
+        # Korean
         Language.KO: "ko-KR",
+        # Norwegian
         Language.NO: "nb-NO",
+        Language.NB: "nb-NO",
+        Language.NB_NO: "nb-NO",
+        # Polish
         Language.PL: "pl-PL",
+        # Portuguese
         Language.PT: "pt-PT",
         Language.PT_BR: "pt-BR",
+        Language.PT_PT: "pt-PT",
+        # Romanian
         Language.RO: "ro-RO",
+        # Russian
         Language.RU: "ru-RU",
+        # Spanish
         Language.ES: "es-ES",
+        Language.ES_MX: "es-MX",
+        Language.ES_US: "es-US",
+        # Swedish
         Language.SV: "sv-SE",
+        # Turkish
         Language.TR: "tr-TR",
+        # Welsh
+        Language.CY: "cy-GB",
+        Language.CY_GB: "cy-GB",
     }
+
     return language_map.get(language)
 
 

src/pipecat/services/azure.py

@@ -63,49 +63,325 @@ except ModuleNotFoundError as e:
 
 def language_to_azure_language(language: Language) -> str | None:
     language_map = {
+        # Afrikaans
+        Language.AF: "af-ZA",
+        Language.AF_ZA: "af-ZA",
+        # Amharic
+        Language.AM: "am-ET",
+        Language.AM_ET: "am-ET",
+        # Arabic
+        Language.AR: "ar-AE",  # Default to UAE Arabic
+        Language.AR_AE: "ar-AE",
+        Language.AR_BH: "ar-BH",
+        Language.AR_DZ: "ar-DZ",
+        Language.AR_EG: "ar-EG",
+        Language.AR_IQ: "ar-IQ",
+        Language.AR_JO: "ar-JO",
+        Language.AR_KW: "ar-KW",
+        Language.AR_LB: "ar-LB",
+        Language.AR_LY: "ar-LY",
+        Language.AR_MA: "ar-MA",
+        Language.AR_OM: "ar-OM",
+        Language.AR_QA: "ar-QA",
+        Language.AR_SA: "ar-SA",
+        Language.AR_SY: "ar-SY",
+        Language.AR_TN: "ar-TN",
+        Language.AR_YE: "ar-YE",
+        # Assamese
+        Language.AS: "as-IN",
+        Language.AS_IN: "as-IN",
+        # Azerbaijani
+        Language.AZ: "az-AZ",
+        Language.AZ_AZ: "az-AZ",
+        # Bulgarian
         Language.BG: "bg-BG",
+        Language.BG_BG: "bg-BG",
+        # Bengali
+        Language.BN: "bn-IN",  # Default to Indian Bengali
+        Language.BN_BD: "bn-BD",
+        Language.BN_IN: "bn-IN",
+        # Bosnian
+        Language.BS: "bs-BA",
+        Language.BS_BA: "bs-BA",
+        # Catalan
         Language.CA: "ca-ES",
-        Language.ZH: "zh-CN",
+        Language.CA_ES: "ca-ES",
-        Language.ZH_TW: "zh-TW",
+        # Czech
         Language.CS: "cs-CZ",
+        Language.CS_CZ: "cs-CZ",
+        # Welsh
+        Language.CY: "cy-GB",
+        Language.CY_GB: "cy-GB",
+        # Danish
         Language.DA: "da-DK",
-        Language.NL: "nl-NL",
+        Language.DA_DK: "da-DK",
-        Language.EN: "en-US",
+        # German
-        Language.EN_US: "en-US",
-        Language.EN_AU: "en-AU",
-        Language.EN_GB: "en-GB",
-        Language.EN_NZ: "en-NZ",
-        Language.EN_IN: "en-IN",
-        Language.ET: "et-EE",
-        Language.FI: "fi-FI",
-        Language.NL_BE: "nl-BE",
-        Language.FR: "fr-FR",
-        Language.FR_CA: "fr-CA",
         Language.DE: "de-DE",
+        Language.DE_AT: "de-AT",
         Language.DE_CH: "de-CH",
+        Language.DE_DE: "de-DE",
+        # Greek
         Language.EL: "el-GR",
+        Language.EL_GR: "el-GR",
+        # English
+        Language.EN: "en-US",  # Default to US English
+        Language.EN_AU: "en-AU",
+        Language.EN_CA: "en-CA",
+        Language.EN_GB: "en-GB",
+        Language.EN_HK: "en-HK",
+        Language.EN_IE: "en-IE",
+        Language.EN_IN: "en-IN",
+        Language.EN_KE: "en-KE",
+        Language.EN_NG: "en-NG",
+        Language.EN_NZ: "en-NZ",
+        Language.EN_PH: "en-PH",
+        Language.EN_SG: "en-SG",
+        Language.EN_TZ: "en-TZ",
+        Language.EN_US: "en-US",
+        Language.EN_ZA: "en-ZA",
+        # Spanish
+        Language.ES: "es-ES",  # Default to Spain Spanish
+        Language.ES_AR: "es-AR",
+        Language.ES_BO: "es-BO",
+        Language.ES_CL: "es-CL",
+        Language.ES_CO: "es-CO",
+        Language.ES_CR: "es-CR",
+        Language.ES_CU: "es-CU",
+        Language.ES_DO: "es-DO",
+        Language.ES_EC: "es-EC",
+        Language.ES_ES: "es-ES",
+        Language.ES_GQ: "es-GQ",
+        Language.ES_GT: "es-GT",
+        Language.ES_HN: "es-HN",
+        Language.ES_MX: "es-MX",
+        Language.ES_NI: "es-NI",
+        Language.ES_PA: "es-PA",
+        Language.ES_PE: "es-PE",
+        Language.ES_PR: "es-PR",
+        Language.ES_PY: "es-PY",
+        Language.ES_SV: "es-SV",
+        Language.ES_US: "es-US",
+        Language.ES_UY: "es-UY",
+        Language.ES_VE: "es-VE",
+        # Estonian
+        Language.ET: "et-EE",
+        Language.ET_EE: "et-EE",
+        # Basque
+        Language.EU: "eu-ES",
+        Language.EU_ES: "eu-ES",
+        # Persian
+        Language.FA: "fa-IR",
+        Language.FA_IR: "fa-IR",
+        # Finnish
+        Language.FI: "fi-FI",
+        Language.FI_FI: "fi-FI",
+        # Filipino
+        Language.FIL: "fil-PH",
+        Language.FIL_PH: "fil-PH",
+        # French
+        Language.FR: "fr-FR",
+        Language.FR_BE: "fr-BE",
+        Language.FR_CA: "fr-CA",
+        Language.FR_CH: "fr-CH",
+        Language.FR_FR: "fr-FR",
+        # Irish
+        Language.GA: "ga-IE",
+        Language.GA_IE: "ga-IE",
+        # Galician
+        Language.GL: "gl-ES",
+        Language.GL_ES: "gl-ES",
+        # Gujarati
+        Language.GU: "gu-IN",
+        Language.GU_IN: "gu-IN",
+        # Hebrew
+        Language.HE: "he-IL",
+        Language.HE_IL: "he-IL",
+        # Hindi
         Language.HI: "hi-IN",
+        Language.HI_IN: "hi-IN",
+        # Croatian
+        Language.HR: "hr-HR",
+        Language.HR_HR: "hr-HR",
+        # Hungarian
         Language.HU: "hu-HU",
+        Language.HU_HU: "hu-HU",
+        # Armenian
+        Language.HY: "hy-AM",
+        Language.HY_AM: "hy-AM",
+        # Indonesian
         Language.ID: "id-ID",
+        Language.ID_ID: "id-ID",
+        # Icelandic
+        Language.IS: "is-IS",
+        Language.IS_IS: "is-IS",
+        # Italian
         Language.IT: "it-IT",
+        Language.IT_IT: "it-IT",
+        # Inuktitut
+        Language.IU_CANS_CA: "iu-Cans-CA",
+        Language.IU_LATN_CA: "iu-Latn-CA",
+        # Japanese
         Language.JA: "ja-JP",
+        Language.JA_JP: "ja-JP",
+        # Javanese
+        Language.JV: "jv-ID",
+        Language.JV_ID: "jv-ID",
+        # Georgian
+        Language.KA: "ka-GE",
+        Language.KA_GE: "ka-GE",
+        # Kazakh
+        Language.KK: "kk-KZ",
+        Language.KK_KZ: "kk-KZ",
+        # Khmer
+        Language.KM: "km-KH",
+        Language.KM_KH: "km-KH",
+        # Kannada
+        Language.KN: "kn-IN",
+        Language.KN_IN: "kn-IN",
+        # Korean
         Language.KO: "ko-KR",
-        Language.LV: "lv-LV",
+        Language.KO_KR: "ko-KR",
+        # Lao
+        Language.LO: "lo-LA",
+        Language.LO_LA: "lo-LA",
+        # Lithuanian
         Language.LT: "lt-LT",
+        Language.LT_LT: "lt-LT",
+        # Latvian
+        Language.LV: "lv-LV",
+        Language.LV_LV: "lv-LV",
+        # Macedonian
+        Language.MK: "mk-MK",
+        Language.MK_MK: "mk-MK",
+        # Malayalam
+        Language.ML: "ml-IN",
+        Language.ML_IN: "ml-IN",
+        # Mongolian
+        Language.MN: "mn-MN",
+        Language.MN_MN: "mn-MN",
+        # Marathi
+        Language.MR: "mr-IN",
+        Language.MR_IN: "mr-IN",
+        # Malay
         Language.MS: "ms-MY",
+        Language.MS_MY: "ms-MY",
+        # Maltese
+        Language.MT: "mt-MT",
+        Language.MT_MT: "mt-MT",
+        # Burmese
+        Language.MY: "my-MM",
+        Language.MY_MM: "my-MM",
+        # Norwegian
+        Language.NB: "nb-NO",
+        Language.NB_NO: "nb-NO",
         Language.NO: "nb-NO",
+        # Nepali
+        Language.NE: "ne-NP",
+        Language.NE_NP: "ne-NP",
+        # Dutch
+        Language.NL: "nl-NL",
+        Language.NL_BE: "nl-BE",
+        Language.NL_NL: "nl-NL",
+        # Odia
+        Language.OR: "or-IN",
+        Language.OR_IN: "or-IN",
+        # Punjabi
+        Language.PA: "pa-IN",
+        Language.PA_IN: "pa-IN",
+        # Polish
         Language.PL: "pl-PL",
+        Language.PL_PL: "pl-PL",
+        # Pashto
+        Language.PS: "ps-AF",
+        Language.PS_AF: "ps-AF",
+        # Portuguese
         Language.PT: "pt-PT",
         Language.PT_BR: "pt-BR",
+        Language.PT_PT: "pt-PT",
+        # Romanian
         Language.RO: "ro-RO",
+        Language.RO_RO: "ro-RO",
+        # Russian
         Language.RU: "ru-RU",
+        Language.RU_RU: "ru-RU",
+        # Sinhala
+        Language.SI: "si-LK",
+        Language.SI_LK: "si-LK",
+        # Slovak
         Language.SK: "sk-SK",
-        Language.ES: "es-ES",
+        Language.SK_SK: "sk-SK",
+        # Slovenian
+        Language.SL: "sl-SI",
+        Language.SL_SI: "sl-SI",
+        # Somali
+        Language.SO: "so-SO",
+        Language.SO_SO: "so-SO",
+        # Albanian
+        Language.SQ: "sq-AL",
+        Language.SQ_AL: "sq-AL",
+        # Serbian
+        Language.SR: "sr-RS",
+        Language.SR_RS: "sr-RS",
+        Language.SR_LATN: "sr-Latn-RS",
+        Language.SR_LATN_RS: "sr-Latn-RS",
+        # Sundanese
+        Language.SU: "su-ID",
+        Language.SU_ID: "su-ID",
+        # Swedish
         Language.SV: "sv-SE",
+        Language.SV_SE: "sv-SE",
+        # Swahili
+        Language.SW: "sw-KE",
+        Language.SW_KE: "sw-KE",
+        Language.SW_TZ: "sw-TZ",
+        # Tamil
+        Language.TA: "ta-IN",
+        Language.TA_IN: "ta-IN",
+        Language.TA_LK: "ta-LK",
+        Language.TA_MY: "ta-MY",
+        Language.TA_SG: "ta-SG",
+        # Telugu
+        Language.TE: "te-IN",
+        Language.TE_IN: "te-IN",
+        # Thai
         Language.TH: "th-TH",
+        Language.TH_TH: "th-TH",
+        # Turkish
         Language.TR: "tr-TR",
+        Language.TR_TR: "tr-TR",
+        # Ukrainian
         Language.UK: "uk-UA",
+        Language.UK_UA: "uk-UA",
+        # Urdu
+        Language.UR: "ur-IN",
+        Language.UR_IN: "ur-IN",
+        Language.UR_PK: "ur-PK",
+        # Uzbek
+        Language.UZ: "uz-UZ",
+        Language.UZ_UZ: "uz-UZ",
+        # Vietnamese
         Language.VI: "vi-VN",
+        Language.VI_VN: "vi-VN",
+        # Wu Chinese
+        Language.WUU: "wuu-CN",
+        Language.WUU_CN: "wuu-CN",
+        # Yue Chinese
+        Language.YUE: "yue-CN",
+        Language.YUE_CN: "yue-CN",
+        # Chinese
+        Language.ZH: "zh-CN",
+        Language.ZH_CN: "zh-CN",
+        Language.ZH_CN_GUANGXI: "zh-CN-guangxi",
+        Language.ZH_CN_HENAN: "zh-CN-henan",
+        Language.ZH_CN_LIAONING: "zh-CN-liaoning",
+        Language.ZH_CN_SHAANXI: "zh-CN-shaanxi",
+        Language.ZH_CN_SHANDONG: "zh-CN-shandong",
+        Language.ZH_CN_SICHUAN: "zh-CN-sichuan",
+        Language.ZH_HK: "zh-HK",
+        Language.ZH_TW: "zh-TW",
+        # Zulu
+        Language.ZU: "zu-ZA",
+        Language.ZU_ZA: "zu-ZA",
     }
     return language_map.get(language)
 

src/pipecat/services/cartesia.py

@@ -44,24 +44,27 @@ except ModuleNotFoundError as e:
 
 
 def language_to_cartesia_language(language: Language) -> str | None:
-    language_map = {
+    BASE_LANGUAGES = {
         Language.DE: "de",
         Language.EN: "en",
-        Language.EN_US: "en",
-        Language.EN_GB: "en",
-        Language.EN_AU: "en",
-        Language.EN_NZ: "en",
-        Language.EN_IN: "en",
         Language.ES: "es",
         Language.FR: "fr",
-        Language.FR_CA: "fr",
         Language.JA: "ja",
         Language.PT: "pt",
-        Language.PT_BR: "pt",
         Language.ZH: "zh",
-        Language.ZH_TW: "zh",
     }
-    return language_map.get(language)
+
+    result = BASE_LANGUAGES.get(language)
+
+    # If not found in base languages, try to find the base language from a variant
+    if not result:
+        # Convert enum value to string and get the base language part (e.g. es-ES -> es)
+        lang_str = str(language.value)
+        base_code = lang_str.split("-")[0].lower()
+        # Look up the base code in our supported languages
+        result = base_code if base_code in BASE_LANGUAGES.values() else None
+
+    return result
 
 
 class CartesiaTTSService(WordTTSService):

src/pipecat/services/elevenlabs.py

@@ -43,24 +43,16 @@ ElevenLabsOutputFormat = Literal["pcm_16000", "pcm_22050", "pcm_24000", "pcm_441
 
 
 def language_to_elevenlabs_language(language: Language) -> str | None:
-    language_map = {
+    BASE_LANGUAGES = {
         Language.BG: "bg",
-        Language.ZH: "zh",
         Language.CS: "cs",
         Language.DA: "da",
-        Language.NL: "nl",
+        Language.DE: "de",
+        Language.EL: "el",
         Language.EN: "en",
-        Language.EN_US: "en",
+        Language.ES: "es",
-        Language.EN_AU: "en",
-        Language.EN_GB: "en",
-        Language.EN_NZ: "en",
-        Language.EN_IN: "en",
         Language.FI: "fi",
         Language.FR: "fr",
-        Language.FR_CA: "fr",
-        Language.DE: "de",
-        Language.DE_CH: "de",
-        Language.EL: "el",
         Language.HI: "hi",
         Language.HU: "hu",
         Language.ID: "id",
@@ -68,20 +60,31 @@ def language_to_elevenlabs_language(language: Language) -> str | None:
         Language.JA: "ja",
         Language.KO: "ko",
         Language.MS: "ms",
+        Language.NL: "nl",
         Language.NO: "no",
         Language.PL: "pl",
-        Language.PT: "pt-PT",
+        Language.PT: "pt",
-        Language.PT_BR: "pt-BR",
         Language.RO: "ro",
         Language.RU: "ru",
         Language.SK: "sk",
-        Language.ES: "es",
         Language.SV: "sv",
         Language.TR: "tr",
         Language.UK: "uk",
         Language.VI: "vi",
+        Language.ZH: "zh",
     }
-    return language_map.get(language)
+
+    result = BASE_LANGUAGES.get(language)
+
+    # If not found in base languages, try to find the base language from a variant
+    if not result:
+        # Convert enum value to string and get the base language part (e.g. es-ES -> es)
+        lang_str = str(language.value)
+        base_code = lang_str.split("-")[0].lower()
+        # Look up the base code in our supported languages
+        result = base_code if base_code in BASE_LANGUAGES.values() else None
+
+    return result
 
 
 def sample_rate_from_output_format(output_format: str) -> int:

src/pipecat/services/gladia.py

@@ -35,50 +35,98 @@ except ModuleNotFoundError as e:
 
 
 def language_to_gladia_language(language: Language) -> str | None:
-    language_map = {
+    BASE_LANGUAGES = {
+        Language.AF: "af",
+        Language.AM: "am",
+        Language.AR: "ar",
+        Language.AS: "as",
+        Language.AZ: "az",
         Language.BG: "bg",
+        Language.BN: "bn",
+        Language.BS: "bs",
         Language.CA: "ca",
-        Language.ZH: "zh",
         Language.CS: "cs",
+        Language.CY: "cy",
         Language.DA: "da",
-        Language.NL: "nl",
+        Language.DE: "de",
+        Language.EL: "el",
         Language.EN: "en",
-        Language.EN_US: "en",
+        Language.ES: "es",
-        Language.EN_AU: "en",
-        Language.EN_GB: "en",
-        Language.EN_NZ: "en",
-        Language.EN_IN: "en",
         Language.ET: "et",
+        Language.EU: "eu",
+        Language.FA: "fa",
         Language.FI: "fi",
         Language.FR: "fr",
-        Language.FR_CA: "fr",
+        Language.GA: "ga",
-        Language.DE: "de",
+        Language.GL: "gl",
-        Language.DE_CH: "de",
+        Language.GU: "gu",
-        Language.EL: "el",
+        Language.HE: "he",
         Language.HI: "hi",
+        Language.HR: "hr",
         Language.HU: "hu",
+        Language.HY: "hy",
         Language.ID: "id",
+        Language.IS: "is",
         Language.IT: "it",
         Language.JA: "ja",
+        Language.JV: "jv",
+        Language.KA: "ka",
+        Language.KK: "kk",
+        Language.KM: "km",
+        Language.KN: "kn",
         Language.KO: "ko",
-        Language.LV: "lv",
+        Language.LO: "lo",
         Language.LT: "lt",
+        Language.LV: "lv",
+        Language.MK: "mk",
+        Language.ML: "ml",
+        Language.MN: "mn",
+        Language.MR: "mr",
         Language.MS: "ms",
+        Language.MT: "mt",
+        Language.MY: "my",
+        Language.NE: "ne",
+        Language.NL: "nl",
         Language.NO: "no",
+        Language.OR: "or",
+        Language.PA: "pa",
         Language.PL: "pl",
+        Language.PS: "ps",
         Language.PT: "pt",
-        Language.PT_BR: "pt",
         Language.RO: "ro",
         Language.RU: "ru",
+        Language.SI: "si",
         Language.SK: "sk",
-        Language.ES: "es",
+        Language.SL: "sl",
+        Language.SO: "so",
+        Language.SQ: "sq",
+        Language.SR: "sr",
+        Language.SU: "su",
         Language.SV: "sv",
+        Language.SW: "sw",
+        Language.TA: "ta",
+        Language.TE: "te",
         Language.TH: "th",
         Language.TR: "tr",
         Language.UK: "uk",
+        Language.UR: "ur",
+        Language.UZ: "uz",
         Language.VI: "vi",
+        Language.ZH: "zh",
+        Language.ZU: "zu",
     }
-    return language_map.get(language)
+
+    result = BASE_LANGUAGES.get(language)
+
+    # If not found in base languages, try to find the base language from a variant
+    if not result:
+        # Convert enum value to string and get the base language part (e.g. es-ES -> es)
+        lang_str = str(language.value)
+        base_code = lang_str.split("-")[0].lower()
+        # Look up the base code in our supported languages
+        result = base_code if base_code in BASE_LANGUAGES.values() else None
+
+    return result
 
 
 class GladiaSTTService(STTService):

src/pipecat/services/google.py

@@ -58,48 +58,161 @@ except ModuleNotFoundError as e:
 
 def language_to_google_language(language: Language) -> str | None:
     language_map = {
+        # Afrikaans
+        Language.AF: "af-ZA",
+        Language.AF_ZA: "af-ZA",
+        # Arabic
+        Language.AR: "ar-XA",
+        # Bengali
+        Language.BN: "bn-IN",
+        Language.BN_IN: "bn-IN",
+        # Bulgarian
         Language.BG: "bg-BG",
+        Language.BG_BG: "bg-BG",
+        # Catalan
         Language.CA: "ca-ES",
+        Language.CA_ES: "ca-ES",
+        # Chinese (Mandarin and Cantonese)
         Language.ZH: "cmn-CN",
+        Language.ZH_CN: "cmn-CN",
         Language.ZH_TW: "cmn-TW",
+        Language.ZH_HK: "yue-HK",
+        # Czech
         Language.CS: "cs-CZ",
+        Language.CS_CZ: "cs-CZ",
+        # Danish
         Language.DA: "da-DK",
+        Language.DA_DK: "da-DK",
+        # Dutch
         Language.NL: "nl-NL",
+        Language.NL_BE: "nl-BE",
+        Language.NL_NL: "nl-NL",
+        # English
         Language.EN: "en-US",
         Language.EN_US: "en-US",
         Language.EN_AU: "en-AU",
         Language.EN_GB: "en-GB",
         Language.EN_IN: "en-IN",
+        # Estonian
         Language.ET: "et-EE",
+        Language.ET_EE: "et-EE",
+        # Filipino
+        Language.FIL: "fil-PH",
+        Language.FIL_PH: "fil-PH",
+        # Finnish
         Language.FI: "fi-FI",
-        Language.NL_BE: "nl-BE",
+        Language.FI_FI: "fi-FI",
+        # French
         Language.FR: "fr-FR",
         Language.FR_CA: "fr-CA",
+        Language.FR_FR: "fr-FR",
+        # Galician
+        Language.GL: "gl-ES",
+        Language.GL_ES: "gl-ES",
+        # German
         Language.DE: "de-DE",
+        Language.DE_DE: "de-DE",
+        # Greek
         Language.EL: "el-GR",
+        Language.EL_GR: "el-GR",
+        # Gujarati
+        Language.GU: "gu-IN",
+        Language.GU_IN: "gu-IN",
+        # Hebrew
+        Language.HE: "he-IL",
+        Language.HE_IL: "he-IL",
+        # Hindi
         Language.HI: "hi-IN",
+        Language.HI_IN: "hi-IN",
+        # Hungarian
         Language.HU: "hu-HU",
+        Language.HU_HU: "hu-HU",
+        # Icelandic
+        Language.IS: "is-IS",
+        Language.IS_IS: "is-IS",
+        # Indonesian
         Language.ID: "id-ID",
+        Language.ID_ID: "id-ID",
+        # Italian
         Language.IT: "it-IT",
+        Language.IT_IT: "it-IT",
+        # Japanese
         Language.JA: "ja-JP",
+        Language.JA_JP: "ja-JP",
+        # Kannada
+        Language.KN: "kn-IN",
+        Language.KN_IN: "kn-IN",
+        # Korean
         Language.KO: "ko-KR",
+        Language.KO_KR: "ko-KR",
+        # Latvian
         Language.LV: "lv-LV",
+        Language.LV_LV: "lv-LV",
+        # Lithuanian
         Language.LT: "lt-LT",
+        Language.LT_LT: "lt-LT",
+        # Malay
         Language.MS: "ms-MY",
+        Language.MS_MY: "ms-MY",
+        # Malayalam
+        Language.ML: "ml-IN",
+        Language.ML_IN: "ml-IN",
+        # Marathi
+        Language.MR: "mr-IN",
+        Language.MR_IN: "mr-IN",
+        # Norwegian
         Language.NO: "nb-NO",
+        Language.NB: "nb-NO",
+        Language.NB_NO: "nb-NO",
+        # Polish
         Language.PL: "pl-PL",
+        Language.PL_PL: "pl-PL",
+        # Portuguese
         Language.PT: "pt-PT",
         Language.PT_BR: "pt-BR",
+        Language.PT_PT: "pt-PT",
+        # Punjabi
+        Language.PA: "pa-IN",
+        Language.PA_IN: "pa-IN",
+        # Romanian
         Language.RO: "ro-RO",
+        Language.RO_RO: "ro-RO",
+        # Russian
         Language.RU: "ru-RU",
+        Language.RU_RU: "ru-RU",
+        # Serbian
+        Language.SR: "sr-RS",
+        Language.SR_RS: "sr-RS",
+        # Slovak
         Language.SK: "sk-SK",
+        Language.SK_SK: "sk-SK",
+        # Spanish
         Language.ES: "es-ES",
+        Language.ES_ES: "es-ES",
+        Language.ES_US: "es-US",
+        # Swedish
         Language.SV: "sv-SE",
+        Language.SV_SE: "sv-SE",
+        # Tamil
+        Language.TA: "ta-IN",
+        Language.TA_IN: "ta-IN",
+        # Telugu
+        Language.TE: "te-IN",
+        Language.TE_IN: "te-IN",
+        # Thai
         Language.TH: "th-TH",
+        Language.TH_TH: "th-TH",
+        # Turkish
         Language.TR: "tr-TR",
+        Language.TR_TR: "tr-TR",
+        # Ukrainian
         Language.UK: "uk-UA",
+        Language.UK_UA: "uk-UA",
+        # Vietnamese
         Language.VI: "vi-VN",
+        Language.VI_VN: "vi-VN",
     }
+
     return language_map.get(language)
 
 

src/pipecat/services/lmnt.py

@@ -36,24 +36,27 @@ except ModuleNotFoundError as e:
 
 
 def language_to_lmnt_language(language: Language) -> str | None:
-    language_map = {
+    BASE_LANGUAGES = {
         Language.DE: "de",
         Language.EN: "en",
-        Language.EN_US: "en",
-        Language.EN_AU: "en",
-        Language.EN_GB: "en",
-        Language.EN_NZ: "en",
-        Language.EN_IN: "en",
         Language.ES: "es",
         Language.FR: "fr",
-        Language.FR_CA: "fr",
-        Language.PT: "pt",
-        Language.PT_BR: "pt",
-        Language.ZH: "zh",
-        Language.ZH_TW: "zh",
         Language.KO: "ko",
+        Language.PT: "pt",
+        Language.ZH: "zh",
     }
-    return language_map.get(language)
+
+    result = BASE_LANGUAGES.get(language)
+
+    # If not found in base languages, try to find the base language from a variant
+    if not result:
+        # Convert enum value to string and get the base language part (e.g. es-ES -> es)
+        lang_str = str(language.value)
+        base_code = lang_str.split("-")[0].lower()
+        # Look up the base code in our supported languages
+        result = base_code if base_code in BASE_LANGUAGES.values() else None
+
+    return result
 
 
 class LmntTTSService(TTSService):

src/pipecat/services/xtts.py

@@ -7,6 +7,7 @@
 from typing import Any, AsyncGenerator, Dict
 
 import aiohttp
+from loguru import logger
 
 from pipecat.audio.utils import resample_audio
 from pipecat.frames.frames import (
@@ -20,9 +21,6 @@ from pipecat.frames.frames import (
 from pipecat.services.ai_services import TTSService
 from pipecat.transcriptions.language import Language
 
-from loguru import logger
-
-
 # The server below can connect to XTTS through a local running docker
 #
 # Docker command: $ docker run --gpus=all -e COQUI_TOS_AGREED=1 --rm -p 8000:80 ghcr.io/coqui-ai/xtts-streaming-server:latest-cuda121
@@ -32,15 +30,10 @@ from loguru import logger
 
 
 def language_to_xtts_language(language: Language) -> str | None:
-    language_map = {
+    BASE_LANGUAGES = {
         Language.CS: "cs",
         Language.DE: "de",
         Language.EN: "en",
-        Language.EN_US: "en",
-        Language.EN_AU: "en",
-        Language.EN_GB: "en",
-        Language.EN_NZ: "en",
-        Language.EN_IN: "en",
         Language.ES: "es",
         Language.FR: "fr",
         Language.HI: "hi",
@@ -51,12 +44,28 @@ def language_to_xtts_language(language: Language) -> str | None:
         Language.NL: "nl",
         Language.PL: "pl",
         Language.PT: "pt",
-        Language.PT_BR: "pt",
         Language.RU: "ru",
         Language.TR: "tr",
+        # Special case for Chinese base language
         Language.ZH: "zh-cn",
     }
-    return language_map.get(language)
+
+    result = BASE_LANGUAGES.get(language)
+
+    # If not found in base languages, try to find the base language from a variant
+    if not result:
+        # Convert enum value to string and get the base language part (e.g. es-ES -> es)
+        lang_str = str(language.value)
+        base_code = lang_str.split("-")[0].lower()
+
+        # Special handling for Chinese variants
+        if base_code == "zh":
+            result = "zh-cn"
+        else:
+            # Look up the base code in our supported languages
+            result = base_code if base_code in BASE_LANGUAGES.values() else None
+
+    return result
 
 
 class XTTSService(TTSService):

src/pipecat/transcriptions/language.py

@@ -5,7 +5,6 @@
 #
 
 import sys
-
 from enum import Enum
 
 if sys.version_info < (3, 11):
@@ -20,46 +19,411 @@ else:
 
 
 class Language(StrEnum):
-    BG = "bg"  # Bulgarian
+    # Afrikaans
-    CA = "ca"  # Catalan
+    AF = "af"
-    ZH = "zh"  # Chinese simplified
+    AF_ZA = "af-ZA"
-    ZH_TW = "zh-TW"  # Chinese traditional
+
-    CS = "cs"  # Czech
+    # Amharic
-    DA = "da"  # Danish
+    AM = "am"
-    NL = "nl"  # Dutch
+    AM_ET = "am-ET"
-    EN = "en"  # English
+
-    EN_US = "en-US"  # English (USA)
+    # Arabic
-    EN_AU = "en-AU"  # English (Australia)
+    AR = "ar"
-    EN_GB = "en-GB"  # English (Great Britain)
+    AR_AE = "ar-AE"
-    EN_NZ = "en-NZ"  # English (New Zealand)
+    AR_BH = "ar-BH"
-    EN_IN = "en-IN"  # English (India)
+    AR_DZ = "ar-DZ"
-    ET = "et"  # Estonian
+    AR_EG = "ar-EG"
-    FI = "fi"  # Finnish
+    AR_IQ = "ar-IQ"
-    NL_BE = "nl-BE"  # Flemmish
+    AR_JO = "ar-JO"
-    FR = "fr"  # French
+    AR_KW = "ar-KW"
-    FR_CA = "fr-CA"  # French (Canada)
+    AR_LB = "ar-LB"
-    DE = "de"  # German
+    AR_LY = "ar-LY"
-    DE_CH = "de-CH"  # German (Switzerland)
+    AR_MA = "ar-MA"
-    EL = "el"  # Greek
+    AR_OM = "ar-OM"
-    HI = "hi"  # Hindi
+    AR_QA = "ar-QA"
-    HU = "hu"  # Hungarian
+    AR_SA = "ar-SA"
-    ID = "id"  # Indonesian
+    AR_SY = "ar-SY"
-    IT = "it"  # Italian
+    AR_TN = "ar-TN"
-    JA = "ja"  # Japanese
+    AR_YE = "ar-YE"
-    KO = "ko"  # Korean
+
-    LV = "lv"  # Latvian
+    # Assamese
-    LT = "lt"  # Lithuanian
+    AS = "as"
-    MS = "ms"  # Malay
+    AS_IN = "as-IN"
-    NO = "no"  # Norwegian
+
-    PL = "pl"  # Polish
+    # Azerbaijani
-    PT = "pt"  # Portuguese
+    AZ = "az"
-    PT_BR = "pt-BR"  # Portuguese (Brazil)
+    AZ_AZ = "az-AZ"
-    RO = "ro"  # Romanian
+
-    RU = "ru"  # Russian
+    # Bulgarian
-    SK = "sk"  # Slovak
+    BG = "bg"
-    ES = "es"  # Spanish
+    BG_BG = "bg-BG"
-    SV = "sv"  # Swedish
+
-    TH = "th"  # Thai
+    # Bengali
-    TR = "tr"  # Turkish
+    BN = "bn"
-    UK = "uk"  # Ukrainian
+    BN_BD = "bn-BD"
-    VI = "vi"  # Vietnamese
+    BN_IN = "bn-IN"
+
+    # Bosnian
+    BS = "bs"
+    BS_BA = "bs-BA"
+
+    # Catalan
+    CA = "ca"
+    CA_ES = "ca-ES"
+
+    # Czech
+    CS = "cs"
+    CS_CZ = "cs-CZ"
+
+    # Welsh
+    CY = "cy"
+    CY_GB = "cy-GB"
+
+    # Danish
+    DA = "da"
+    DA_DK = "da-DK"
+
+    # German
+    DE = "de"
+    DE_AT = "de-AT"
+    DE_CH = "de-CH"
+    DE_DE = "de-DE"
+
+    # Greek
+    EL = "el"
+    EL_GR = "el-GR"
+
+    # English
+    EN = "en"
+    EN_AU = "en-AU"
+    EN_CA = "en-CA"
+    EN_GB = "en-GB"
+    EN_HK = "en-HK"
+    EN_IE = "en-IE"
+    EN_IN = "en-IN"
+    EN_KE = "en-KE"
+    EN_NG = "en-NG"
+    EN_NZ = "en-NZ"
+    EN_PH = "en-PH"
+    EN_SG = "en-SG"
+    EN_TZ = "en-TZ"
+    EN_US = "en-US"
+    EN_ZA = "en-ZA"
+
+    # Spanish
+    ES = "es"
+    ES_AR = "es-AR"
+    ES_BO = "es-BO"
+    ES_CL = "es-CL"
+    ES_CO = "es-CO"
+    ES_CR = "es-CR"
+    ES_CU = "es-CU"
+    ES_DO = "es-DO"
+    ES_EC = "es-EC"
+    ES_ES = "es-ES"
+    ES_GQ = "es-GQ"
+    ES_GT = "es-GT"
+    ES_HN = "es-HN"
+    ES_MX = "es-MX"
+    ES_NI = "es-NI"
+    ES_PA = "es-PA"
+    ES_PE = "es-PE"
+    ES_PR = "es-PR"
+    ES_PY = "es-PY"
+    ES_SV = "es-SV"
+    ES_US = "es-US"
+    ES_UY = "es-UY"
+    ES_VE = "es-VE"
+
+    # Estonian
+    ET = "et"
+    ET_EE = "et-EE"
+
+    # Basque
+    EU = "eu"
+    EU_ES = "eu-ES"
+
+    # Persian
+    FA = "fa"
+    FA_IR = "fa-IR"
+
+    # Finnish
+    FI = "fi"
+    FI_FI = "fi-FI"
+
+    # Filipino
+    FIL = "fil"
+    FIL_PH = "fil-PH"
+
+    # French
+    FR = "fr"
+    FR_BE = "fr-BE"
+    FR_CA = "fr-CA"
+    FR_CH = "fr-CH"
+    FR_FR = "fr-FR"
+
+    # Irish
+    GA = "ga"
+    GA_IE = "ga-IE"
+
+    # Galician
+    GL = "gl"
+    GL_ES = "gl-ES"
+
+    # Gujarati
+    GU = "gu"
+    GU_IN = "gu-IN"
+
+    # Hebrew
+    HE = "he"
+    HE_IL = "he-IL"
+
+    # Hindi
+    HI = "hi"
+    HI_IN = "hi-IN"
+
+    # Croatian
+    HR = "hr"
+    HR_HR = "hr-HR"
+
+    # Hungarian
+    HU = "hu"
+    HU_HU = "hu-HU"
+
+    # Armenian
+    HY = "hy"
+    HY_AM = "hy-AM"
+
+    # Indonesian
+    ID = "id"
+    ID_ID = "id-ID"
+
+    # Icelandic
+    IS = "is"
+    IS_IS = "is-IS"
+
+    # Italian
+    IT = "it"
+    IT_IT = "it-IT"
+
+    # Inuktitut
+    IU_CANS = "iu-Cans"
+    IU_CANS_CA = "iu-Cans-CA"
+    IU_LATN = "iu-Latn"
+    IU_LATN_CA = "iu-Latn-CA"
+
+    # Japanese
+    JA = "ja"
+    JA_JP = "ja-JP"
+
+    # Javanese
+    JV = "jv"
+    JV_ID = "jv-ID"
+
+    # Georgian
+    KA = "ka"
+    KA_GE = "ka-GE"
+
+    # Kazakh
+    KK = "kk"
+    KK_KZ = "kk-KZ"
+
+    # Khmer
+    KM = "km"
+    KM_KH = "km-KH"
+
+    # Kannada
+    KN = "kn"
+    KN_IN = "kn-IN"
+
+    # Korean
+    KO = "ko"
+    KO_KR = "ko-KR"
+
+    # Lao
+    LO = "lo"
+    LO_LA = "lo-LA"
+
+    # Lithuanian
+    LT = "lt"
+    LT_LT = "lt-LT"
+
+    # Latvian
+    LV = "lv"
+    LV_LV = "lv-LV"
+
+    # Macedonian
+    MK = "mk"
+    MK_MK = "mk-MK"
+
+    # Malayalam
+    ML = "ml"
+    ML_IN = "ml-IN"
+
+    # Mongolian
+    MN = "mn"
+    MN_MN = "mn-MN"
+
+    # Marathi
+    MR = "mr"
+    MR_IN = "mr-IN"
+
+    # Malay
+    MS = "ms"
+    MS_MY = "ms-MY"
+
+    # Maltese
+    MT = "mt"
+    MT_MT = "mt-MT"
+
+    # Burmese
+    MY = "my"
+    MY_MM = "my-MM"
+
+    # Norwegian
+    NB = "nb"
+    NB_NO = "nb-NO"
+    NO = "no"
+
+    # Nepali
+    NE = "ne"
+    NE_NP = "ne-NP"
+
+    # Dutch
+    NL = "nl"
+    NL_BE = "nl-BE"
+    NL_NL = "nl-NL"
+
+    # Odia
+    OR = "or"
+    OR_IN = "or-IN"
+
+    # Punjabi
+    PA = "pa"
+    PA_IN = "pa-IN"
+
+    # Polish
+    PL = "pl"
+    PL_PL = "pl-PL"
+
+    # Pashto
+    PS = "ps"
+    PS_AF = "ps-AF"
+
+    # Portuguese
+    PT = "pt"
+    PT_BR = "pt-BR"
+    PT_PT = "pt-PT"
+
+    # Romanian
+    RO = "ro"
+    RO_RO = "ro-RO"
+
+    # Russian
+    RU = "ru"
+    RU_RU = "ru-RU"
+
+    # Sinhala
+    SI = "si"
+    SI_LK = "si-LK"
+
+    # Slovak
+    SK = "sk"
+    SK_SK = "sk-SK"
+
+    # Slovenian
+    SL = "sl"
+    SL_SI = "sl-SI"
+
+    # Somali
+    SO = "so"
+    SO_SO = "so-SO"
+
+    # Albanian
+    SQ = "sq"
+    SQ_AL = "sq-AL"
+
+    # Serbian
+    SR = "sr"
+    SR_RS = "sr-RS"
+    SR_LATN = "sr-Latn"
+    SR_LATN_RS = "sr-Latn-RS"
+
+    # Sundanese
+    SU = "su"
+    SU_ID = "su-ID"
+
+    # Swedish
+    SV = "sv"
+    SV_SE = "sv-SE"
+
+    # Swahili
+    SW = "sw"
+    SW_KE = "sw-KE"
+    SW_TZ = "sw-TZ"
+
+    # Tagalog
+    TL = "tl"
+
+    # Tamil
+    TA = "ta"
+    TA_IN = "ta-IN"
+    TA_LK = "ta-LK"
+    TA_MY = "ta-MY"
+    TA_SG = "ta-SG"
+
+    # Telugu
+    TE = "te"
+    TE_IN = "te-IN"
+
+    # Thai
+    TH = "th"
+    TH_TH = "th-TH"
+
+    # Turkish
+    TR = "tr"
+    TR_TR = "tr-TR"
+
+    # Ukrainian
+    UK = "uk"
+    UK_UA = "uk-UA"
+
+    # Urdu
+    UR = "ur"
+    UR_IN = "ur-IN"
+    UR_PK = "ur-PK"
+
+    # Uzbek
+    UZ = "uz"
+    UZ_UZ = "uz-UZ"
+
+    # Vietnamese
+    VI = "vi"
+    VI_VN = "vi-VN"
+
+    # Wu Chinese
+    WUU = "wuu"
+    WUU_CN = "wuu-CN"
+
+    # Yue Chinese
+    YUE = "yue"
+    YUE_CN = "yue-CN"
+
+    # Chinese
+    ZH = "zh"
+    ZH_CN = "zh-CN"
+    ZH_CN_GUANGXI = "zh-CN-guangxi"
+    ZH_CN_HENAN = "zh-CN-henan"
+    ZH_CN_LIAONING = "zh-CN-liaoning"
+    ZH_CN_SHAANXI = "zh-CN-shaanxi"
+    ZH_CN_SHANDONG = "zh-CN-shandong"
+    ZH_CN_SICHUAN = "zh-CN-sichuan"
+    ZH_HK = "zh-HK"
+    ZH_TW = "zh-TW"
+
+    # Xhosa
+    XH = "xh"
+
+    # Zulu
+    ZU = "zu"
+    ZU_ZA = "zu-ZA"